Robust tracking method with drift correction

A new method is proposed to address the problem of template drift, a common phenomenon in which the target gradually shifts away from the template in object tracking. This paper integrates drift monitoring and drift correction with template matching. During the tracking based on template matching, drift is corrected once it is detected. The robustness and practicality of the method have been proven by experimental results.

[1]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[2]  Christopher Haworth,et al.  Performance of reference block updating techniques when tracking with the block matching algorithm , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[3]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[4]  Takahiro Ishikawa,et al.  The template update problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[7]  Marc Pollefeys,et al.  Multiple view geometry , 2005 .

[8]  Heinrich Niemann,et al.  Efficient Feature Tracking for Long Video Sequences , 2004, DAGM-Symposium.

[9]  Bo Hu,et al.  Robust and Accurate Object Tracking Under Various Types of Occlusions , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[10]  Toshimitsu Kaneko,et al.  Template update criterion for template matching of image sequences , 2002, Object recognition supported by user interaction for service robots.