A method for multi-target human behavior recognition in small and medium scenes

Abstract

Aiming at the low accuracy of behavior recognition technology for multi-target human behavior recognition in small and medium scenes, a method for multi-target human behavior recognition in small and medium scenes is proposed. In this paper, YOLOv5 and DeepSort are used to detect, track and locate human targets in the video stream. According to the detection frame, the appropriate size of the human target is cropped as the input image of the behavior recognition module to reduce the interference of human behavior background, and finally realize the multi-target human body behavior recognition. The behavior recognition module is composed of an improved C3D network, and the features extracted by YOLOv5 are shared with the behavior recognition module to reduce the amount of computation. Experiments show that this method achieves end-to-end recognition,and can recognize the behavior of different target human bodies in small and medium scenes, and achieves comparable results.