Title :
GA-based three-view matching algorithm for multi-polyhedron reconstruction
Author_Institution :
Dept. of Electr. Eng., Chang Gung Univ., Tao-Yuan, Taiwan
fDate :
1/22/1998 12:00:00 AM
Abstract :
A GA-based stereo matching algorithm is proposed for finding the correspondences among multi-polyhedron objects in a three-view system. An optimal camera configuration is used to reduce the feature searching area and a genetic algorithm is employed to refine the matching results. Experimental results show that the 3D multiple polyhedra in a complex scene can be successfully reconstructed. The proposed algorithm is fast, requires little memory, and is noise tolerant
Keywords :
genetic algorithms; image matching; image reconstruction; stereo image processing; complex scene; feature searching area reduction; genetic algorithm; multi-polyhedron reconstruction; optimal camera configuration; stereo matching algorithm; three-view matching algorithm;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19980146
