Title :
Matching condition for range images
Author :
Zhien, Yu ; Ke, Wang ; Tanfeng, Sun
Author_Institution :
Dept. of Electron. Eng., Jilin Univ. of Technol., Changchun, China
Abstract :
To find the correspondences between the key features of two range images is important for computer vision, motion estimation or autonomous navigation. False match is one of the problems that needs to be solved. After analyzing the reason for producing false matches in finding the correspondences between the key features of two range images, a matching condition for range images is presented in this paper. The approach is first to establish 3-D models of the range images and then use the moment invariant technique to find out the matching condition that can reduce or get rid of the false matches
Keywords :
computer vision; image matching; matrix algebra; motion estimation; navigation; 3-D models; autonomous navigation; computer vision; false matches; image ranges; matching condition; moment invariant technique; motion estimation; Computer vision; Feature extraction; Helium; Image analysis; Layout; Motion estimation; Navigation; Object recognition; Position measurement; Sun;
Conference_Titel :
Industrial Electronics, Control and Instrumentation, 1997. IECON 97. 23rd International Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-7803-3932-0
DOI :
10.1109/IECON.1997.671054
