| 摘要 |
A system and method for stereo matching of at least two images, e.g., a s tereoscopic image pair, employing a global optimization function, e.g., a be lief propagation function, that utilizes dynamic programming as a preprocess ing step are provided. The system and method of the present disclosure provi de for acquiring a first image and a second image from a scene (402), estima ting the disparity of at least one point in the first image with at least on e corresponding point in the second image (404, 406), and minimizing the est imated disparity using a belief propagation function (410), e.g., a global o ptimization function, wherein the belief propagation function is initialized with a result of a deterministic matching function (408), e.g., dynamic pro gramming, applied to the first and second image to speed up the belief propa gation function. The system and method further generates a disparity map fro m the estimated disparity and converts the disparity map into a depth map. |
