Three-view matching algorithm for multipolyhedron reconstruction using genetic algorithm

Authors
Citation
Jd. Lee, Three-view matching algorithm for multipolyhedron reconstruction using genetic algorithm, COMPUT MATH, 42(10-11), 2001, pp. 1465-1483
Citations number
26
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Computer Science & Engineering
Journal title
COMPUTERS & MATHEMATICS WITH APPLICATIONS
ISSN journal
0898-1221 → ACNP
Volume
42
Issue
10-11
Year of publication
2001
Pages
1465 - 1483
Database
ISI
SICI code
0898-1221(200111/12)42:10-11<1465:TMAFMR>2.0.ZU;2-
Abstract
In this paper, a novel stereo matching algorithm based on genetic algorithm (GA) is proposed to find the correspondences among multipolyhedron objects in a three-view system. Optimal camera configuration in the approach is us ed to reduce the feature searching area on the image plane, and GA is then used to refine the matching results. Due to optimal camera configuration, w e can achieve a smaller searching area, less ambiguity, and a faster matchi ng process. The features on the second image near the intersection of the t wo epipolar lines derived from the first and the third images considered as possible triplets are refined using GA. The fitness function for every cor responding triplet is assigned according to the corresponding distance betw een the feature location and the intersection of two epipolar lines. The co nsistent connection relationship is then enforced in the evolution process to resolve the ambiguous correspondence triplets. Experimental results show that the 3-D multiple polyhedra in a complex scene can be successfully rec onstructed in a three-view system. (C) 2001 Elsevier Science Ltd. All right s reserved.