Implementation of Behavior Recognition Based on Machine Vision
Yuanjun Ding, Haibo Pu, Jiaxin Zhang, Jing Yang · 2019
Since the beginning of the 21st century, with the rapid development of the global economy and the rapid advancement of science and technology, real-time monitoring of human behavior through video surveillance has become a common security measure. However, most of them have a series of problems such as fast calculation speed, low recognition accuracy and delay. In this paper, the moving target detection is performed on the video sequence frame, and the moving target is tracked and analyzed. Through the related algorithms to complete the recognition of the behavior of the target human body and the determination of normal and abnormal behavior, it has broad application prospects in the future.