Title :
Robust point feature matching in projective space
Author_Institution :
Human-Computer-Interface Labs., STMicroelectronics, San Diego, CA, USA
Abstract :
We present a robust method for matching point features across a set of images under full perspective projection. An expectation-maximization-like algorithm is developed to build an optimal potential match set (PMS) between each consecutive pair of views, by iteratively maximizing a heuristic objective function. All two-view matches are combined to form an M-view potential match set (MPMS) with a low contamination rate. Outliers in MPMS are removed incorporating the least-median-of-squares technique with projective reconstruction. The current work extends previous ones in two- or three-view matching, or under affine camera projection. Results on real imagery demonstrate the validity of the proposed method.
Keywords :
feature extraction; image matching; affine camera projection; expectation-maximization-like algorithm; heuristic objective function; least-median-of-squares technique; low contamination rate; optimal potential match set; point features matching; real imagery; robust method; Cameras; Computer vision; Contamination; Detectors; Image edge detection; Iterative algorithms; Laboratories; Least squares approximation; Robustness; Tracking;
Conference_Titel :
Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on
Print_ISBN :
0-7695-1272-0
DOI :
10.1109/CVPR.2001.990546
