A Human Fall Detection System Using an Omni-Directional Camera in Practical Environments for Health Care Applications

This paper proposes a vision-based fall detection system for the elderly and patients at home or in health-care institutions. The system uses an omni-directional camera to avoid blind spot. The system also considers practical environmental factors that may take place in our daily life, such as the occurrence of light source glimmer, turning a light on and off and leaving over static abandoned objects in the environment. We divide the fall down patterns in omni-directional images into non-radial and radial directions according to the angle associated with a body line. We further categorize the radial fall down patterns into inward and outward directions. The recognition features proposed for the system include angle and length variation associated with the body line and motion history images. Given these features, a simple thresholding and decision tree technique is adopted for fall detection. Experimental results show that the proposed system can solve the problems of light source glimmer and static abandoned objects. In fall-down detection, the recognition accuracy is 0.87 and the Kappa value is 0.75. These results show that the proposed fall down detection system is quite effective.