Abstract
This thesis proposes a vision-based people counting system that can count the number of persons getting in or out of the entrance of a building.First, we develop a so-called adaptive AV codebook background model and use background subtraction to divide foreground object from background in RGB color-space. In ROI (range of interest), we use the template matching method to find the objects, and then apply Hough transform to detect head contours to verify whether the object is a person. Second, we use a white rectangle to locate personal location and record the bottom center point as the trajectory point. To track the moving object, we compute the color distance between the previous and current tracked object, and link the center points which belong the same person as the trajectory of movement. Finally we analyze the trajectory to determine whether the person enters or exits or just passes by the entrance. Finally some experimental results are illustrated to verify our system.