On optimizing template matching via performance characterization

Template matching is a fundamental operator in computer vision and is widely used in feature tracking, motion estimation, image alignment, and mosaicing. Under a certain parameterized warping model, the traditional template matching algorithm estimates the geometric warp parameters that minimize the SSD between the target and a warped template. The performance of the template matching can be characterized by deriving the distribution of warp parameter estimate as a function of the ideal template, the ideal warp parameters, and a given noise or perturbation model. In this paper, we assume a discretization of the warp parameter space and derive the theoretical expression for the probability mass function (PMF) of the parameter estimate. As the PMF is also a function of the template size, we can optimize the choice of the template or block size by determining the template/block size that gives the estimate with minimum entropy. Experimental results illustrate the correctness of the theory. An experiment involving feature point tracking in face video is shown to illustrate the robustness of the algorithm in a real-world problem.

[1]  Yiannis Aloimonos,et al.  The Statistics of Optical Flow , 2001, Comput. Vis. Image Underst..

[2]  Michael J. Black,et al.  EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation , 1996, International Journal of Computer Vision.

[3]  Harry Shum,et al.  Construction and refinement of panoramic mosaics with global and local alignment , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[4]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[5]  P. Pirsch,et al.  Advances in picture coding , 1985, Proceedings of the IEEE.

[6]  Takeo Kanade,et al.  A Multibody Factorization Method for Independently Moving Objects , 1998, International Journal of Computer Vision.

[7]  David J. Fleet,et al.  Robust Online Appearance Models for Visual Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Thomas S. Huang,et al.  Explanation-based facial motion tracking using a piecewise Bezier volume deformation model , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[9]  W. R. Buckland,et al.  Distributions in Statistics: Continuous Multivariate Distributions , 1973 .

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

[11]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Richard Szeliski,et al.  Construction of Panoramic Image Mosaics with Global and Local Alignment , 2001 .

[13]  Dorin Comaniciu,et al.  Robust real-time myocardial border tracking for echocardiography: an information fusion approach , 2004, IEEE Transactions on Medical Imaging.

[14]  N. L. Johnson,et al.  Continuous Univariate Distributions. , 1995 .

[15]  Michel Dhome,et al.  Hyperplane Approximation for Template Matching , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  José M. F. Moura,et al.  Image motion estimation-convergence and error analysis , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[17]  Toshimitsu Kaneko,et al.  Feature selection for reliable tracking using template matching , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[18]  P. Anandan,et al.  Hierarchical Model-Based Motion Estimation , 1992, ECCV.

[19]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.