Umeå universitets logga

umu.sePublikationer
Ändra sökning
Avgränsa sökresultatet
1234 1 - 50 av 168
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Abedin, Md Reaz Ashraful
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Bensch, Suna
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Hellström, Thomas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Self-supervised language grounding by active sensing combined with Internet acquired images and text2017Ingår i: Proceedings of the Fourth International Workshop on Recognition and Action for Scene Understanding (REACTS2017) / [ed] Jorge Dias George Azzopardi, Rebeca Marf, Málaga: REACTS , 2017, s. 71-83Konferensbidrag (Refereegranskat)
    Abstract [en]

    For natural and efficient verbal communication between a robot and humans, the robot should be able to learn names and appearances of new objects it encounters. In this paper we present a solution combining active sensing of images with text based and image based search on the Internet. The approach allows the robot to learn both object name and how to recognise similar objects in the future, all self-supervised without human assistance. One part of the solution is a novel iterative method to determine the object name using image classi- fication, acquisition of images from additional viewpoints, and Internet search. In this paper, the algorithmic part of the proposed solution is presented together with evaluations using manually acquired camera images, while Internet data was acquired through direct and reverse image search with Google, Bing, and Yandex. Classification with multi-classSVM and with five different features settings were evaluated. With five object classes, the best performing classifier used a combination of Pyramid of Histogram of Visual Words (PHOW) and Pyramid of Histogram of Oriented Gradient (PHOG) features, and reached a precision of 80% and a recall of 78%.

    Ladda ner fulltext (pdf)
    fulltext
  • 2.
    Alaa, Halawani
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Haibo, Li
    School of Computer Science & Communication, Royal Institute of Technology (KTH), Stockholm, Sweden.
    Template-based Search: A Tool for Scene Analysis2016Ingår i: 12th IEEE International Colloquium on Signal Processing & its Applications (CSPA): Proceeding, IEEE, 2016, artikel-id 7515772Konferensbidrag (Refereegranskat)
    Abstract [en]

    This paper proposes a simple and yet effective technique for shape-based scene analysis, in which detection and/or tracking of specific objects or structures in the image is desirable. The idea is based on using predefined binary templates of the structures to be located in the image. The template is matched to contours in a given edge image to locate the designated entity. These templates are allowed to deform in order to deal with variations in the structure's shape and size. Deformation is achieved by dividing the template into segments. The dynamic programming search algorithm is used to accomplish the matching process, achieving very robust results in cluttered and noisy scenes in the applications presented.

  • 3.
    Algers, Björn
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Stereo Camera Calibration Accuracy in Real-time Car Angles Estimation for Vision Driver Assistance and Autonomous Driving2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Bilsäkerhetsföretaget Veoneer är utvecklare av avancerade kamerasystem inom förarassistans, men kunskapen om den absoluta noggrannheten i deras dynamiska kalibreringsalgoritmer som skattar fordonets orientering är begränsad.

    I denna avhandling utvecklas och testas ett nytt mätsystem för att samla in referensdata av ett fordons orientering när det är i rörelse, mer specifikt dess pitchvinkel och rollvinkel. Fokus har legat på att skatta hur osäkerheten i mätsystemet påverkas av fel som introducerats vid dess konstruktion, samt att utreda dess potential när det kommer till att vara ett gångbart alternativ för att samla in referensdata för evaluering av prestandan hos algoritmerna.

    Systemet bestod av tre laseravståndssensorer monterade på fordonets kaross. En rad mätförsök utfördes med olika störningar introducerade genom att köra längs en vägsträcka i Linköping med vikter lastade i fordonet. Det insamlade referensdatat jämfördes med data från kamerasystemet där bias hos de framräknade vinklarna skattades, samt att de dynamiska egenskaperna kamerasystemets algoritmer utvärderades. Resultaten från mätförsöken visade på att noggrannheten i mätsystemet översteg 0.1 grader för både pitchvinklarna och rollvinklarna, men några slutsatser kring eventuell bias hos algoritmerna kunde ej dras då systematiska fel uppstått i mätresultaten.

    Ladda ner fulltext (pdf)
    fulltext
  • 4.
    Ali, Hazrat
    et al.
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Umander, Johannes
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Rohlén, Robin
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Grönlund, Christer
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    A Deep Learning Pipeline for Identification of Motor Units in Musculoskeletal Ultrasound2020Ingår i: IEEE Access, E-ISSN 2169-3536, Vol. 8, s. 170595-170608Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Skeletal muscles are functionally regulated by populations of so-called motor units (MUs). An MU comprises a bundle of muscle fibers controlled by a neuron from the spinal cord. Current methods to diagnose neuromuscular diseases and monitor rehabilitation, and study sports sciences rely on recording and analyzing the bio-electric activity of the MUs. However, these methods provide information from a limited part of a muscle. Ultrasound imaging provides information from a large part of the muscle. It has recently been shown that ultrafast ultrasound imaging can be used to record and analyze the mechanical response of individual MUs using blind source separation. In this work, we present an alternative method - a deep learning pipeline - to identify active MUs in ultrasound image sequences, including segmentation of their territories and signal estimation of their mechanical responses (twitch train). We train and evaluate the model using simulated data mimicking the complex activation pattern of tens of activated MUs with overlapping territories and partially synchronized activation patterns. Using a slow fusion approach (based on 3D CNNs), we transform the spatiotemporal image sequence data to 2D representations and apply a deep neural network architecture for segmentation. Next, we employ a second deep neural network architecture for signal estimation. The results show that the proposed pipeline can effectively identify individual MUs, estimate their territories, and estimate their twitch train signal at low contraction forces. The framework can retain spatio-temporal consistencies and information of the mechanical response of MU activity even when the ultrasound image sequences are transformed into a 2D representation for compatibility with more traditional computer vision and image processing techniques. The proposed pipeline is potentially useful to identify simultaneously active MUs in whole muscles in ultrasound image sequences of voluntary skeletal muscle contractions at low force levels.

    Ladda ner fulltext (pdf)
    fulltext
  • 5.
    AliNazari, Mirian
    Umeå universitet, Fakultet för lärarutbildning, Institutionen för estetiska ämnen.
    Kreativ Uppväxtmiljö: en studie av stadieteorier2007Självständigt arbete på grundnivå (yrkesexamen), 10 poäng / 15 hpStudentuppsats
    Abstract [sv]

    I examensarbetet studerades bildutveckling som även jämförts med författarens egen uppväxtmiljö. Metoden har varit en litteraturstudie som behandlar ämnet estetiska uttrycksformer och kreativ uppväxt. Därtill har en granskning av författarens uppväxtmiljö gällande möjlighet till övande av kreativ förmåga tagits upp i relation till personlig utveckling. Jämförelse har gjorts med stadieteorier om utvecklande av barns bildanvändning. Genom dokumenterade av författarens egna bilder under tidiga år visades bildutveckling i de olika teckningsutvecklingsstadierna. Slutsatsen är att kreativ förmåga påverkas sannolikt av uppfostran fylld med möjligheten att få måla och teckna, något som bildlärare kan utveckla i arbetet med barn. Behov att som blivande lärare integrera bilden i de teoretiska ämnena kan utveckla dessa möjligheter ytterligare.

    Ladda ner fulltext (pdf)
    FULLTEXT01
  • 6.
    Andersson, Axel
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Real-Time Feedback for Agility Training: Tracking of reflective markers using a time-of-flight camera2017Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
  • 7.
    Andersson, Jennifer
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Servin, Martin
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Predicting Gripability Heatmaps using Conditional GANs2021Rapport (Övrigt vetenskapligt)
    Abstract [en]

    The feasibility of using conditional GANs (Generative Adversarial Networks) to predict gripability in log piles is investigated. This is done by posing gripability heatmap prediction from RGB-D data as an image-to-image translation problem. Conditional GANs have previously achieved impressive results on several image-to-image translation tasks predicting physical properties and adding details not present in the input images. Here, piles of logs modelled as sticks or rods are generated in simulation, and groundtruth gripability maps are created using a simple algorithm streamlining the datacollection process. A modified SSIM (Structural Similarity Index) is used to evaluate the quality of the gripability heatmap predictions. The results indicate promising model performance on several different datasets and heatmap designs, including using base plane textures from a real forest production site to add realistic noise in the RGB data. Including a depth channel in the input data is shown to increase performance compared to using pure RGB data. The implementation is based on the general Pix2Pix network developed by Isola et al. in 2017. However, there is potential to increase performance and model generalization, and the adoption of more advanced loss functions and network architectures are suggested. Next steps include using terrains reconstructed from highdensity laser scans in physics-based simulation for data generation. A more in-depth discussion regarding the level of sophistication required in the gripability heatmaps should also be carried out, along with discussions regarding other specifications that will be required for future deployment. This will enable derivation of a tailored gripability metric for ground-truth heatmap generation, and method evaluation on less ideal data.

    Ladda ner fulltext (pdf)
    fulltext
  • 8.
    Aoshima, Koji
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik. Komatsu Ltd..
    Fälldin, Arvid
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Wadbro, Eddie
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Karlstad University, Sweden.
    Servin, Martin
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik. Algoryx Simulation.
    Data-driven models for predicting the outcome of autonomous wheel loader operationsManuskript (preprint) (Övrigt vetenskapligt)
    Abstract [en]

    This paper presents a method using data-driven models for selecting actions and predicting the total performance of autonomous wheel loader operations over many loading cycles in a changing environment. The performance includes loaded mass, loading time, work. The data-driven models input the control parameters of a loading action and the heightmap of the initial pile state to output the inference of either the performance or the resulting pile state. By iteratively utilizing the resulting pile state as the initial pile state for consecutive predictions, the prediction method enables long-horizon forecasting. Deep neural networks were trained on data from over 10,000 random loading actions in gravel piles of different shapes using 3D multibody dynamics simulation. The models predict the performance and the resulting pile state with, on average, 95% accuracy in 1.2 ms, and 97% in 4.5 ms, respectively. The performance prediction was found to be even faster in exchange for accuracy by reducing the model size with the lower dimensional representation of the pile state using its slope and curvature. The feasibility of long-horizon predictions was confirmed with 40 sequential loading actions at a large pile. With the aid of a physics-based model, the pile state predictions are kept sufficiently accurate for longer-horizon use.

