A vision-based people counting approach based on the symmetry measure

In this paper, we propose a vision-based people counting system. The symmetry property of human torso is utilized for the detection of people. Using the symmetry property as feature, one can solve the incomplete extraction of human silhouette problem that is commonly encountered in the process of background subtraction. In addition, since the perspective projection effect may influence the orientation of principal axis of a torso, we also propose a solution to address this issue. The experiment results show that the proposed system can perform accurate people counting.