A real-time people tracking system based on trajectory estimation using single field of camera view

摘要

Object detection is a crucial step for video surveillance systems. In this paper, we propose to detect moving objects in video sequences. Under the assumption that our camera is fixed, we use first subtracting the background to extract moving objects. From the detected foreground we applied the Harris corner detector to identify points of interest on the moving object. The analysis of connected components detected by subtracting the background allows grouped the pixels of moving objects in order to extract the center of gravity to draw the trajectory of the objects present in the scene.