An Abnormal Behavior Monitoring System with the Algorithm Design Based on Deep Learning
To monitor abnormal behavior of people in public places and send alarm information automatically,an embedded real-time abnormal behavior monitoring system based on deep learning is designed.The system detects the key point coordinates of human body by pose detection network in the embedded equipment,after the image information is captured by the camera,and classifies the key point coordinates for abnormal behavior with deep forest algorithm.When the abnormal behavior is moni-tored,the information is sent to the server-side,and the server-side notifies the user-side.Compared with manual monitoring and intelligent monitoring systems using server-side computing neural network,this system is less expensive and requires less transmission speed and stability of the network.Experimental results show that the system can effectively detect abnormal be-haviors such as violence and falling in real time and send alarm messages automatically.
deep learningembedded systembehavior detectionintelligent monitoringdeep forest algorithm
万方数据
维普
