Depth-Assisted Face Detection and Association for People Counting

This paper describes a system capable of detecting and counting people using the Kinect camera. Upon the assistance of the depth information, most false face detection can be effectively eliminated, and then a 3D data association is used for the link of tracks and detection results. Finally, the validated trajectory is used for counting the people who enters the region of interest. Experimental results show that the use of depth information strongly enhance the counting performance.