A Study of Fall Detection: Review and Implementation

This thesis presents a research study on Fall detection with a comprehensive survey on available related literature and an evaluation experiment. Fall detection is a major challenge in the public health care domain, especially for the elderly, and reliable surveillance is a necessity to mitigate the effects of falls. The technology and products related to fall detection have always been in high demand within the security and the health-care industries. An effective fall detection system is required to provide rgent support and to significantly reduce the medical care costs associated with falls. In this thesis, we initially give a comprehensive survey of different systems for fall detection and their underlying algorithms. Fall detection approaches are divided into three main categories: wearable device based, ambience device based and vision based. These approaches are summarised and compared with each other and a conclusion is derived with some discussions on possible future work. Then we present an evaluation of fall detection using optical flow. Optical flow is one of the widely used approaches in computer vision to estimate motion. The literature of optical flow is briefly reviewed and some of the methods are implemented with discussion on experimental results. The best output yielding algorithm with respect to accuracy is used to setup an evaluation of fall detection. The evaluation compares our experimental results with the results obtained using other techniques. At the end we draw a conclusion in general on our research study and in particular on our contributions: Fall detection survey and Fall detection Evaluation. We also point out the futuristic direction of our research study with suggestions on possible areas with further development.