Track Multiple Objects with Feature-Correlation Algorithms

We propose a method to compute objective contour feature. Conventional objective chain algorithms correlate the motion with area characteristics of the objectives to reach the goals. Nevertheless, they may not be efficient under certain circumstances of complicated tracking. In this paper, we incorporate the contour characteristic of the objective into conventional methods and thus construct a function to estimate the similarity of the objective. Experiments show that more reliable results are obtained when rigid objects are tracked.