Title :
Ridge´s corner detection and correspondence
Author :
Shilat, Erez ; Werman, Michael ; Gdalyahn, Y.
Author_Institution :
Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
Abstract :
Traditionally, corners are found along step edges. In this paper we present an alternative approach-corners along ridges/troughs and local minima points. These features seem to be more reliable for tracking. A new approach for sub-pixel localization of these corners is suggested, using a local approximation of the image surface
Keywords :
computational geometry; computer vision; feature extraction; Ridge´s corner detection; corner correspondence; image surface; local approximation; local minima points; step edges; subpixel localization; Calibration; Computer science; Computer vision; Detectors; Image edge detection; Image sequences; Layout; Motion estimation; Navigation; Tensile stress;
Conference_Titel :
Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on
Conference_Location :
San Juan
Print_ISBN :
0-8186-7822-4
DOI :
10.1109/CVPR.1997.609446
