Research on Human Motion Recognition System Based on MEMS Sensor Network

The traditional human motion perception and behavior recognition methods are based on machine vision and image processing. This method has the disadvantages of strong intrusion of individual data privacy, large environmental impact and tedious data processing, and cannot meet the practical requirements in real time. This paper introduced a solution of accurately capture human motion by using multi-sensor of MEMS to construct Zigbee wireless network, and utilizing SVM classification algorithm to realize human action recognition efficiently. The system is used to detect the abnormal human fall behavior, which is perfect reliability and real-time performance and the recognition accuracy of the action is above to 90%.