umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
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
3D Head Pose Estimation Using the Kinect
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
Visa övriga samt affilieringar
2011 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Head pose estimation plays an essential role for bridging the information gap between humans and computers. Conventional head pose estimation methods are mostly done in images captured by cameras. However accurate and robust pose estimation is often problematic. In this paper we present an algorithm for recovering the six degrees of freedom (DOF) of motion of a head from a sequence of range images taken by the Microsoft Kinectfor Xbox 360. The proposed algorithm utilizes a least-squares minimization of the difference between themeasured rate of change of depth at a point and the rate predicted by the depth rate constraint equation. We segment the human head from its surroundings and background, and then we estimate the head motion. Our system has the capability to recover the six DOF of the head motion of multiple people in one image. Theproposed system is evaluated in our lab and presents superior results.

Ort, förlag, år, upplaga, sidor
IEEE conference proceedings, 2011. s. 1-4
Nationell ämneskategori
Medicinteknik
Identifikatorer
URN: urn:nbn:se:umu:diva-52815DOI: 10.1109/WCSP.2011.6096866ISBN: 978-1-4577-1008-7 (tryckt)OAI: oai:DiVA.org:umu-52815DiVA, id: diva2:507238
Konferens
IEEE International Conference on Wireless Communications and Signal Processing (WCSP2011), 9-11 nov, TBD, Nanjing, China
Tillgänglig från: 2012-03-02 Skapad: 2012-03-02 Senast uppdaterad: 2018-06-08Bibliografiskt granskad
Ingår i avhandling
1. Human Motion Analysis for Creating Immersive Experiences
Öppna denna publikation i ny flik eller fönster >>Human Motion Analysis for Creating Immersive Experiences
2012 (Engelska)Licentiatavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

From an early age, people display the ability to quickly and effortlessly interpret the orientation and movement of human body parts, thereby allowing one to infer the intentions of others who are nearby and to comprehend an important nonverbal form of communication. The ease with which one accomplishes this task belies the difficulty of a problem that has challenged computational systems for decades, human motion analysis.

Technological developments over years have resulted into many systems for measuring body segment positions and angles between segments. In these systems human body is typically considered as a system of rigid links connected by joints. The motion is estimated by the use of measurements from mechanical, optical, magnetic, or inertial trackers. Among all kinds of sensors, optical sensing encompasses a large and varying collection of technologies.

In a computer vision context, human motion analysis is a topic that studies methods and applications in which two or more consecutive images from an image sequences, e.g. captured by a video camera, are processed to produce information based on the apparent human body motion in the images.

Many different disciplines employ motion analysis systems to capture movement and posture of human body for applications such as medical diagnostics, virtual reality, human-computer interaction etc.

This thesis gives an insight into the state of the art human motion analysissystems, and provides new methods for capturing human motion.

Ort, förlag, år, upplaga, sidor
Umeå: Umeå University, 2012. s. 71
Serie
Digital Media Lab, ISSN 1652-6295 ; 15
Nationell ämneskategori
Elektroteknik och elektronik
Identifikatorer
urn:nbn:se:umu:diva-55832 (URN)978-91-7459-416-4 (ISBN)
Presentation
2012-04-13, room A305, Department of Applied Physics and Electronics, Umeå University, Umeå, 10:00 (Engelska)
Handledare
Tillgänglig från: 2012-06-04 Skapad: 2012-06-04 Senast uppdaterad: 2018-06-08Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Personposter BETA

Abedan Kondori, FaridYousefi, ShahrouzLi, HaiboSonning, Samuel

Sök vidare i DiVA

Av författaren/redaktören
Abedan Kondori, FaridYousefi, ShahrouzLi, HaiboSonning, Samuel
Av organisationen
Institutionen för tillämpad fysik och elektronik
Medicinteknik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 1340 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
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