Local Geometrically Enriched Mixtures for Stable and Robust Human Tracking in Detecting Falls
Detecting a fall through visual cues is emerging as a hot research agenda for improving the independence of the elderly. However, the traditional motion-based algorithms are very sensitive to noise, reducing fall detection accuracy. Another approach is to efficiently localize and then track the fore...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2013-01-01
|
| Series: | International Journal of Advanced Robotic Systems |
| Online Access: | https://doi.org/10.5772/54049 |
| _version_ | 1818609923360030720 |
|---|---|
| author | Michalis Kokkinos Nikolaos D. Doulamis Anastasios D. Doulamis |
| author_facet | Michalis Kokkinos Nikolaos D. Doulamis Anastasios D. Doulamis |
| author_sort | Michalis Kokkinos |
| collection | DOAJ |
| description | Detecting a fall through visual cues is emerging as a hot research agenda for improving the independence of the elderly. However, the traditional motion-based algorithms are very sensitive to noise, reducing fall detection accuracy. Another approach is to efficiently localize and then track the foreground object followed by measurements that aid the identification of a fall. However, to perform robust and stable tracking over a long time is a challenging research aspect in computer vision society. In this paper, we introduce a stable human tracker able to efficiently cope with the trade-off between model stability (accurate tracking performance) and adaptability (model evolution to visual changes). In particular, we introduce local geometrically enriched mixture models for background modelling. Then, we incorporate iterative motion information methods, constrained by shape and time properties, to estimate high confidence image regions for background model updating. This way, we are able to detect and track the foreground objects even when visual conditions are dynamically changed over time (luminosity or background/foreground changes or active cameras). |
| first_indexed | 2024-12-16T15:06:15Z |
| format | Article |
| id | doaj.art-737925836f1b4741a69e816b565b2f2e |
| institution | Directory Open Access Journal |
| issn | 1729-8814 |
| language | English |
| last_indexed | 2024-12-16T15:06:15Z |
| publishDate | 2013-01-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | International Journal of Advanced Robotic Systems |
| spelling | doaj.art-737925836f1b4741a69e816b565b2f2e2022-12-21T22:27:07ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142013-01-011010.5772/5404910.5772_54049Local Geometrically Enriched Mixtures for Stable and Robust Human Tracking in Detecting FallsMichalis Kokkinos0Nikolaos D. Doulamis1Anastasios D. Doulamis2 National Technical University of Athens, Zografou, Athens, Greece National Technical University of Athens, Zografou, Athens, Greece Technical University of Crete, Kounoupidiania, Chania GreeceDetecting a fall through visual cues is emerging as a hot research agenda for improving the independence of the elderly. However, the traditional motion-based algorithms are very sensitive to noise, reducing fall detection accuracy. Another approach is to efficiently localize and then track the foreground object followed by measurements that aid the identification of a fall. However, to perform robust and stable tracking over a long time is a challenging research aspect in computer vision society. In this paper, we introduce a stable human tracker able to efficiently cope with the trade-off between model stability (accurate tracking performance) and adaptability (model evolution to visual changes). In particular, we introduce local geometrically enriched mixture models for background modelling. Then, we incorporate iterative motion information methods, constrained by shape and time properties, to estimate high confidence image regions for background model updating. This way, we are able to detect and track the foreground objects even when visual conditions are dynamically changed over time (luminosity or background/foreground changes or active cameras).https://doi.org/10.5772/54049 |
| spellingShingle | Michalis Kokkinos Nikolaos D. Doulamis Anastasios D. Doulamis Local Geometrically Enriched Mixtures for Stable and Robust Human Tracking in Detecting Falls International Journal of Advanced Robotic Systems |
| title | Local Geometrically Enriched Mixtures for Stable and Robust Human Tracking in Detecting Falls |
| title_full | Local Geometrically Enriched Mixtures for Stable and Robust Human Tracking in Detecting Falls |
| title_fullStr | Local Geometrically Enriched Mixtures for Stable and Robust Human Tracking in Detecting Falls |
| title_full_unstemmed | Local Geometrically Enriched Mixtures for Stable and Robust Human Tracking in Detecting Falls |
| title_short | Local Geometrically Enriched Mixtures for Stable and Robust Human Tracking in Detecting Falls |
| title_sort | local geometrically enriched mixtures for stable and robust human tracking in detecting falls |
| url | https://doi.org/10.5772/54049 |
| work_keys_str_mv | AT michaliskokkinos localgeometricallyenrichedmixturesforstableandrobusthumantrackingindetectingfalls AT nikolaosddoulamis localgeometricallyenrichedmixturesforstableandrobusthumantrackingindetectingfalls AT anastasiosddoulamis localgeometricallyenrichedmixturesforstableandrobusthumantrackingindetectingfalls |