An Image Alignment Based Framework for Ground Vehicle Tracking from an Air-borne Platform

摘要

Ground vehicle tracking is an important component of Aerial Video Surveillance System (AVS), which has important military and civilian uses. This paper presents an image alignment based framework for ground vehicle tracking from an air-borne platform, which can precisely track a pointed out vehicle and get back it when it reappear. We track a set of point features of the selected vehicle by the technique of image alignment. An edge feature-based outlier rejection criterion, a Kalman filter and a reappearance verification program are used to make the proposed tracking system perform excellently under complicated conditions. Experimental results on real aerial images show that the proposed framework is rational and robust.