  • 9.
    Aoshima, Koji
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Lindmark, Daniel
    Algoryx Simulation AB.
    Servin, Martin
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Examining the simulation-to-reality-gap of a wheel loader interacting with deformable terrain2022Konferensbidrag (Övrigt vetenskapligt)
    Abstract [en]

    Simulators are essential for developing autonomous control of off-road vehicles and heavy equipment. They allow automatic testing under safe and controllable conditions, and the generation of large amounts of synthetic and annotated training data necessary for deep learning to be applied [1]. Limiting factors are the computational speed and how accurately the simulator reflects the real system. When the deviation is too large, a controller transfers poorly from the simulated to the real environment. On the other hand, a finely resolved simulator easily becomes too computationally intense and slow for running the necessary number of simulations or keeping realtime pace with hardware in the loop.

    We investigate how well a physics-based simulator can be made to match its physical counterpart, a full-scale wheel loader instrumented with motion and force sensors performing a bucket filling operation [2]. The simulated vehicle is represented as a rigid multibody system with nonsmooth contact and driveline dynamics. The terrain model combines descriptions of the frictional-cohesive soil as a continuous solid and particles, discretized in voxels and discrete elements [3]. Strong and stable force coupling with the equipment is mediated via rigid aggregate bodies capturing the bulk mechanics of the soil. The results include analysis of the agreement between a calibrated simulation model and the field tests, and of how the simulation performance and accuracy depend on spatial and temporal resolution. The system’s degrees of freedom range from hundreds to millions and the simulation speed up to ten times faster than realtime. Furthermore, it is investigated how sensitive a deep learning controller is to variations in the simulator environment parameters.

    [1]  S. Backman, D. Lindmark, K. Bodin, M. Servin, J. Mörk, and H. Löfgren. Continuous control of an underground loader using deep reinforcement learning. Machines 9(10): 216 (2021).

    [2]  K. Aoshima, M. Servin, E. Wadbro. Simulation-Based Optimization of High-Performance Wheel Loading. Proc. 38th Int. Symp. Automation and Robotics in Construction (ISARC), Dubai, UAE (2021).

    [3]  M. Servin., T. Berglund., and S. Nystedt. A multiscale model of terrain dynamics for real-time earthmoving simulation. Advanced Modeling and Simulation in Engineering Sciences 8, 11 (2021). 

  • 10.
    Becher, Marina
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för ekologi, miljö och geovetenskap.
    Börlin, Niclas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Klaminder, Jonatan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för ekologi, miljö och geovetenskap.
    Measuring soil motion with terrestrial close range photogrammetry in periglacial environments2014Ingår i: EUCOP 4: Book of Abstracts / [ed] Gonçalo Vieira, Pedro Pina, Carla Mora and António Correia, University of Lisbon and the University of Évora , 2014, s. 351-351Konferensbidrag (Övrigt vetenskapligt)
    Abstract [en]

    Cryoturbation plays an important role in the carbon cycle as it redistributes carbon deeper down in the soil where the cold temperature prevents microbial decomposition. This contribution is also included in recent models describing the long-term build up of carbon stocks in artic soils. Soil motion rate in cryoturbated soils is sparsely studied. This is because the internal factors maintaining cryoturbation will be affected by any excavation, making it impossible to remove soil samples or install pegs without changing the structure of the soil. So far, mainly the motion of soil surface markers on patterned ground has been used to infer lateral soil motion rates. However, such methods constrain the investigated area to a predetermined distribution of surface markers that may result in a loss of information regarding soil motion in other parts of the patterned ground surface.

    We present a novel method based on terrestrial close range (<5m) photogrammetry to calculate lateral and vertical soil motion across entire small-scale periglacial features, such as non-sorted circles (frost boils). Images were acquired by a 5-camera calibrated rig from at least 8 directions around a non-sorted circle. During acquisition, the rig was carried by one person in a backpack-like portable camera support system. Natural feature points were detected by SIFT and matched between images using the known epipolar geometry of the calibrated rig. The 3D coordinates of points matched between at least 3 images were calculated to create a point cloud of the surface of interest. The procedure was repeated during two consecutive years to be able to measure any net displacement of soil and calculate rates of soil motion. The technique was also applied to a peat palsa where multiple exposures where acquired of selected areas.

    The method has the potential to quantify areas of disturbance and estimate lateral and vertical soil motion in non-sorted circles. Furthermore, it should be possible to quantify peat erosion and rates of desiccation crack formations in peat palsas. This tool could provide new information about cryoturbation rates that could improve existing soil carbon models and increase our understanding about how soil carbon stocks will respond to climate change.

  • 11.
    Billing, Erik
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Cognition Rehearsed: Recognition and Reproduction of Demonstrated Behavior2012Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    The work presented in this dissertation investigates techniques for robot Learning from Demonstration (LFD). LFD is a well established approach where the robot is to learn from a set of demonstrations. The dissertation focuses on LFD where a human teacher demonstrates a behavior by controlling the robot via teleoperation. After demonstration, the robot should be able to reproduce the demonstrated behavior under varying conditions. In particular, the dissertation investigates techniques where previous behavioral knowledge is used as bias for generalization of demonstrations.

    The primary contribution of this work is the development and evaluation of a semi-reactive approach to LFD called Predictive Sequence Learning (PSL). PSL has many interesting properties applied as a learning algorithm for robots. Few assumptions are introduced and little task-specific configuration is needed. PSL can be seen as a variable-order Markov model that progressively builds up the ability to predict or simulate future sensory-motor events, given a history of past events. The knowledge base generated during learning can be used to control the robot, such that the demonstrated behavior is reproduced. The same knowledge base can also be used to recognize an on-going behavior by comparing predicted sensor states with actual observations. Behavior recognition is an important part of LFD, both as a way to communicate with the human user and as a technique that allows the robot to use previous knowledge as parts of new, more complex, controllers.

    In addition to the work on PSL, this dissertation provides a broad discussion on representation, recognition, and learning of robot behavior. LFD-related concepts such as demonstration, repetition, goal, and behavior are defined and analyzed, with focus on how bias is introduced by the use of behavior primitives. This analysis results in a formalism where LFD is described as transitions between information spaces. Assuming that the behavior recognition problem is partly solved, ways to deal with remaining ambiguities in the interpretation of a demonstration are proposed.

    The evaluation of PSL shows that the algorithm can efficiently learn and reproduce simple behaviors. The algorithm is able to generalize to previously unseen situations while maintaining the reactive properties of the system. As the complexity of the demonstrated behavior increases, knowledge of one part of the behavior sometimes interferes with knowledge of another parts. As a result, different situations with similar sensory-motor interactions are sometimes confused and the robot fails to reproduce the behavior.

    One way to handle these issues is to introduce a context layer that can support PSL by providing bias for predictions. Parts of the knowledge base that appear to fit the present context are highlighted, while other parts are inhibited. Which context should be active is continually re-evaluated using behavior recognition. This technique takes inspiration from several neurocomputational models that describe parts of the human brain as a hierarchical prediction system. With behavior recognition active, continually selecting the most suitable context for the present situation, the problem of knowledge interference is significantly reduced and the robot can successfully reproduce also more complex behaviors.

    Ladda ner fulltext (pdf)
    Introduction chapters
  • 12.
    Billing, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Hellström, Thomas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Janlert, Lars Erik
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Robot learning from demonstration using predictive sequence learning2011Ingår i: Robotic systems: applications, control and programming / [ed] Ashish Dutta, Kanpur, India: IN-TECH, 2011, s. 235-250Kapitel i bok, del av antologi (Refereegranskat)
    Abstract [en]

    In this chapter, the prediction algorithm Predictive Sequence Learning (PSL) is presented and evaluated in a robot Learning from Demonstration (LFD) setting. PSL generates hypotheses from a sequence of sensory-motor events. Generated hypotheses can be used as a semi-reactive controller for robots. PSL has previously been used as a method for LFD, but suffered from combinatorial explosion when applied to data with many dimensions, such as high dimensional sensor and motor data. A new version of PSL, referred to as Fuzzy Predictive Sequence Learning (FPSL), is presented and evaluated in this chapter. FPSL is implemented as a Fuzzy Logic rule base and works on a continuous state space, in contrast to the discrete state space used in the original design of PSL. The evaluation of FPSL shows a significant performance improvement in comparison to the discrete version of the algorithm. Applied to an LFD task in a simulated apartment environment, the robot is able to learn to navigate to a specific location, starting from an unknown position in the apartment.

  • 13. Billing, Erik
    et al.
    Hellström, Thomas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Janlert, Lars-Erik
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Simultaneous recognition and reproduction of demonstrated behavior2015Ingår i: Biologically Inspired Cognitive Architectures, ISSN 2212-683X, Vol. 12, s. 43-53Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Predictions of sensory-motor interactions with the world is often referred to as a key component in cognition. We here demonstrate that prediction of sensory-motor events, i.e., relationships between percepts and actions, is sufficient to learn navigation skills for a robot navigating in an apartment environment. In the evaluated application, the simulated Robosoft Kompai robot learns from human demonstrations. The system builds fuzzy rules describing temporal relations between sensory-motor events recorded while a human operator is tele-operating the robot. With this architecture, referred to as Predictive Sequence Learning (PSL), learned associations can be used to control the robot and to predict expected sensor events in response to executed actions. The predictive component of PSL is used in two ways: (1) to identify which behavior that best matches current context and (2) to decide when to learn, i.e., update the confidence of different sensory-motor associations. Using this approach, knowledge interference due to over-fitting of an increasingly complex world model can be avoided. The system can also automatically estimate the confidence in the currently executed behavior and decide when to switch to an alternate behavior. The performance of PSL as a method for learning from demonstration is evaluated with, and without, contextual information. The results indicate that PSL without contextual information can learn and reproduce simple behaviors, but fails when the behavioral repertoire becomes more diverse. When a contextual layer is added, PSL successfully identifies the most suitable behavior in almost all test cases. The robot's ability to reproduce more complex behaviors, with partly overlapping and conflicting information, significantly increases with the use of contextual information. The results support a further development of PSL as a component of a dynamic hierarchical system performing control and predictions on several levels of abstraction.

