Users behavior tracking for Education Assisting by using Multiple Kinect sensors

Abstract

It is difficult to track multiple people effectively in a complex environment because people's clothes and body shapes may be similar, and their postures may be constantly changing. This paper proposes a novel method for detecting and tracking multiple people in crowded places where people can be partially or completely occluding each other is proposed in this paper. In the method, the features of multiple people are detected and tracked by using a particle filter. Meanwhile, accurate color information is obtained by integrating color image and depth information by using YOLO human detection method. The effectiveness of the proposed method is proven by experiments tracking multiple children in a classroom. It is difficult to track multiple people effectively in a complex environment because people's clothes and body shapes may be similar, and their postures may be constantly changing.