利用图像分割的基于图割的立体匹配算法

立体匹配通过寻找同一空间景物在不同视点下投影图像的像素间的一一对应关系, 最终得到该景物的视差图。在对匹配算法作了深入研究的基础上, 提出了一种利用图像分割的基于图割的立体匹配算法。算法把参考图分割成多个区域, 然后用平面公式在一个分割中建立视差。视差模板是从初始视差分割中提取的。每一个分割被分配到精确的视差模板。构建全局能量函数,能量函数的鲁棒最小化是由基于图割的最优化获得的。算法对低纹理区域和接近视差边界区域有很好的匹配效果, 同时, 又解决了传统的基于全局算法中计算量过大, 实时性不好的问题。实验表明, 本算法能满足高精度、高实时性要求。

Graph-Cut-Based Stereo-Matching Algorithm Using Image Segmentation

Stereo-matching is an algorithm that through searching the corresponding relations between the projection images’ pixels of the same scene on different visual point, gains a disparity map of the scene finally. This paper presents a graph-cut-based stereo-matching algorithm using image segmentation on the basis of in-depth study on the images matching algorithms. In proposed algorithm, the reference image is divided into segments. Then modeling disparity is built inside a segment by a planar equation. A set of disparity layers is extracted from initial disparity segments in a clustering process. A global energy function is constructed. Robust minimization of the cost function is achieved by graph-cut-based optimization. The proposed algorithm produces good-quality results, especially in regions of low texture and close to disparity boundaries. The expensive computing cost for traditional global algorithms can also be reduced. Experiments demonstrate that the algorithm can meet both demands for high resolution and real time.