Online Determination of Track Loss Using Template Inverse Matching

Online determination of track loss in the absence of ground truth is an important and challenging problem in visual tracking systems. In this paper, we construct a novel track loss determination strategy using Template Inverse Matching (TIM). The idea of TIM is to inverse the common process of template tracking match. Ground truth is not required to be known. It is proved to be highly efficient and accurate, and is adaptive to all the visual tracking frameworks. The proposed strategy is justified in the theoretical framework of Stable Marriage (SM) problem. In this paper, we prove that the combination between the target position got from the TIM algorithm and the original one can meet the constraints of SM pairs and is irreplaceable when a correct tracking process is performed. This guarantees the stability of object tracking. Compariative experiments show high accuracy of the present method in determining track loss. The performance of tracking systems can be improved based on online track loss determination.

[1]  Stéphane Lecoeuche,et al.  A New Kernel-Based Algorithm for Online Clustering , 2005, ICANN.

[2]  Lucy Y. Pao,et al.  Detecting track-loss for the Probabilistic Data Association Filter in the absence of truth data , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[3]  A. Murat Tekalp,et al.  Non-rigid object tracking using performance evaluation measures as feedback , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[4]  Matthew K. Franklin,et al.  Improved Efficiency for Private Stable Matching , 2007, CT-RSA.

[5]  Lucy Y. Pao,et al.  Determining track loss without truth information for distributed target tracking applications , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[6]  Qinfen Zheng,et al.  Self-Evaluation for Video Tracking Systems , 2004 .

[7]  Gregory D. Hager,et al.  A Particle Filter without Dynamics for Robust 3D Face Tracking , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[8]  Rama Chellappa,et al.  In Situ Evaluation of Tracking Algorithms Using Time Reversed Chains , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  L. B. Wilson,et al.  The stable marriage problem , 1971, Commun. ACM.

[10]  Masayuki Inaba,et al.  Robot vision system with a correlation chip for real-time tracking, optical flow and depth map generation , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[11]  Athman Bouguettaya,et al.  On-Line Clustering , 1996, IEEE Trans. Knowl. Data Eng..

[12]  Shuichi Miyazaki,et al.  Approximation algorithms for the sex-equal stable marriage problem , 2007, TALG.

[13]  Magnús M. Halldórsson,et al.  Improved approximation results for the stable marriage problem , 2007, TALG.

[14]  A. Murat Tekalp,et al.  Metrics for performance evaluation of video object segmentation and tracking without ground-truth , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).