Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Autonomous Bed Detection and Real-time Patient Bed Entry-Exit Detection using Kinect RGB-D Camera
KTH, School of Information and Communication Technology (ICT).
2017 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Over the last two decades many studies have been conducted to avoid patient injuries caused by a lack of caregivers. The increase in global elderly population has lead to a growing demand of nursing staff in hospitals. The common practice to detect and avoid injuries in hospital involves invasive methods such as wearable devices which can cause inconvenience for patients and includes additional work for the nursing staff. Recent advances in computer vision technologies has brought with it the promising possibilities of autonomous patient supervision which can help reduce the work of hospital staff by using non-invasive video based patient activity monitoring.

Image processing team at Philips Research has successfully proposed and implemented RGB camera based trajectory method which is able to perform bed occupancy detection and body tracking tasks for General ward scenarios with reasonable reliability. The downside of RGB camera based trajectory detection method is that it is dependent on illumination conditions, position of camera and fails in cases of occlusion. RGB camera also raises concerns on privacy of patient during monitoring.

In recent days, depth sensing (3D) cameras are flooding the camera market and lot of research is being conducted to analyse their feasibility in different vision applications. This thesis work involves analysing the applicability of depth sensing cameras for patient monitoring application, design and implementation of autonomous bed detection and patient bed entry-exit detection. Subsequently the algorithm is ported on the Embedded ARM Imx6 PhyFLEX board and tested in real-time in a general ward scenario.

This project uses the novel technology of 3D depth measurement to autonomously detect the hospital bed, then detect patient bed entry-exits with enhanced reliability. The main goal of the project is to use 3D cameras to overcome the shortcomings of the RGB cameras. This thesis hopes to pave way for further research in 3D camera based patient monitoring solutions and intends to make patient stay in hospital more pleasant with continuous non-invasive patient supervision.

Place, publisher, year, edition, pages
2017. , p. 128
Series
TRITA-ICT-EX ; 2017:29
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:kth:diva-227799OAI: oai:DiVA.org:kth-227799DiVA, id: diva2:1205319
Subject / course
Electronic- and Computer Systems
Educational program
Master of Science - Embedded Systems
Examiners
Available from: 2018-05-14 Created: 2018-05-14 Last updated: 2018-05-14Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Information and Communication Technology (ICT)
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 12 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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