The Elderly Man Fall Recognition Algorithms Based on Video Monitoring
Wan Jiang Han · Journal of Taiyuan University of Science and Technology · 2013
How to identify the elderly man falls is a difficult technical problem in image processing. In order to achieve the aim of identifying the elderly man fall behaviors,this paper proposes a new people fall identification algorithm. Three frame differential methods were used to extract the contour of the target image in the video,and then the fuzzy outline denoising,expansion,corrosion,such as the Canny edge detection processing were done,and then the center of gravity of the binary image was obtained,and the center of gravity location and magnitude of the acceleration was used to determine the behaviors of older people whether they fall or not,the alarm information will be sent if they fall. The experimental results show that the algorithm is able to achieve better recognition results.