Contour matching by epipolar geometry

Mao-Lin Hu; Damin Zhang; Sui Wei

doi:10.1117/12.539844

Translator Disclaimer

25 September 2003 Contour matching by epipolar geometry

Mao-Lin Hu, Damin Zhang, Sui Wei

Author Affiliations +

Proceedings Volume 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition; (2003) https://doi.org/10.1117/12.539844
Event: Third International Symposium on Multispectral Image Processing and Pattern Recognition, 2003, Beijing, China

Abstract

Matching features computed in images is an important process in multiview image analysis. When the motion between two images is large, the matching problem becomes very difficult. In this paper, we propose a contour matching algorithm based on geometric constraints. With the assumption that the contours are obtained from images taken from a moving camera with static scenes, we apply the epipolar constraint between two sets of contours and compute the corresponding points on the contours. From the initial epipolar constraints obtained from comer point matching, candidate contours are selected according to the epipolar geometry, the linear relation among tangent vectors of the contour. In order to reduce the possibility of false matches, the curvature of the contour of match points on a contour is also used as a selection method. The initial epipolar constraint is refined from the matched sets of contours. The algorithm can be applied to a pair or two pairs of images. All of the processes are fully automatic and successfully implemented and tested with various synthetic images.

Citation Download Citation

Mao-Lin Hu, Damin Zhang, and Sui Wei "Contour matching by epipolar geometry", Proc. SPIE 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition, (25 September 2003); https://doi.org/10.1117/12.539844

ACCESS THE FULL ARTICLE