Real-time bi-directional people counting using video blob analysis

In this paper an analysis and implementation of the new algorithm for detecting and counting people in video surveillance systems is presented. First, we recapitulate methods used in the commercial systems, which can be used for people counting. Next, we concentrate on our new Matlab/Simulink model for detecting people, who are passing under a camera positioned vertically down at the entrance to a monitored area (e.g., a building). The prepared algorithm takes the direction of the transition of a person into account.