The epipolar geometry is the fundamental and important constraint between stereo image pair. It is independent of scene structure and plays a very important role in feature correspondence

Homography characterizes the correspondences between the two views due to the same plane scene which is extensively applied in plane scenes. To avoid the degenerate configuration when directly computing the homography given the epipolar geometry in curve scene

the area-detection approach is presented in this paper. In addition

the constraint relation between homography matrix and fundamental matrix is involved in the homography estimation. The two schemes can greatly improve the matching precision and efficiency of the algorithm

Experimental results with real image data have illustrate the performance of the schemes.