  • 14.
    Bokman, Georg
    et al.
    Chalmers University of Technology, Department of Electrical Engineering, Sweden.
    Kahla, Fredrik
    Chalmers University of Technology, Department of Electrical Engineering, Sweden.
    Flinth, Axel
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för matematik och matematisk statistik. Chalmers University of Technology, Department of Electrical Engineering, Sweden.
    ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds2022Ingår i: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 2022, s. 10966-10975Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper, we are concerned with rotation equivariance on 2D point cloud data. We describe a particular set of functions able to approximate any continuous rotation equivariant and permutation invariant function. Based on this result, we propose a novel neural network architecture for processing 2D point clouds and we prove its universality for approximating functions exhibiting these symmetries. We also show how to extend the architecture to accept a set of 2D-2D correspondences as indata, while maintaining similar equivariance properties. Experiments are presented on the estimation of essential matrices in stereo vision.

  • 15.
    Boman, Jimmy
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    A deep learning approach to defect detection with limited data availability2020Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    In industrial processes, products are often visually inspected for defects inorder to verify their quality. Many automated visual inspection algorithms exist, and in many cases humans still perform the inspections. Advances in machine learning have showed that deep learning methods lie at the forefront of reliability and accuracy in such inspection tasks. In order to detect defects, most deep learning methods need large amounts of training data to learn from. This makes demonstrating such methods to a new customer problematic, since such data often does not exist beforehand, and has to be gathered specifically for the task. The aim of this thesis is to develop a method to perform such demonstrations. With access to only a small dataset, the method should be able to analyse an image and return a map of binary values, signifying which pixels in the original image belong to a defect and which do not. A method was developed that divides an image into overlapping patches, and analyses each patch individually for defects, using a deep learning method. Three different deep learning methods for classifying the patches were evaluated; a convolutional neural network, a transfer learning model based on the VGG19 network, and an autoencoder. The three methods were first compared in a simple binary classification task, without the patching method. They were then tested together with the patching method on two sets of images. The transfer learning model was able to identify every defect across both tests, having been trained using only four training images, proving that defect detection with deep learning can be done successfully even when there is not much training data available.

    Ladda ner fulltext (pdf)
    fulltext
  • 16. Bontsema, Jan
    et al.
    Hemming, Jochen
    Pekkeriet, Erik
    Saeys, Wouter
    Edan, Yael
    Shapiro, Amir
    Hočevar, Marko
    Oberti, Roberto
    Armada, Manuel
    Ulbrich, Heinz
    Baur, Jörg
    Debilde, Benoit
    Best, Stanley
    Evain, Sébastien
    Gauchel, Wolfgang
    Hellström, Thomas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Ringdahl, Ola
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    CROPS: Clever Robots for Crops2015Ingår i: Engineering & Technology Reference, ISSN 2056-4007, Vol. 1, nr 1Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In the EU-funded CROPS project robots are developed for site-specific spraying and selective harvesting of fruit and fruit vegetables. The robots are being designed to harvest crops, such as greenhouse vegetables, apples, grapes and for canopy spraying in orchards and for precision target spraying in grape vines. Attention is paid to the detection of obstacles for autonomous navigation in a safe way in plantations and forests. For the different applications, platforms were built. Sensing systems and vision algorithms have been developed. For software the Robot Operating System is used. A 9 degrees of freedom manipulator was designed and tested for sweet-pepper harvesting, apple harvesting and in close range spraying. For the applications different end-effectors were designed and tested. For sweet pepper a platform that can move in between the crop rows on the common greenhouse rail system which also serves as heating pipes was built. The apple harvesting platform is based on a current mechanical grape harvester. In discussion with growers so-called ‘walls of fruit trees’ have been designed which bring robots closer to the practice. A canopy-optimised sprayer has been designed as a trailed sprayer with a centrifugal blower. All the applications have been tested under practical conditions.

  • 17.
    Brynte, Lucas
    et al.
    Chalmers University of Technology, Department of Electrical Engineering, Gothenburg, Sweden.
    Bökman, Georg
    Chalmers University of Technology, Department of Electrical Engineering, Gothenburg, Sweden.
    Flinth, Axel
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för matematik och matematisk statistik.
    Kahl, Fredrik
    Chalmers University of Technology, Department of Electrical Engineering, Gothenburg, Sweden.
    Rigidity preserving image transformations and equivariance in perspective2023Ingår i: Image analysis: 23rd Scandinavian conference, SCIA 2023, Sirkka, Finland, April 18–21, 2023, proceedings, part II / [ed] Rikke Gade; Michael Felsberg; Joni-Kristian Kämäräinen, Cham: Springer Nature, 2023, Vol. 2, s. 59-76Konferensbidrag (Refereegranskat)
    Abstract [en]

    We characterize the class of image plane transformations which realize rigid camera motions and call these transformations ‘rigidity preserving’. It turns out that the only rigidity preserving image transformations are homographies corresponding to rotating the camera. In particular, 2D translations of pinhole images are not rigidity preserving. Hence, when using CNNs for 3D inference tasks, it can be beneficial to modify the inductive bias from equivariance w.r.t. translations to equivariance w.r.t. rotational homographies. We investigate how equivariance with respect to rotational homographies can be approximated in CNNs, and test our ideas on 6D object pose estimation. Experimentally, we improve on a competitive baseline.

  • 18.
    Börlin, Niclas
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Grussenmeyer, Pierre
    INSA Strasbourg, France.
    Bundle adjustment with and without damping2013Ingår i: Photogrammetric Record, ISSN 0031-868X, E-ISSN 1477-9730, Vol. 28, nr 144, s. 396-415Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The least squares adjustment (LSA) method is studied as an optimisation problem and shown to be equivalent to the undamped Gauss-Newton (GN) optimisation method. Three problem-independent damping modifications of the GN method are presented: the line-search method of Armijo (GNA); the Levenberg-Marquardt algorithm (LM); and Levenberg-Marquardt-Powell (LMP). Furthermore, an additional problem-specific "veto" damping technique, based on the chirality condition, is suggested. In a perturbation study on a terrestrial bundle adjustment problem the GNA and LMP methods with veto damping can increase the size of the pull-in region compared to the undamped method; the LM method showed less improvement. The results suggest that damped methods can, in many cases, provide a solution where undamped methods fail and should be available in any LSA software package. Matlab code for the algorithms discussed is available from the authors.

    Ladda ner fulltext (pdf)
    fulltext
  • 19.
    Börlin, Niclas
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Grussenmeyer, Pierre
    INSA Strasbourg, France.
    Camera Calibration using the Damped Bundle Adjustment Toolbox2014Ingår i: ISPRS Annals - Volume II-5, 2014: ISPRS Technical Commission V Symposium 23–25 June 2014, Riva del Garda, Italy / [ed] F. Remondino and F. Menna, Copernicus GmbH , 2014, Vol. II-5, s. 89-96Konferensbidrag (Refereegranskat)
    Abstract [en]

    Camera calibration is one of the fundamental photogrammetric tasks. The standard procedure is to apply an iterative adjustment to measurements of known control points. The iterative adjustment needs initial values of internal and external parameters. In this paper we investigate a procedure where only one parameter - the focal length is given a specific initial value. The procedure is validated using the freely available Damped Bundle Adjustment Toolbox on five calibration data sets using varying narrow- and wide-angle lenses. The results show that the Gauss-Newton-Armijo and Levenberg-Marquardt-Powell bundle adjustment methods implemented in the toolbox converge even if the initial values of the focal length are between 1/2 and 32 times the true focal length, even if the parameters are highly correlated. Standard statistical analysis methods in the toolbox enable manual selection of the lens distortion parameters to estimate, something not available in other camera calibration toolboxes. A standardised camera calibration procedure that does not require any information about the camera sensor or focal length is suggested based on the convergence results. The toolbox source and data sets used in this paper are available from the authors.

    Ladda ner fulltext (pdf)
    Camera Calibration using the Damped Bundle Adjustment Toolbox
  • 20.
    Börlin, Niclas
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Grussenmeyer, Pierre
    INSA Strasbourg, France.
    Experiments with Metadata-derived Initial Values and Linesearch Bundle Adjustment in Architectural Photogrammetry2013Konferensbidrag (Refereegranskat)
    Abstract [en]

    According to the Waldhäusl and Ogleby (1994) "3x3 rules", a well-designed close-range architetural photogrammetric project should include a sketch of the project site with the approximate position and viewing direction of each image. This orientation metadata is important to determine which part of the object each image covers. In principle, the metadata could be used as initial values for the camera external orientation (EO) parameters. However, this has rarely been used, partly due to convergence problem for the bundle adjustment procedure.

    In this paper we present a photogrammetric reconstruction pipeline based on classical methods and investigate if and how the linesearch bundle algorithms of Börlin et al. (2004) and/or metadata can be used to aid the reconstruction process in architectural photogrammetry when the classical methods fail. The primary initial values for the bundle are calculated by the five-point algorithm by Nistér (Stewénius et al., 2006). Should the bundle fail, initial values derived from metadata are calculated and used for a second bundle attempt.

    The pipeline was evaluated on an image set of the INSA building in Strasbourg. The data set includes mixed convex and non-convex subnetworks and a combination of manual and automatic measurements.

    The results show that, in general, the classical bundle algorithm with five-point initial values worked well. However, in cases where it did fail, linesearch bundle and/or metadata initial values did help. The presented approach is interesting for solving EO problems when the automatic orientation processes fail as well as to simplify keeping a link between the metadata containing the plan of how the project should have become and the actual reconstructed network as it turned out to be.

