基于模拟退火算法的立体匹配搜索方法

选择图像的边缘特征点作为匹配基元，求出边缘梯度的大小、方向和拉普拉斯值作为特征的属性值，在满足一定的立体匹配约束条件下，建立全局能量函数和状态空间，并用模拟退火算法，随着对状态空间的随机扰动，使能量函数达到全局最小，从而实现立体匹配。

Stereo matching searching method based on simulated annealing algorithm

The edge feature points were chosen as the primitives for matching. During the edge detection, the magnitude and direction of the edge gradient and the Laplace values were figured out as the three properties of the edge feature points. On the condition of some constraints for stereo matching, a global energy function and its corresponding state space were built. With the state space transferring, simulated annealing algorithm was used to minimize the energy function. When the energy function arrived the minimization, all the features in left image would find the corresponding features in the right images.