Video Monitoring of Vulnerable People in Home Environment

Authors:
Quoc-Cuong Pham;Yoann Dhome;Laetitia Gond;Patrick Sayd
Affiliations:
CEA, LIST, Lab., Embedded Vision Systems, Gif s/ Yvette, France 91191;CEA, LIST, Lab., Embedded Vision Systems, Gif s/ Yvette, France 91191;CEA, LIST, Lab., Embedded Vision Systems, Gif s/ Yvette, France 91191;CEA, LIST, Lab., Embedded Vision Systems, Gif s/ Yvette, France 91191
Venue:
ICOST '08 Proceedings of the 6th international conference on Smart Homes and Health Telematics
Year:
2008

Citing 5
Cited 1

Summarising contextual activity and detecting unusual inactivity in a supportive home environment

Pattern Analysis & Applications
Human Tracking by Particle Filtering Using Full 3D Model of Both Target and Environment

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Contrast Context Histogram - A Discriminating Local Descriptor for Image Matching

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
Efficient hierarchical method for background subtraction

Pattern Recognition
A 3D Shape Descriptor for Human Pose Recovery

AMDO '08 Proceedings of the 5th international conference on Articulated Motion and Deformable Objects

Concept and Design of a Video Monitoring System for Activity Recognition and Fall Detection

ICOST '09 Proceedings of the 7th International Conference on Smart Homes and Health Telematics: Ambient Assistive Health and Wellness Management in the Heart of the City

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a Video Monitoring System, which aims to achieve behavior analysis of elderly people. Real-time tracking and posture discrimination enable to detect emergency situation (by trigging an alarm in case of fall detection for example) and to analyze long term activity which enforces medical follow-up. These are key-issues to improve healthcare quality for rural population. Monitoring human activity in a home environment is a challenging task in computer vision. A multi-camera system is proposed to address the complexity of home environment. Person silhouette is extracted thanks to a robust background/foreground segmentation process. A multi-view particle filter is built to track the silhouette in the scene and discriminate the person posture. This posture is used to interpret basic activities and detect falls. A finer gesture reconstruction is finally exposed which will offer a more accurate activity determination and gait analysis for future system.