    Ladda ner fulltext (pdf)
    Experiments with Metadata-derived Initial Values and Linesearch Bundle Adjustment in Architectural Photogrammetry
  • 21.
    Claesson, Kenji
    Umeå universitet, Teknisk-naturvetenskaplig fakultet, Fysik.
    Implementation and Validation of Independent Vector Analysis2010Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    This Master’s Thesis was part of the project called Multimodalanalysis at the Depart-ment of Biomedical Engineering and Informatics at the Ume˚ University Hospital inUme˚ Sweden. The aim of the project is to develop multivariate measurement anda,analysis methods of the skeletal muscle physiology. One of the methods used to scanthe muscle is functional ultrasound. In a study performed by the project group datawas aquired, where test subjects were instructed to follow a certain exercise scheme,which was measured. Since there currently is no superior method to analyze the result-ing data (in form of ultrasound video sequences) several methods are being looked at.One considered method is called Independent Vector Analysis (IVA). IVA is a statisticalmethod to find independent components in a mix of components. This Master’s Thesisis about segmenting and analyzing the ultrasound images with help of IVA, to validateif it is a suitable method for this kind of tasks.First the algorithm was tested on generated mixed data to find out how well itperformed. The results were very accurate, considering that the method only usesapproximations. Some expected variation from the true value occured though.When the algorithm was considered performing to satisfactory, it was tested on thedata gathered by the study and the result can very well reflect an approximation of truesolution, since the resulting segmented signals seem to move in a possible way. But themethod has weak sides (which have been tried to be minimized) and all error analysishas been done by human eye, which definitly is a week point. But for the time being itis more important to analyze trends in the signals, rather than analyze exact numbers.So as long as the signals behave in a realistic way the result can not be said to becompletley wrong. So the overall results of the method were deemed adequate for the application at hand.

    Ladda ner fulltext (pdf)
    FULLTEXT01
  • 22.
    Coser, Omar
    et al.
    Unit of Computer Systems and Bioinformatics, Università Campus Bio-Medico di Roma, Rome, Italy; Unit of Advanced Robotics and Human-Centered Technologies, Università Campus Bio-Medico di Roma, Rome, Italy.
    Tamantini, Christian
    Unit of Advanced Robotics and Human-Centered Technologies, Università Campus Bio-Medico di Roma, Rome, Italy.
    Soda, Paolo
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik. Umeå universitet, Medicinska fakulteten, Institutionen för diagnostik och intervention. Unit of Computer Systems and Bioinformatics, Università Campus Bio-Medico di Roma, Rome, Italy.
    Zollo, Loredana
    Unit of Advanced Robotics and Human-Centered Technologies, Università Campus Bio-Medico di Roma, Rome, Italy.
    AI-based methodologies for exoskeleton-assisted rehabilitation of the lower limb: a review2024Ingår i: Frontiers in Robotics and AI, E-ISSN 2296-9144, Vol. 11, artikel-id 1341580Artikel, forskningsöversikt (Refereegranskat)
    Abstract [en]

    Over the past few years, there has been a noticeable surge in efforts to design novel tools and approaches that incorporate Artificial Intelligence (AI) into rehabilitation of persons with lower-limb impairments, using robotic exoskeletons. The potential benefits include the ability to implement personalized rehabilitation therapies by leveraging AI for robot control and data analysis, facilitating personalized feedback and guidance. Despite this, there is a current lack of literature review specifically focusing on AI applications in lower-limb rehabilitative robotics. To address this gap, our work aims at performing a review of 37 peer-reviewed papers. This review categorizes selected papers based on robotic application scenarios or AI methodologies. Additionally, it uniquely contributes by providing a detailed summary of input features, AI model performance, enrolled populations, exoskeletal systems used in the validation process, and specific tasks for each paper. The innovative aspect lies in offering a clear understanding of the suitability of different algorithms for specific tasks, intending to guide future developments and support informed decision-making in the realm of lower-limb exoskeleton and AI applications.

    Ladda ner fulltext (pdf)
    fulltext
  • 23.
    Dahlgren Lindström, Adam
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Abraham, Savitha Sam
    Örebro University, Sweden.
    CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning2022Ingår i: CEUR Workshop Proceedings / [ed] d'Avila Garcez A.; Jimenez-Ruiz E.; Jimenez-Ruiz E., CEUR-WS , 2022, Vol. 3212Konferensbidrag (Refereegranskat)
    Abstract [en]

    We introduce CLEVR-Math, a multi-modal math word problems dataset consisting of simple math word problems involving addition/subtraction, represented partly by a textual description and partly by an image illustrating the scenario. The text describes actions performed on the scene that is depicted in the image. Since the question posed may not be about the scene in the image, but about the state of the scene before or after the actions are applied, the solver envision or imagine the state changes due to these actions. Solving these word problems requires a combination of language, visual and mathematical reasoning. We apply state-of-the-art neural and neuro-symbolic models for visual question answering on CLEVR-Math and empirically evaluate their performances. Our results show how neither method generalise to chains of operations. We discuss the limitations of the two in addressing the task of multi-modal word problem solving.

    Ladda ner fulltext (pdf)
    fulltext
  • 24.
    de Flon, Jacques
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Automation of forest road inventory using computer vision and machine learning2023Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    There are around 300, 000 kilometer of gravel roads throughout the Swedish countryside, used every day by common people and companies. These roads face constant wear due to harsh weather as well as from heavy traffic, and thus, regular maintenance is required to keep up the road standard. A cost effective maintenance requires knowledge of where support is needed and such data is obtained through inventorying. Today, the road inventory is done primarily by hand using manual tools and requiring trained personel. With new tools, this work could be partially automated which could save on cost as well as open up for more complex analysis. This project aims to investigate the possibility of automating road inventory using computer vision and machine learning. Previous works within the field show promising results using deep convolutional networks to detect and classify road anomalies like potholes and cracks on paved roads. With their results in mind, we try to translate the solutions to also work on unpaved forest roads. During the project, we have collected our own dataset containing 3522 labelled images of gravel and forest roads. There are 203 instances of potholes, 614 bare roads and 3099 snow covered roads. These images were used to train an image segmentation model based on the YOLOv8 architecture for 30 epochs. Using transfer learning we took advantage of pretrained weights gained from training on the COCO dataset. The predicted road segmentation results were also used to estimate the width of the road, using the pinhole camera model and inverse projective geometry. The segmentation model reaches a AP50−95 = 0.746 for the road and 0.813 for the snow covered road. The model shows poor detection of potholes with AP50−95 = 0.048. Using the road segmentations to estimate the road width shows that the model can estimate road width with a mean average error of 0.24 m.

    The results from this project shows that there are already areas where machine learning could assist human operators with inventory work. Even difficult tasks, like estimating the road width of partially covered roads, can be solved with computer vision and machine learning.

    Ladda ner fulltext (pdf)
    fulltext
  • 25.
    de Pierrefeu, Amicie
    et al.
    NeuroSpin, CEA, Gif-sur-Yvette, France.
    Löfstedt, Tommy
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Laidi, C.
    NeuroSpin, CEA, Gif-sur-Yvette, France; Institut National de la Santé et de la Recherche Médicale (INSERM), U955, Institut Mondor de Recherche Biomédicale, Psychiatrie Translationnelle, Créteil, France; Fondation Fondamental, Créteil, France; Pôle de Psychiatrie, Assistance Publique–Hôpitaux de Paris (AP-HP), Faculté, de Médecine de Créteil, DHU PePsy, Hôpitaux Universitaires Mondor, Créteil, France.
    Hadj-Selem, Fouad
    Energy Transition Institute: VeDeCoM, Versailles, France.
    Bourgin, Julie
    Department of Psychiatry, Louis-Mourier Hospital, AP-HP, Colombes, France; INSERM U894, Centre for Psychiatry and Neurosciences, Paris, France.
    Hajek, Tomas
    Department of Psychiatry, Dalhousie University, Halifax, NS, Canada; National Institute of Mental Health, Klecany, Czech Republic.
    Spaniel, Filip
    National Institute of Mental Health, Klecany, Czech Republic.
    Kolenic, Marian
    National Institute of Mental Health, Klecany, Czech Republic.
    Ciuciu, Philippe
    NeuroSpin, CEA, Gif-sur-Yvette, France; INRIA, CEA, Parietal team, University of Paris-Saclay, France.
    Hamdani, Nora
    Institut National de la Santé et de la Recherche Médicale (INSERM), U955, Institut Mondor de Recherche Biomédicale, Psychiatrie Translationnelle, Créteil, France; Fondation Fondamental, Créteil, France; Pôle de Psychiatrie, Assistance Publique–Hôpitaux de Paris (AP-HP), Faculté, de Médecine de Créteil, DHU PePsy, Hôpitaux Universitaires Mondor, Créteil, France.
    Leboyer, Marion
    Institut National de la Santé et de la Recherche Médicale (INSERM), U955, Institut Mondor de Recherche Biomédicale, Psychiatrie Translationnelle, Créteil, France; Fondation Fondamental, Créteil, France; Pôle de Psychiatrie, Assistance Publique–Hôpitaux de Paris (AP-HP), Faculté, de Médecine de Créteil, DHU PePsy, Hôpitaux Universitaires Mondor, Créteil, France.
    Fovet, Thomas
    Laboratoire de Sciences Cognitives et Sciences Affectives (SCALab-PsyCHIC), CNRS UMR 9193, University of Lille; Pôle de Psychiatrie, Unité CURE, CHU Lille, Lille, France.
    Jardri, Renaud
    INRIA, CEA, Parietal team, University of Paris-Saclay, France; Laboratoire de Sciences Cognitives et Sciences Affectives (SCALab-PsyCHIC), CNRS UMR 9193, University of Lille; Pôle de Psychiatrie, Unité CURE, CHU Lille, Lille, France.
    Houenou, Josselin
    NeuroSpin, CEA, Gif-sur-Yvette, France; Institut National de la Santé et de la Recherche Médicale (INSERM), U955, Institut Mondor de Recherche Biomédicale, Psychiatrie Translationnelle, Créteil, France; Fondation Fondamental, Créteil, France; Pôle de Psychiatrie, Assistance Publique–Hôpitaux de Paris (AP-HP), Faculté, de Médecine de Créteil, DHU PePsy, Hôpitaux Universitaires Mondor, Créteil, France.
    Duchesnay, Edouard
    NeuroSpin, CEA, Gif-sur-Yvette, France.
    Identifying a neuroanatomical signature of schizophrenia, reproducible across sites and stages, using machine-learning with structured sparsity2018Ingår i: Acta Psychiatrica Scandinavica, ISSN 0001-690X, E-ISSN 1600-0447, Vol. 138, s. 571-580Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    ObjectiveStructural MRI (sMRI) increasingly offers insight into abnormalities inherent to schizophrenia. Previous machine learning applications suggest that individual classification is feasible and reliable and, however, is focused on the predictive performance of the clinical status in cross‐sectional designs, which has limited biological perspectives. Moreover, most studies depend on relatively small cohorts or single recruiting site. Finally, no study controlled for disease stage or medication's effect. These elements cast doubt on previous findings’ reproducibility.

