摘要
为解决边界模糊区域和低纹理区域易出现误匹配的问题,研究了基于图像分割的改进立体匹配算法.首先利用均值平移算法(Meanshift)分割参考图像,然后利用自适应加权自适应相异算法(ASW-SelfAd)计算初始视差,再利用奇异值分解算法(SVD)拟合视差平面,最后利用改进的聚类算法合并相邻图像分割区域,并利用协同算法优化能量函数以细化视差图.实验结果表明,该改进算法不仅能缩短匹配时间,提高匹配精度,而且在低纹理区域、视差不连续区域和遮挡区域也能准确匹配.
In order to solve the problem of fuzzy boundary and low texture regions prone to mismatching,this paper studied stereo matching algorithm based on image segmentation.The first step of the algorithm employs the meanshift algorithm to segment the reference image.Then,it＇s followed by the use of Adaptive Support Weighted SelfAdaptation dissimilarity algorithm（ASW-SelfAd）for the estimation of initial disparity.The third step is the application of Singular Value Decomposition（SVD）in solving the robust disparity plane fitting.Lastly,we apply improved clustering algorithm to merge the neighboring segments,and refine the disparity map by the new energy function.Matching experiments show that this method can not only improve the matching speed and accuracy,but also be an exact match in textureless regions,disparity discontinuous boundaries and occluded portions.
出处
《微电子学与计算机》
CSCD
北大核心
2014年第12期61-66,共6页
Microelectronics & Computer
基金
陕西省自然科学基金项目(2013JM8016)
关键词
图像分割
立体匹配
聚类
image segmentation
stereo matching
clustering
