DocumentCode
322914
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
Volume
1
fYear
1997
fDate
9-14 Nov 1997
Firstpage
239
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;
fLanguage
English
Publisher
ieee
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
Type
conf
DOI
10.1109/IECON.1997.671054
Filename
671054
Link To Document