A Software Framework for People Counting and Monitoring System in CCTV
Oliver C. Agustin, Byung-Joo Oh · 한국정보기술학회논문지 · 2010
This paper proposes a software framework for people counting system(PCS) in crowded environments using a single camera in stationary position. The proposed system is intended to estimates the number of people in indoor or outdoor environments. A background model of the scene is first constructed to detect and track moving objects (people) in a video stream. Detected foreground objects are then preprocessed to eliminate pixel noise and small artifacts by performing opening morphology operation on the foreground image. We then provide a framework for some classifiers to count the number of people present in the current video frame. The result shows a software tool for developing and testing a new people counting system(PCS).