Multi-view Pedestrian Detection Using Statistical Colour Matching

To increase the robustness of detection in intelligent video surveillance systems, homography has been widely used to fuse foreground regions projected from multiple camera views to a reference view. The objective of this paper is to detect multiple pedestrians and identify the false-positive detections, which occur due to the foreground intersections of non-corresponding objects, in the top view using occupancy information and colour matching. Multiple homographies are used to detect the head plane and height of each pedestrian. The head locations can be used in the further tracking part. Experimental results show good performance of this method.