Stereo matching is an important research area in stereovision and stereo matching of curved surface is especially crucial. A nov el correspondence algorithm is presented and its matching uncertainty is compute d robustly for feature points of curved surface. The corners are matched by usin g homography constraint besides epipolar constraint to solve the occlusion probl em. The uncertainty sources are analyzed. A cost function is established and act s as an optimal rule to compute the matching uncertainty. An adaptive scheme Gau ss weights are put forward to make the matching results robust to noises. It mak es the practical application of corner matching possible. From the experimental results of an image pair of curved surface it is shown that computing uncertaint y robustly can restrain the affection caused by noises to the matching precision .
