浅析最优斜面参数估计的局部立体匹配算法.docxVIP

基于最优斜面参数估计的局部立体匹配算法曹晓倩1,2，马彩文11.中国科学院西安光学精密机械研究所,陕西 西安7101192.中国科学院大学，北京100039摘 要：针对传统局部匹配算法在斜面场景匹配中所表现出的“阶梯效应”，本文提出了一种基于最优斜面参数估计的局部立体匹配算法。该算法首先为每一个像素随机地分配一组斜面参数，然后以新的斜面参数所定义的支撑域下当前像素的匹配代价是否减小为准则，迭代地进行斜面参数的“邻域传播—单点优化”过程，并最终使得计算结果收敛到最优斜面，同时估计得到稠密的亚像素级视差。通过对典型斜面场景图像和Middlebury标准测试图像对的匹配实验表明，本文算法在将对普通场景的匹配效果保持在当前先进水平的同时，对斜面场景的匹配消除了“阶梯效应，且匹配率代表了局部匹配的先进水平。关键词：图像处理；立体匹配；斜面估计；阶梯效应中图分类号：TP391.41，文献标识码： A 文章编号：Best slant-plane estimation based stereo matching algorithmCAO Xiao-qian1,2 MA Cai-wen11. Xi;an Institute ofoptics and precision mechenics , Chinese Academy of Sciences, Xi’an 710119, China;2. University of Chinese Academy of Sciences, Beijing 100039, ChinaAbstract：A novel stereo matching algorithm based on best slant-plane estimation is proposed in this paper in the purpose of eliminating“stair-casing” which shows up frequently in the slant scene matching process where the window-based matching algorithm is used. In this procedure, a slant parameter vector was randomly attributed to every pixel in the reference image firstly, then , those vectors are iteratively propagated between neighbor pixels followed by a recursively slant-plane parameter refinement process for each pixels in the principle of whether a lower cost could be got under the new slant-plane parameter vectors, until the parameter vectors are converged to the best slant-plane parameter vectors while a sub-pixel disparity is got for each pixel in the reference image. Experiment results indicate the effectiveness of the algorithm, the performance of the algorithm on the slant scene is ranked on top of those state-of –art algorithm which is relatively close to the algorithm proposed here, while the performance on the normal scene is comparable with the state-of –art algorithm.Key words： Image Processing Stereo matching slant plane evaluation stair-casing0 引 言立体视觉技术因其信息的丰富性以及在对抗环境中的隐蔽性在视觉导航，航天航空探测[1,2]等领域有很好的应用前景。而立体视觉的关键技术之一则是立体匹配，即寻找两幅或者多幅图像中对应于同一空间物点的像素，这一概念与普通图像处理中的图像配准[3,4]算法类似，只是立体匹配需要获取稠密的配