    MethodWe propose a machine learning algorithm that provides an interpretable brain signature. Using large datasets collected from 4 sites (276 schizophrenia patients, 330 controls), we assessed cross‐site prediction reproducibility and associated predictive signature. For the first time, we evaluated the predictive signature regarding medication and illness duration using an independent dataset of first‐episode patients.

    ResultsMachine learning classifiers based on neuroanatomical features yield significant intersite prediction accuracies (72%) together with an excellent predictive signature stability. This signature provides a neural score significantly correlated with symptom severity and the extent of cognitive impairments. Moreover, this signature demonstrates its efficiency on first‐episode psychosis patients (73% accuracy).

    ConclusionThese results highlight the existence of a common neuroanatomical signature for schizophrenia, shared by a majority of patients even from an early stage of the disorder.

  • 26.
    Ding, Feng
    et al.
    School of Management, Nanchang University, Nanchang, Jiangxi 330031, China..
    Yu, Keping
    Global Information and Telecommunication Institute, Waseda University, Tokyo 169-8555, Japan (e-mail: keping.yu@aoni.waseda.jp).
    Gu, Zonghua
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Li, Xiangjun
    School of Software, Nanchang University, Nanchang 330047, China..
    Shi, Yunqing
    Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ 07101 USA..
    Perceptual Enhancement for Autonomous Vehicles: Restoring Visually Degraded Images for Context Prediction via Adversarial Training2022Ingår i: IEEE transactions on intelligent transportation systems (Print), ISSN 1524-9050, E-ISSN 1558-0016, Vol. 23, nr 7, s. 9430-9441Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Realizing autonomous vehicles is one of the ultimate dreams for humans. However, perceptual information collected by sensors in dynamic and complicated environments, in particular, vision information, may exhibit various types of degradation. This may lead to mispredictions of context followed by more severe consequences. Thus, it is necessary to improve degraded images before employing them for context prediction. To this end, we propose a generative adversarial network to restore images from common types of degradation. The proposed model features a novel architecture with an inverse and a reverse module to address additional attributes between image styles. With the supplementary information, the decoding for restoration can be more precise. In addition, we develop a loss function to stabilize the adversarial training with better training efficiency for the proposed model. Compared with several state-of-the-art methods, the proposed method can achieve better restoration performance with high efficiency. It is highly reliable for assisting in context prediction in autonomous vehicles.

  • 27.
    Eftekhari, Armin
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för matematik och matematisk statistik.
    Bendory, Tamir
    Program in Applied and Computational Mathematics, Princeton University, Princeton, United States.
    Tang, Gongguo
    Department of Electrical Engineering, Colorado School of Mines, CO, Golden, United States.
    Stable super-resolution of images: Theoretical study2021Ingår i: Information and Inference, E-ISSN 2049-8772, Vol. 10, nr 1, s. 161-193Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We study the ubiquitous super-resolution problem, in which one aims at localizing positive point sources in an image, blurred by the point spread function of the imaging device. To recover the point sources, we propose to solve a convex feasibility program, which simply finds a non-negative Borel measure that agrees with the observations collected by the imaging device. In the absence of imaging noise, we show that solving this convex program uniquely retrieves the point sources, provided that the imaging device collects enough observations. This result holds true if the point spread function of the imaging device can be decomposed into horizontal and vertical components and if the translations of these components form a Chebyshev system, i.e., a system of continuous functions that loosely behave like algebraic polynomials. Building upon the recent results for one-dimensional signals, we prove that this super-resolution algorithm is stable, in the generalized Wasserstein metric, to model mismatch (i.e., when the image is not sparse) and to additive imaging noise. In particular, the recovery error depends on the noise level and how well the image can be approximated with well-separated point sources. As an example, we verify these claims for the important case of a Gaussian point spread function. The proofs rely on the construction of novel interpolating polynomials - which are the main technical contribution of this paper - and partially resolve the question raised in Schiebinger et al. (2017, Inf. Inference, 7, 1-30) about the extension of the standard machinery to higher dimensions.

  • 28.
    Fetty, Lukas
    et al.
    Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria.
    Bylund, Mikael
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Kuess, Peter
    Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria.
    Heilemann, Gerd
    Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria.
    Nyholm, Tufve
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Georg, Dietmar
    Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria.
    Löfstedt, Tommy
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Latent space manipulation for high-resolution medical image synthesis via the StyleGAN2020Ingår i: Zeitschrift für Medizinische Physik, ISSN 0939-3889, E-ISSN 1876-4436, Vol. 30, nr 4, s. 305-314Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Introduction: This paper explores the potential of the StyleGAN model as an high-resolution image generator for synthetic medical images. The possibility to generate sample patient images of different modalities can be helpful for training deep learning algorithms as e.g. a data augmentation technique.

    Methods: The StyleGAN model was trained on Computed Tomography (CT) and T2- weighted Magnetic Resonance (MR) images from 100 patients with pelvic malignancies. The resulting model was investigated with regards to three features: Image Modality, Sex, and Longitudinal Slice Position. Further, the style transfer feature of the StyleGAN was used to move images between the modalities. The root-mean-squard error (RMSE) and the Mean Absolute Error (MAE) were used to quantify errors for MR and CT, respectively.

    Results: We demonstrate how these features can be transformed by manipulating the latent style vectors, and attempt to quantify how the errors change as we move through the latent style space. The best results were achieved by using the style transfer feature of the StyleGAN (58.7 HU MAE for MR to CT and 0.339 RMSE for CT to MR). Slices below and above an initial central slice can be predicted with an error below 75 HU MAE and 0.3 RMSE within 4 cm for CT and MR, respectively.

    Discussion: The StyleGAN is a promising model to use for generating synthetic medical images for MR and CT modalities as well as for 3D volumes.

    Ladda ner fulltext (pdf)
    fulltext
  • 29.
    Fonooni, Benjamin
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Jevtić, Aleksandar
    Hellström, Thomas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Janlert, Lars-Erik
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Applying Ant Colony Optimization Algorithms for High-Level Behavior Learning and Reproduction from Demonstrations2015Ingår i: Robotics and Autonomous Systems, ISSN 0921-8890, E-ISSN 1872-793X, Vol. 65, s. 24-39Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In domains where robots carry out human’s tasks, the ability to learn new behaviors easily and quickly plays an important role. Two major challenges with Learning from Demonstration (LfD) are to identify what information in a demonstrated behavior requires attention by the robot, and to generalize the learned behavior such that the robot is able to perform the same behavior in novel situations. The main goal of this paper is to incorporate Ant Colony Optimization (ACO) algorithms into LfD in an approach that focuses on understanding tutor's intentions and learning conditions to exhibit a behavior. The proposed method combines ACO algorithms with semantic networks and spreading activation mechanism to reason and generalize the knowledge obtained through demonstrations. The approach also provides structures for behavior reproduction under new circumstances. Finally, applicability of the system in an object shape classification scenario is evaluated.

  • 30.
    Forsgren, Edvin
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Kemiska institutionen.
    Edlund, Christoffer
    Sartorius Corporate Research, Sartorius Stedim Data Analytics AB, Umeå, Sweden.
    Oliver, Miniver
    Sartorius BioAnalytics, Essen BioScience, Ltd., Units 2 & 3 The Quadrant, Hertfordshire, Royston, United Kingdom.
    Barnes, Kalpana
    Sartorius BioAnalytics, Essen BioScience, Ltd., Units 2 & 3 The Quadrant, Hertfordshire, Royston, United Kingdom.
    Sjögren, Rickard
    Sartorius Corporate Research, Sartorius Stedim Data Analytics AB, Umeå, Sweden.
    Jackson, Timothy R.
    Sartorius BioAnalytics, Essen BioScience, Ltd., Units 2 & 3 The Quadrant, Hertfordshire, Royston, United Kingdom.
    High-throughput widefield fluorescence imaging of 3D samples using deep learning for 2D projection image restoration2022Ingår i: PLOS ONE, E-ISSN 1932-6203, Vol. 17, nr 5 May, artikel-id e0264241Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Fluorescence microscopy is a core method for visualizing and quantifying the spatial and temporal dynamics of complex biological processes. While many fluorescent microscopy techniques exist, due to its cost-effectiveness and accessibility, widefield fluorescent imaging remains one of the most widely used. To accomplish imaging of 3D samples, conventional widefield fluorescence imaging entails acquiring a sequence of 2D images spaced along the z-dimension, typically called a z-stack. Oftentimes, the first step in an analysis pipeline is to project that 3D volume into a single 2D image because 3D image data can be cumbersome to manage and challenging to analyze and interpret. Furthermore, z-stack acquisition is often time-consuming, which consequently may induce photodamage to the biological sample; these are major barriers for workflows that require high-throughput, such as drug screening. As an alternative to z-stacks, axial sweep acquisition schemes have been proposed to circumvent these drawbacks and offer potential of 100-fold faster image acquisition for 3D-samples compared to z-stack acquisition. Unfortunately, these acquisition techniques generate low-quality 2D z-projected images that require restoration with unwieldy, computationally heavy algorithms before the images can be interrogated. We propose a novel workflow to combine axial z-sweep acquisition with deep learning-based image restoration, ultimately enabling high-throughput and high-quality imaging of complex 3D-samples using 2D projection images. To demonstrate the capabilities of our proposed workflow, we apply it to live-cell imaging of large 3D tumor spheroid cultures and find we can produce high-fidelity images appropriate for quantitative analysis. Therefore, we conclude that combining axial z-sweep image acquisition with deep learning-based image restoration enables high-throughput and high-quality fluorescence imaging of complex 3D biological samples.

