umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
AWSAS: Automated Work Safety and Alert System Using Depth Cameras
Umeå University, Faculty of Science and Technology, Department of Computing Science.
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Labourers in factories and companies all over the world perform a lot of tasks and movements that can cause musculoskeletal disorders (MSDs). MSDs lead to huge overhead costs to their factories and companies which result from sick leave days, compensations and lower production. That is why many workplaces are now taking actions to apply more robust worker safety practices. One of these practices is applying ergonomic evaluations within the workspace. Some ergonomic techniques require expensive motion tracking sensors or marker based tools in which they either need lots of initial setups or need large spaces to be considered under specific conditions. Other methodologies are done manually and require constant supervision by highly paid ergonomics experts, where the evaluations are not done in real-time and are opened to human errors. Employers need to have a body ergonomics assessment tool in which have low cost, simple to use, performs in real-time, effective and has non-interfere methodology with the work being performed.This research aimed to perform a framework by using depth cameras to facilitate a low-cost posture analysis and ergonomic real-time assessment for workers in different industries. We implemented a system and a framework using Microsoft Kinect that can be used in companies and factories, in which it evaluates, notifies and visually alerts workers in real-time if their current posture is on the edge of being at risk and may have injuries, without the need of having markers on their bodies. We defined a detailed methodology and framework for data aggregation between low-cost depth cameras and body ergonomic assessment tools. We integrated REBA ergonomic assessment tool procedures with depth cameras outputs to give a real-time evaluation for the postures of workers in their daily work. Our results showed that our system has been very effective and gives visual feedback for risks in real time, which will help workers to improve their body postures and reduce the risk of being injured. Moreover, our system has achieved comparable accuracy with 83% to the standard manual ergonomics evaluation procedures or expensive marker based solutions, making it a good and cheap alternative.

Place, publisher, year, edition, pages
2019. , p. 69
Series
UMNAD ; 1178
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:umu:diva-160124OAI: oai:DiVA.org:umu-160124DiVA, id: diva2:1324199
Educational program
Master of Science Programme in Computing Science and Engineering
Supervisors
Examiners
Available from: 2019-06-13 Created: 2019-06-13 Last updated: 2019-06-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Department of Computing Science
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 198 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf