Artificial Intelligence - Special volume on computer vision
Evaluation of Interest Point Detectors
International Journal of Computer Vision - Special issue on a special section on visual surveillance
Combining Appearance and Topology for Wide Baseline Matching
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
A direct method for stereo correspondence based on singular value decomposition
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Comparative study of algorithms for matching sets of reference points
Pattern Recognition and Image Analysis
Hi-index | 0.00 |
This paper presents a simple and effective method for matching two uncalibrated images. First, corner points are extracted in both images separately. Then the initial set of point matches is obtained by singular value decomposition of a well-designed correspondence strength matrix. A new expression of this matrix is introduced to get more reliable initial matches. Last, the epipolar geometry constraint is imposed to reject the false matches. Experimental results on real images show this method to be effective for general image matching.