Using optic flows as extra constraints for binocular stereo matching

摘要

Stereo matching techniques is a hot issue and a difficult problem of computer vision. Because the accuracy and real-time of matching will affect the follow-up work, stereo matching techniques is also a central issue in the visual field. In view of the current stability and accuracy of binocular stereo matching algorithm is poor, the optic flows as an additional condition of a new algorithm for stereo matching is presented. This method doesn't need epipolar constraint; therefore the range of correspondence research is within a square area centred on the seed point position. Furthermore, the correspondence research is conducted in continuous image sequences rather than the left and right image pairs. So, for the right image sequence, the optic flows can be calculated on all candidate points to be matched with the seed points in the left image. The experimental results demonstrate that this method can improve the matching accuracy and stability.