    Ladda ner fulltext (pdf)
    fulltext
  • 31.
    Forsman, Mona
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Point cloud densification2010Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Several automatic methods exist for creating 3D point clouds extracted from 2D photos. In manycases, the result is a sparse point cloud, unevenly distributed over the scene.After determining the coordinates of the same point in two images of an object, the 3D positionof that point can be calculated using knowledge of camera data and relative orientation. A model created from a unevenly distributed point clouds may loss detail and precision in thesparse areas. The aim of this thesis is to study methods for densification of point clouds.

    This thesis contains a literature study over different methods for extracting matched point pairs,and an implementation of Least Square Template Matching (LSTM) with a set of improvementtechniques. The implementation is evaluated on a set of different scenes of various difficulty. LSTM is implemented by working on a dense grid of points in an image and Wallis filtering isused to enhance contrast. The matched point correspondences are evaluated with parameters fromthe optimization in order to keep good matches and discard bad ones. The purpose is to find detailsclose to a plane in the images, or on plane-like surfaces. A set of extensions to LSTM is implemented in the aim of improving the quality of the matchedpoints. The seed points are improved by Transformed Normalized Cross Correlation (TNCC) andMultiple Seed Points (MSP) for the same template, and then tested to see if they converge to thesame result. Wallis filtering is used to increase the contrast in the image. The quality of the extractedpoints are evaluated with respect to correlation with other optimization parameters and comparisonof standard deviation in x- and y- direction. If a point is rejected, the option to try again with a largertemplate size exists, called Adaptive Template Size (ATS).

    Ladda ner fulltext (pdf)
    FULLTEXT01
  • 32.
    Forsman, Mona
    et al.
    Department of Forest Resource Management, Swedish University of Agricultural Sciences, 90183 Umeå, Sweden.
    Börlin, Niclas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Holmgren, Johan
    Department of Forest Resource Management, Swedish University of Agricultural Sciences, 90183 Umeå, Sweden.
    Estimation of Tree Stem Attributes using Terrestrial Photogrammetry with a Camera Rig2016Ingår i: Forests, ISSN 1999-4907, E-ISSN 1999-4907, Vol. 7, nr 3, artikel-id 61Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We propose a novel photogrammetric method for field plot inventory, designed for simplicity and time efficiency on-site. A prototype multi-camera rig was used to acquire images from field plot centers in multiple directions. The acquisition time on-site was less than two minutes. From each view, a point cloud was generated using a novel, rig-based matching of detected SIFT keypoints. Stems were detected in the merged point cloud, and their positions and diameters were estimated. The method was evaluated on 25 hemi-boreal forest plots of a 10-m radius. Due to difficult lighting conditions and faulty hardware, imagery from only six field plots was processed. The method performed best on three plots with clearly visible stems with a 76% detection rate and 0% commission. Dieameters could be estimated for 40% of the stems with an RMSE of 2.8-9.5 cm. The results are comparable to other camera-based methods evaluated in a similar manner. The results are inferior to TLS-based methods. However, our method is easily extended to multiple station image schemas, something that could significantly improve the results while retaining low commission errors and time on-site. Furthermore, with smaller hardware, we believe this could be a useful technique for measuring stem attributes in the forest.

    Ladda ner fulltext (pdf)
    forsman2016_estimation.pdf
  • 33.
    Fälldin, Arvid
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Learning by Digging: A Differentiable Prediction Model for an Autonomous Wheel Loader2022Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Wheel loaders are heavy duty machines that are ubiquitous on construction sites and in mines all over the world. Fully autonomous wheel loaders remains an open problem but the industry is hoping that increasing their level of autonomy will help to reduce costs and energy consumption while also increasing workplace safety. Operating a wheel loader efficiently requires dig plans that extend over multiple dig cycles and not just one at a time. This calls for a model that can predict both the performance of a dig action and the resulting shape of the pile. In this thesis project, we use simulations to develop a data-driven artificial neural network model that can predict the outcome of a dig action. The model is able to predict the wheel loader’s productivity with an average error of 7.3% and the altered shape of the pile with an average relative error of 4.5%. We also show that automatic differentiation techniques can be used to accurately differentiate the model with respect to input. This makes it possible to use gradient-based optimization methods to find the dig action that maximises the performance of the wheel loader.

    Ladda ner fulltext (pdf)
    fulltext
  • 34.
    Garpebring, Anders
    et al.
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Brynolfsson, Patrik
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Kuess, Peter
    Department of Radiotherapy, Medical University of Vienna, Vienna, Austria; Christian Doppler Laboratory for Medical Radiation Research for Radiation Oncology, Vienna, Austria.
    Georg, Dietmar
    Department of Radiotherapy, Medical University of Vienna, Vienna, Austria; Christian Doppler Laboratory for Medical Radiation Research for Radiation Oncology, Vienna, Austria.
    Helbich, Thomas H.
    Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, Vienna, Austria; Christian Doppler Laboratory for Medical Radiation Research for Radiation Oncology, Vienna, Austria.
    Nyholm, Tufve
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Löfstedt, Tommy
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Density Estimation of Grey-Level Co-Occurrence Matrices for Image Texture Analysis2018Ingår i: Physics in Medicine and Biology, ISSN 0031-9155, E-ISSN 1361-6560, Vol. 63, nr 19, s. 9-15, artikel-id 195017Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The Haralick texture features are common in the image analysis literature, partly because of their simplicity and because their values can be interpreted. It was recently observed that the Haralick texture features are very sensitive to the size of the GLCM that was used to compute them, which led to a new formulation that is invariant to the GLCM size. However, these new features still depend on the sample size used to compute the GLCM, i.e. the size of the input image region-of-interest (ROI).

    The purpose of this work was to investigate the performance of density estimation methods for approximating the GLCM and subsequently the corresponding invariant features.

    Three density estimation methods were evaluated, namely a piece-wise constant distribution, the Parzen-windows method, and the Gaussian mixture model. The methods were evaluated on 29 different image textures and 20 invariant Haralick texture features as well as a wide range of different ROI sizes.

    The results indicate that there are two types of features: those that have a clear minimum error for a particular GLCM size for each ROI size, and those whose error decreases monotonically with increased GLCM size. For the first type of features, the Gaussian mixture model gave the smallest errors, and in particular for small ROI sizes (less than about 20×20).

    In conclusion, the Gaussian mixture model is the preferred method for the first type of features (in particular for small ROIs). For the second type of features, simply using a large GLCM size is preferred.

    Ladda ner fulltext (pdf)
    fulltext
  • 35.
    Guillemot, Vincent
    et al.
    Bioinformatics and Biostatistics Hub, Institut Pasteur, Paris, France.
    Beaton, Derek
    The Rotman Research Institute, Institution at Baycrest, Toronto, Canada.
    Gloaguen, Arnaud
    L2S, UMR CNRS 8506, CNRS–Centrale Supélec–Université Paris-Sud, Université Paris-Saclay, 3 rue Joliot-Curie, 91192 Gif-sur-Yvette, France.
    Löfstedt, Tommy
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Levine, Brian
    The Rotman Research Institute, Institution at Baycrest, Toronto, Canada.
    Raymond, Nicolas
    IRMAR, UMR 6625, Université de Rennes, Rennes, France.
    Tenenhaus, Arthur
    L2S, UMR CNRS 8506, CNRS–Centrale Supélec–Université Paris-Sud, Université Paris-Saclay, 3 rue Joliot-Curie, Gif-sur-Yvette, France.
    Abdi, Hervé
    School of Behavioral and Brain Sciences, The University of Texas at Dallas, Richardson, TX, United States of America.
    A constrained singular value decomposition method that integrates sparsity and orthogonality2019Ingår i: PLOS ONE, E-ISSN 1932-6203, Vol. 14, nr 3, artikel-id e0211463Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We propose a new sparsification method for the singular value decomposition—called the constrained singular value decomposition (CSVD)—that can incorporate multiple constraints such as sparsification and orthogonality for the left and right singular vectors. The CSVD can combine different constraints because it implements each constraint as a projection onto a convex set, and because it integrates these constraints as projections onto the intersection of multiple convex sets. We show that, with appropriate sparsification constants, the algorithm is guaranteed to converge to a stable point. We also propose and analyze the convergence of an efficient algorithm for the specific case of the projection onto the balls defined by the norms L1 and L2. We illustrate the CSVD and compare it to the standard singular value decomposition and to a non-orthogonal related sparsification method with: 1) a simulated example, 2) a small set of face images (corresponding to a configuration with a number of variables much larger than the number of observations), and 3) a psychometric application with a large number of observations and a small number of variables. The companion R-package, csvd, that implements the algorithms described in this paper, along with reproducible examples, are available for download from https://github.com/vguillemot/csvd.

