Description: The method used object matching to get objects’ position in different frames, and used feature monitoring to deal with object occlusion, object split and implement real-time update for objects features. Objects were matched based on the similarity voting of their features in successive frames. Experimental study had been carried out using image sequences captured in real scene. The experimental results show that the method is robust against noise, shadows, occlusion, and split and it performs multiple objects tracking finely.
File list (Check if you may need any files):
biye.m
Download