Traditional color-based mean shift tracking algorithm is unable to accurately track the object. To address this problem, we present an improved tracking algorithm. The improved tracker integrates the color and motion cues which characterize the appearance and motion information of the object, respectively. These two visual cues can complement each other and make for more precise target localization. Experiments show that the proposed tracking algorithm has better performance than the traditional mean shift tracker.

A hybrid algorithm based on seeded region growing and k-means clustering was proposed to improve image object segmentation result. A user friendly segmentation tool was provided for the definition of objects, then k-means algorithm was utilized to cluster the selected points into k seeds-clusters, finally the seeded region growing algorithm was used for object segmentation. Experimental results show that the proposed method is suitable for segmentation of multi-colored object, while conventional seeded region growing methods can only segment uniform-colored object.

An improved block-matching algorithm for fast motion estimation is proposed. The matching criterion is the sum of absolute difference. The basic idea is to obtain the best estimation of motion vectors by an optimization of the search process which can terminate the time-consuming computation of matching evaluation between the current block and the ineligible candidate block as early as possible and eliminate the search positions as many as possible in the search area. The performance of this algorithm is evaluated by theoretic analysis and compared with the full search algorithm (FSA). The simulation results demonstrate that the computation load of this algorithm is much less than that of FSA, and the motion vectors obtained by this algorithm are identical to those of FSA.