立体视觉校正也称为极线校正,它的目的是使得立体图像的对应极线平行于水平方向,消除垂直方向上的视差,从而使得在立体匹配过程中可以更为快速准确地寻找对应点.在传统的投影校正算法的基础上提出了一种鲁棒性校正算法,直接通过原始匹配点计算投影变换矩阵,利用遗传算法良好的全局搜索能力和Levenberg-Marquardt算法稳定快速的局部搜索功能进行分步优化计算,同时本算法采用了随机抽样一致算法（RANSAC）鲁棒估计思想,避免了由于对应点噪声引起的误差.此外,还针对两个平行放置的摄像机之间具有较小运动的情况,提出了一种鲁棒的优化函数.实验结果说明,该算法是一种有效的极线校正方法.

Rectification of stereo vision is also called rectification of Epipolar Lines. To search the corresponding points rapidly and accurately, the rectification is used to make the epipolar lines of stereo images be parallel to the horizontal direction and to remove the parallax in vertical direction. A robust algorithm is presented to rectify the stereo images based on the traditional projective rectification algorithm. In this method, the projective matrix is calculated by corresponding points and then is optimized by Levenberg-Marquardt and GA algorithm. And meanwhile the RANSAC algorithm is used to avoid the error caused by the noise. Furthermore, a robust optimization function is proposed for the situation with slight movement of two cameras. Experiments with real images show that the method is an effective rectification method.