Measurement of target motion in image sequence

Abstract

In automatic image tracking systems, Ihe motion information on the target image is a very important cue for locking onto the aim point. A four points matching approach for measuring the motion information of a target image in a dynamic image sequence is proposed. Comparing with two simple spatio-temporal gradient approaches, it provides good measurements in a gaussian noisy image sequence. An algorithm for extracting four points of a target image by entropic segmentation is developed. The effect of different pre-processing techniques is also discussed. Finally, the simulations are effected by a natural FLIR target image template with two artificial manoeuvring paths. The simulation results appear satisfactory even in a noise corrupted medium.