    Ladda ner fulltext (pdf)
    fulltext
  • 36.
    Gupta, Himanshu
    et al.
    Centre for Applied Autonomous Sensor Systems, Institutionen för naturvetenskap & teknik, Örebro University, Örebro, Sweden.
    Lilienthal, Achim J.
    Centre for Applied Autonomous Sensor Systems, Institutionen för naturvetenskap & teknik, Örebro University, Örebro, Sweden; Perception for Intelligent Systems, Technical University of Munich, Munich, Germany.
    Andreasson, Henrik
    Centre for Applied Autonomous Sensor Systems, Institutionen för naturvetenskap & teknik, Örebro University, Örebro, Sweden.
    Kurtser, Polina
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik. Centre for Applied Autonomous Sensor Systems, Institutionen för naturvetenskap & teknik, Örebro University, Örebro, Sweden.
    NDT-6D for color registration in agri-robotic applications2023Ingår i: Journal of Field Robotics, ISSN 1556-4959, E-ISSN 1556-4967, Vol. 40, nr 6, s. 1603-1619Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Registration of point cloud data containing both depth and color information is critical for a variety of applications, including in-field robotic plant manipulation, crop growth modeling, and autonomous navigation. However, current state-of-the-art registration methods often fail in challenging agricultural field conditions due to factors such as occlusions, plant density, and variable illumination. To address these issues, we propose the NDT-6D registration method, which is a color-based variation of the Normal Distribution Transform (NDT) registration approach for point clouds. Our method computes correspondences between pointclouds using both geometric and color information and minimizes the distance between these correspondences using only the three-dimensional (3D) geometric dimensions. We evaluate the method using the GRAPES3D data set collected with a commercial-grade RGB-D sensor mounted on a mobile platform in a vineyard. Results show that registration methods that only rely on depth information fail to provide quality registration for the tested data set. The proposed color-based variation outperforms state-of-the-art methods with a root mean square error (RMSE) of 1.1-1.6 cm for NDT-6D compared with 1.1 - 2.3 cm for other color-information-based methods and 1.2 - 13.7 cm for noncolor-information-based methods. The proposed method is shown to be robust against noises using the TUM RGBD data set by artificially adding noise present in an outdoor scenario. The relative pose error (RPE) increased 14% for our method compared to an increase of 75% for the best-performing registration method. The obtained average accuracy suggests that the NDT-6D registration methods can be used for in-field precision agriculture applications, for example, crop detection, size-based maturity estimation, and growth modeling.

    Ladda ner fulltext (pdf)
    fulltext
  • 37.
    Hadj-Selem, Fouad
    et al.
    Energy Transition Institute VeDeCoM, Versailles, France.
    Löfstedt, Tommy
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Dohmatob, Elvis
    PARIETAL Team, INRIA/CEA, Université Paris-Saclay, Gif-sur-Yvette, France.
    Frouin, Vincent
    NeuroSpin, CEA, Université Paris-Saclay, Gif-sur-Yvette, France.
    Dubois, Mathieu
    NeuroSpin, CEA, Université Paris-Saclay, Gif-sur-Yvette, France.
    Guillemot, Vincent
    NeuroSpin, CEA, Université Paris-Saclay, Gif-sur-Yvette, France.
    Duchesnay, Edouard
    NeuroSpin, CEA, Université Paris-Saclay, Gif-sur-Yvette, France.
    Continuation of Nesterov's Smoothing for Regression With Structured Sparsity in High-Dimensional Neuroimaging2018Ingår i: IEEE Transactions on Medical Imaging, ISSN 0278-0062, E-ISSN 1558-254X, Vol. 37, nr 11, s. 2403-2413Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Predictive models can be used on high-dimensional brain images to decode cognitive states or diagnosis/prognosis of a clinical condition/evolution. Spatial regularization through structured sparsity offers new perspectives in this context and reduces the risk of overfitting the model while providing interpretable neuroimaging signatures by forcing the solution to adhere to domain-specific constraints. Total variation (TV) is a promising candidate for structured penalization: it enforces spatial smoothness of the solution while segmenting predictive regions from the background. We consider the problem of minimizing the sum of a smooth convex loss, a non-smooth convex penalty (whose proximal operator is known) and a wide range of possible complex, non-smooth convex structured penalties such as TV or overlapping group Lasso. Existing solvers are either limited in the functions they can minimize or in their practical capacity to scale to high-dimensional imaging data. Nesterov’s smoothing technique can be used to minimize a large number of non-smooth convex structured penalties. However, reasonable precision requires a small smoothing parameter, which slows down the convergence speed to unacceptable levels. To benefit from the versatility of Nesterov’s smoothing technique, we propose a first order continuation algorithm, CONESTA, which automatically generates a sequence of decreasing smoothing parameters. The generated sequence maintains the optimal convergence speed toward any globally desired precision. Our main contributions are: gap to probe the current distance to the global optimum in order to adapt the smoothing parameter and the To propose an expression of the duality convergence speed. This expression is applicable to many penalties and can be used with other solvers than CONESTA. We also propose an expression for the particular smoothing parameter that minimizes the number of iterations required to reach a given precision. Furthermore, we provide a convergence proof and its rate, which is an improvement over classical proximal gradient smoothing methods. We demonstrate on both simulated and high-dimensional structural neuroimaging data that CONESTA significantly outperforms many state-of-the-art solvers in regard to convergence speed and precision.

  • 38.
    Halawani, Alaa
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik. Computer Engineering Department, Palestine Polytechnic University, Hebron, Palestine.
    Li, Haibo
    KTH.
    100 lines of code for shape-based object localization2016Ingår i: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 60, s. 458-472Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We introduce a simple and effective concept for localizing objects in densely cluttered edge images based on shape information. The shape information is characterized by a binary template of the object's contour, provided to search for object instances in the image. We adopt a segment-based search strategy, in which the template is divided into a set of segments. In this work, we propose our own segment representation that we callone-pixel segment (OPS), in which each pixel in the template is treated as a separate segment. This is done to achieve high flexibility that is required to account for intra-class variations. OPS representation can also handle scale changes effectively. A dynamic programming algorithm uses the OPS representation to realize the search process, enabling a detailed localization of the object boundaries in the image. The concept's simplicity is reflected in the ease of implementation, as the paper's title suggests. The algorithm works directly with very noisy edge images extracted using the Canny edge detector, without the need for any preprocessing or learning steps. We present our experiments and show that our results outperform those of very powerful, state-of-the-art algorithms.

  • 39.
    Halawani, Alaa
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Li, Haibo
    Human Ear Localization: A Template-based Approach2015Konferensbidrag (Övrigt vetenskapligt)
    Abstract [en]

    We propose a simple and yet effective technique for shape-based ear localization. The idea is based on using a predefined binary ear template that is matched to ear contours in a given edge image. To cope with changes in ear shapes and sizes, the template is allowed to deform. Deformation is achieved by dividing the template into segments. The dynamic programming search algorithm is used to accomplish the matching process, achieving very robust localization results in various cluttered and noisy setups.

  • 40.
    Halawani, Alaa
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    ur Réhman, Shafiq
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Li, Haibo
    Active Vision for Tremor Disease Monitoring2015Ingår i: 6th International Conference on Applied Human Factors and Ergonomics (AHFE 2015) and the Affiliated Conferences AHFE 2015, 2015, Vol. 3, s. 2042-2048Konferensbidrag (Refereegranskat)
    Abstract [en]

    The aim of this work is to introduce a prototype for monitoring tremor diseases using computer vision techniques.  While vision has been previously used for this purpose, the system we are introducing differs intrinsically from other traditional systems. The essential difference is characterized by the placement of the camera on the user’s body rather than in front of it, and thus reversing the whole process of motion estimation. This is called active motion tracking. Active vision is simpler in setup and achieves more accurate results compared to traditional arrangements, which we refer to as “passive” here. One main advantage of active tracking is its ability to detect even tiny motions using its simple setup, and that makes it very suitable for monitoring tremor disorders. 

    Ladda ner fulltext (pdf)
    fulltext
  • 41.
    Halawani, Alaa
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    ur Réhman, Shafiq
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Li, Haibo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Anani, Adi
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Active vision for controlling an electric wheelchair2012Ingår i: Intelligent Service Robotics, ISSN 1861-2776, Vol. 5, nr 2, s. 89-98Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Most of the electric wheelchairs available in the market are joystick-driven and therefore assume that the user is able to use his hand motion to steer the wheelchair. This does not apply to many users that are only capable of moving the head like quadriplegia patients. This paper presents a vision-based head motion tracking system to enable such patients of controlling the wheelchair. The novel approach that we suggest is to use active vision rather than passive to achieve head motion tracking. In active vision-based tracking, the camera is placed on the user’s head rather than in front of it. This makes tracking easier, more accurate and enhances the resolution. This is demonstrated theoretically and experimentally. The proposed tracking scheme is then used successfully to control our electric wheelchair to navigate in a real world environment.

  • 42.
    Hallén, Mattias
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Comminution control using reinforcement learning: Comparing control strategies for size reduction in mineral processing2018Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    In mineral processing the grinding comminution process is an integral part since it is often the bottleneck of the concentrating process, thus small improvements may lead to large savings. By implementing a Reinforcement Learning controller this thesis aims to investigate if it is possible to control the grinding process more efficiently compared to traditional control strategies. Based on a calibrated plant simulation we compare existing control strategies with Proximal Policy Optimization and show possible increase in profitability under certain conditions.

    Ladda ner fulltext (pdf)
    fulltext
  • 43.
    Hallén, Mattias
    et al.
    ABB Corporate Research.
    Åstrand, Max
    ABB Corporate Research.
    Sikström, Johannes
    Boliden.
    Servin, Martin
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Reinforcement Learning for Grinding Circuit Control in Mineral Processing2019Ingår i: 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), IEEE, 2019, s. 488-495Konferensbidrag (Refereegranskat)
    Abstract [en]

    Grinding, i.e. reducing the particle size of mined ore, is often the bottleneck of the mining concentrating process. Thus, even small improvements may lead to large increases in profit. The goal of the grinding circuit is two-sided; to maximize the throughput of ore, and minimize the resulting particle size of the ground ore within some acceptable range. In this work we study the control of a two-stage grinding circuit using reinforcement learning. To this end, we present a solution for integrating industrial simulation models into the reinforcement learning framework OpenAI Gym. We compare an existing PID controller, based on vast domain knowledge and years of hand-tuning, with a black-box algorithm called Proximal Policy Optimization on a calibrated grinding circuit simulation model. The comparison show that it is possible to control the grinding circuit using reinforcement learning. In addition, contrasting reinforcement learning from the existing PID control, the algorithm is able tomaximize an abstract control goal: maximizing profit as defined by a profit function given by our industrial collaborator. In some operating cases the algorithm is able to control the plant more efficiently compared to existing control.

