An eigenspace-based approach for human fall detection using Integrated Time Motion Image and multi-class Support Vector Machine

Abstract

Falls are a major health hazard for the elderly and a serious obstacle for independent living. Since falling causes dramatic physical-psychological consequences, development of intelligent video surveillance systems is so important due to providing safe environments. To this end, this paper proposes a novel approach for human fall detection based on combination of integrated time motion images and eigenspace technique. Integrated Time Motion Image (ITMI) is a type of spatio-temporal database that includes motion and time of motion occurrence. Applying eigenspace technique to ITMIs leads in extracting eigen-motion and finally multi-class Support Vector Machine is used for precise classification of motions and determination of a fall event. Unlike existent fall detection systems that only deal with limited movement patterns, we considered wide range of motions consisting of normal daily life activities, abnormal behaviors and also unusual events. Reliable recognition rate of experimental results underlines satisfactory performance of our system.