Title :
Robust multi-view correspondence of noisy 2D points using relaxation
Author :
Lee, Dong Hoon ; Jung, Soon Ki ; Wohn, Kwangyun
Author_Institution :
Dept. of Comput. Eng., Kyungpook Nat. Univ., Taegu, South Korea
fDate :
4/13/2000 12:00:00 AM
Abstract :
An efficient ghost removal algorithm for reliably extracting correspondence information for 2D points from several views using epipolar constraints is proposed. The point matching relations are modelled using a weighted k-partite graph and a globally convergent iterative algorithm is used to extract reliable maximum cliques from the graph using probabilistic relaxation labelling. Experimental results show the effectiveness of the proposed method
Keywords :
graph theory; image matching; image motion analysis; iterative methods; epipolar geometry; ghost removal algorithm; global convergence; iterative algorithm; maximum clique; noisy 2D point matching; optical motion capture system; probabilistic relaxation labelling; robust multi-view correspondence; weighted k-partite graph;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20000553