  • 44.
    Hanqing, Zhang
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Wiklund, Krister
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Andersson, Magnus
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    A fast and robust circle detection method using isosceles triangles sampling2016Ingår i: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 54, s. 218-228Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Circle detection using randomized sampling has been developed in recent years to reduce computational intensity. However, randomized sampling is sensitive to noise that can lead to reduced accuracy and false-positive candidates. To improve on the robustness of randomized circle detection under noisy conditions this paper presents a new methodology for circle detection based upon randomized isosceles triangles sampling. It is shown that the geometrical property of isosceles triangles provides a robust criterion to find relevant edge pixels which, in turn, offers an efficient means to estimate the centers and radii of circles. For best efficiency, the estimated results given by the sampling from individual connected components of the edge map were analyzed using a simple clustering approach. To further improve on the accuracy we applied a two-step refinement process using chords and linear error compensation with gradient information of the edge pixels. Extensive experiments using both synthetic and real images have been performed. The results are compared to leading state-of-the-art algorithms and it is shown that the proposed methodology has a number of advantages: it is efficient in finding circles with a low number of iterations, it has high rejection rate of false-positive circle candidates, and it has high robustness against noise. All this makes it adaptive and useful in many vision applications.

  • 45.
    Harel, Ben
    et al.
    Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer Sheva, Israel.
    Kurtser, Polina
    Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer Sheva, Israel.
    van Herck, Liesbet
    Proefstation voor de Groenteteelt, Sint-Katelijne-Waver, Belgium.
    Parmet, Yisrael
    Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer Sheva, Israel.
    Edan, Yael
    Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer Sheva, Israel.
    Sweet pepper maturity evaluation via multiple viewpoints color analyses2016Konferensbidrag (Refereegranskat)
    Abstract [en]

    Maturity evaluation is an important feature for selective robotic harvesting. This paper focuses on maturity evaluation derived by a color camera for a sweet pepper robotic harvester. Fruit visibility for sweet peppers is limited to 65% and multiple viewpoints are necessary to detect more than 90% of the fruit. This paper aims to determine the number of viewpoints required to determine the maturity level of a sweet pepper and the best single viewpoint. Different colorbased measures to estimate the maturity level of a pepper were evaluated. Two datasets were analyzed: images of 54 yellow bell sweet peppers and 30 red peppers both harvested at the last fruit setting; all images were taken in uniform illumination conditions with white background. Each pepper was photographed from 5-6 viewpoints: one photo of the top of the pepper, one photo of the bottom and 3-4 photos of the pepper sides. Each pepper was manually tagged by a human professional observer as ‘mature’ or ‘immature’. Image processing routines were implemented to extract color level measures which included different hue features. Results indicates high correlation between the sides to the bottom view, the bottom view shows the best 0.86 correlation in the case of yellow peppers while the side view shows the best 0.835 correlation in the case of red peppers (the bottom view yields 0.82 correlation).

  • 46.
    Harisubramanyabalaji, Subramani Palanisamy
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik. Scania CV AB, Södertälje, Sweden.
    ur Réhman, Shafiq
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Nyberg, Mattias
    Gustavsson, Joakim
    Improving Image Classification Robustness Using Predictive Data Augmentation2018Ingår i: Computer Safety, Reliability, and Security: SAFECOMP 2018 / [ed] Gallina B., Skavhaug A., Schoitsch E., Bitsch F., Springer, 2018, s. 548-561Konferensbidrag (Refereegranskat)
    Abstract [en]

    Safer autonomous navigation might be challenging if there is a failure in sensing system. Robust classifier algorithm irrespective of camera position, view angles, and environmental condition of an autonomous vehicle including different size & type (Car, Bus, Truck, etc.) can safely regulate the vehicle control. As training data play a crucial role in robust classification of traffic signs, an effective augmentation technique enriching the model capacity to withstand variations in urban environment is required. In this paper, a framework to identify model weakness and targeted augmentation methodology is presented. Based on off-line behavior identification, exact limitation of a Convolutional Neural Network (CNN) model is estimated to augment only those challenge levels necessary for improved classifier robustness. Predictive Augmentation (PA) and Predictive Multiple Augmentation (PMA) methods are proposed to adapt the model based on acquired challenges with a high numerical value of confidence. We validated our framework on two different training datasets and with 5 generated test groups containing varying levels of challenge (simple to extreme). The results show impressive improvement by 5-20% in overall classification accuracy thereby keeping their high confidence.

  • 47.
    Hedström, Lucas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Classifying the rotation of bacteria using neural networks2019Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Bakterier kan snabbt sprida sig genom människokroppen, vilket försvårar starkt möjligheterna att kurera vissa sjukdomar. För att få en inblick i hur bakterier kan initiera och utvecklas till en infektion används som mall laborativa uppställningar med vätskekanaler i mikroskala när man söker förstå hur bakterier reagerar på olika typer av flöden. Att spåra dessa rörelser med god säkerhet är dock en utmaning, då man experimentellt söker fånga små skalor med hög upplösning, som sedan ska analyseras med datorintensiva metoder. Populära avbildningsmetoder använder sig utav digital holografisk mikroskopi, där tredimensionella rörelser kan fångas med hjälp av tvådimensionella bilder genom att numeriskt återskapa ljusets brytningsmönster mot objekten. Eftersom dessa metoder blir beräkningstunga när god säkerhet krävs så utforskar detta examensarbete möjligheterna att utnyttja faltningsnätverk för att snabbt och säkert bestämma vertikalrotationen hos bakterier avbildade med holografi. Genom nogranna tester av moderna samt äldre nätverk så presenteras en ny nätverksdesign, utvecklad i mål med att eliminera så många avbildningsproblem som möjligt. Vi fann att vissa designval vid nätverksutvecklingen kan hjälpa med att reducera klassificeringsfelen givet vårt system, och med en väl utvald träningsmängd med lämpliga justeringar så lyckades vi nå en klassificeringssäkerhet på över 60% med vissa nätverk. På grund av bristande experimentellt data där de riktiga värdena är kända så har ingen utförlig experimentell analys utförts, men några tester på experimentella bilder i god kvalité har visats ge resultat som tyder på en korrekt analys inom den förväntade vertikalrotationen.

    Ladda ner fulltext (pdf)
    fulltext
  • 48.
    Heith, Anne
    Umeå universitet, Humanistiska fakulteten, Litteraturvetenskap och nordiska språk.
    Gömda. En sann historia: romantik, spänning, melodram och populärorientalism2006Ingår i: Svenskläraren, ISSN 0346-2412, nr 4, s. 20-26Artikel i tidskrift (Övrig (populärvetenskap, debatt, mm))
  • 49.
    Hellström, Max
    et al.
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper.
    Löfstedt, Tommy
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Garpebring, Anders
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper.
    Denoising and uncertainty estimation in parameter mapping with approximate Bayesian deep image priors2023Ingår i: Magnetic Resonance in Medicine, ISSN 0740-3194, E-ISSN 1522-2594, Vol. 90, nr 6, s. 2557-2571Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Purpose: To mitigate the problem of noisy parameter maps with high uncertainties by casting parameter mapping as a denoising task based on Deep Image Priors.

    Methods: We extend the concept of denoising with Deep Image Prior (DIP) into parameter mapping by treating the output of an image-generating network as a parametrization of tissue parameter maps. The method implicitly denoises the parameter mapping process by filtering low-level image features with an untrained convolutional neural network (CNN). Our implementation includes uncertainty estimation from Bernoulli approximate variational inference, implemented with MC dropout, which provides model uncertainty in each voxel of the denoised parameter maps. The method is modular, so the specifics of different applications (e.g., T1 mapping) separate into application-specific signal equation blocks. We evaluate the method on variable flip angle T1 mapping, multi-echo T2 mapping, and apparent diffusion coefficient mapping.

    Results: We found that deep image prior adapts successfully to several applications in parameter mapping. In all evaluations, the method produces noise-reduced parameter maps with decreased uncertainty compared to conventional methods. The downsides of the proposed method are the long computational time and the introduction of some bias from the denoising prior.

    Conclusion: DIP successfully denoise the parameter mapping process and applies to several applications with limited hyperparameter tuning. Further, it is easy to implement since DIP methods do not use network training data. Although time-consuming, uncertainty information from MC dropout makes the method more robust and provides useful information when properly calibrated.

    Ladda ner fulltext (pdf)
    fulltext
  • 50.
    Hellström, Thomas
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Ostovar, Ahmad
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Detection of Trees Based on Quality Guided Image Segmentation2014Ingår i: Second International Conference on Robotics and associated High-technologies and Equipment for Agriculture and forestry (RHEA-2014): New trends in mobile robotics, perception and actuation for agriculture and forestry / [ed] Pablo Gonzalez-de-Santos and Angela Ribeiro, RHEA Consortium , 2014, s. 531-540Konferensbidrag (Refereegranskat)
    Abstract [en]

    Detection of objects is crucial for any autonomous field robot orvehicle. Typically, object detection is used to avoid collisions whennavigating, but detection capability is essential also for autonomous or semiautonomousobject manipulation such as automatic gripping of logs withharvester cranes used in forestry. In the EU financed project CROPS,special focus is given to detection of trees, bushes, humans, and rocks inforest environments. In this paper we address the specific problem ofidentifying trees using color images. A presented method combinesalgorithms for seed point generation and segmentation similar to regiongrowing. Both algorithms are tailored by heuristics for the specific task oftree detection. Seed points are generated by scanning a verticallycompressed hue matrix for outliers. Each one of these seed points is thenused to segment the entire image into segments with pixels similar to asmall surrounding around the seed point. All generated segments are refinedby a series of morphological operations, taking into account thepredominantly vertical nature of trees. The refined segments are evaluatedby a heuristically designed quality function. For each seed point, thesegment with the highest quality is selected among all segments that coverthe seed point. The set of all selected segments constitute the identified treeobjects in the image. The method was evaluated with images containing intotal 197 trees, collected in forest environments in northern Sweden. In thispreliminary evaluation, precision in detection was 81% and recall rate 87%.

1234 1 - 50 av 168
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf