Title :
A New Structural Constraint and its Application in Wide Baseline Matching
Author :
Lu, X. ; Manduchi, R.
Author_Institution :
California Univ., Santa Cruz, CA
Abstract :
We introduce a new structural constraint that can be used for matching points in image pairs taken from a wide baseline. No assumption is made about the geometry of the 3D points or of surfaces in the scene, nor about the location or orientation of the cameras. This structural constraint can be used to reduce the search space when matching a number of feature points in two images, eliminating the risk of selecting a matching that is provably wrong because unrealizable
Keywords :
feature extraction; image matching; search problems; stereo image processing; 3D point geometry; feature point matching; image matching; image pairs; search space; structural constraint; surface geometry; wide baseline matching; Cameras; Computer vision; Explosions; H infinity control; Image reconstruction; Information geometry; Layout; Motion measurement; Sampling methods;
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2521-0
DOI :
10.1109/ICPR.2006.127
