Adaptive Step Size Window Matching for Detection

An often overlooked problem in matching lies in selecting an appropriate step size. The selection of the step size for real-time applications is critical both from the point of view of computational efficiency and detection performance. Current systems set the step size in an ad hoc manner. This paper describes an algorithm for selecting the step size based on a theoretical worst case analysis. We have implemented this adaptive step size method in an object detection algorithm. Experimental evaluation demonstrates the effectiveness of our proposed algorithm

[1]  Gregory D. Hager,et al.  Real-time tracking of image regions with changes in geometry and illumination , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  R. A. Silverman,et al.  Introductory Real Analysis , 1972 .

[3]  Bernd Jähne,et al.  Digital Image Processing: Concepts, Algorithms, and Scientific Applications , 1991 .

[4]  Minas E. Spetsakis,et al.  Optimal Computing Of Structure From Motion Using Point Correspondences In Two Frames , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[5]  Ernest L. Hall,et al.  Sequential Hierarchical Scene Matching , 1978, IEEE Transactions on Computers.

[6]  P. Anandan,et al.  A computational framework and an algorithm for the measurement of visual motion , 1987, International Journal of Computer Vision.

[7]  Darius Burschka,et al.  Advances in Computational Stereo , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[9]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Wu Zhong.  International Trends of Pattern Recognition Research A Brief Introduction to the 18th International Conference on Pattern Recognition , 2006 .