Feature Point Matching Using Temporal Smoothness in Velocity

One of the vital problems in motion analysis is to match a set of feature points over an image sequence. In this paper, we solve this problem by relying on continuity of motion which is known to play an important role in motion perception in biological vision systems. We propose a relaxation algorithm for feature point matching where the formation of smooth trajectories over space and time is favored. Experimental results on a laboratory generated as well as a real scene sequence are presented to demonstrate the merit of our approach.