The traditional semi-global matching methods provide a good trade-off between accuracy and complexity compared withthe local matching methods and global matching methods, however, they still need to traverse the full disparity searchrange to find the best matching point. Therefore, it still needs high computational cost especially for stereo images withlarge disparity search range. We proposes an efficient semi-global matching method that disparity search range is reducedbased on 3D plane fitting. Firstly, the simple linear iterative clustering (SLIC) algorithm is adopted to segment the stereoimages. Secondly, the dense SIFT keypoints are extracted and matched from the left and right images. Thirdly, similaradjacent superpixels are merged based on the gray mean and variance, and for each merged region, 3-D plane is fittedbased on matched keypoints. Finally, the pixel-wise disparity search range is limited into several pixels for more-globalmatching method which can reduce the computational complexity and obtain an accurate disparity map. Experimentalresults demonstrate that the computational speed of the new semi-global matching method is several times faster than thatof the original method, as well as offering a more accurate disparity map.
展开▼
