A motion tracking method based on Kalman filter combined with mean-shift

In this paper, it proposes an object tracking algorithm based-on the Kalman filter combined with the mean-shift algorithm. It can predict the object motion more accurate with Kalman filter, including position and velocity. And the adjacent locations of the predicted point are defined as the search window. In the search window, the position of object is fixed on by mean-shift. The experiment results show that this algorithm can make full use of the prediction function of Kalman filter, improve the search speed, and achieve a more accurate tracking even the color is similar, and also solve the problem of shelter to some extent.

[1]  Shai Avidan,et al.  Support Vector Tracking , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Gary R. Bradski,et al.  Real time face and object tracking as a component of a perceptual user interface , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[3]  Luc Van Gool,et al.  Real-time affine region tracking and coplanar grouping , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[4]  Greg Welch,et al.  Welch & Bishop , An Introduction to the Kalman Filter 2 1 The Discrete Kalman Filter In 1960 , 1994 .

[5]  Takeo Kanade,et al.  Algorithms for cooperative multisensor surveillance , 2001, Proc. IEEE.

[6]  Larry S. Davis,et al.  Mean-shift analysis using quasiNewton methods , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).