Title :
Adaptive Step Size Window Matching for Detection
Author :
Mekuz, Nathan ; Derpanis, Konstantinos G. ; Tsotsos, John K.
Author_Institution :
Dept. of Comput. Sci. & Center for Vision Res., York Univ., Toronto, Ont.
Abstract :
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
Keywords :
image matching; object detection; adaptive step size window matching; object detection; step size selection; theoretical worst case analysis; Algorithm design and analysis; Application software; Computational efficiency; Computer science; Computer vision; Image reconstruction; Object detection; Optical devices; Stereo image processing; Stereo vision;
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2521-0
DOI :
10.1109/ICPR.2006.224
