基于双目视觉的基准差梯度立体匹配法

被引:9
作者
管业鹏
顾伟康
机构
[1] 浙江大学信息科学与电子工程学系
关键词
特征点; 灰度相关; 复峰集; 匹配; 基准点;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
因灰度相关只是从一个侧面来描述左右图像特征点区域之间的灰度相似性 ,没有考虑特征点之间的空间相关性 ,因此利用灰度间的相似性作为测量标准进行匹配 ,不可避免地出现误匹配 ,提出了在进行双目视觉立体匹配时 ,采用灰度相关匹配技术 ,提取复峰特征点作为初始匹配集 ,采用视差梯度有限约束优化初始匹配集。利用左右图像一对已知对应基准点 ,通过计算基准点与复峰集各点间的基准差梯度 ,采用基准差梯度极小化评判标准 ,确定唯一匹配 ,并将匹配结果确定为新的基准点以不断更新基准点 ,直至左 (右 )图像特征点匹配完毕。通过分别对一幅弱纹理实际自然图像及已知三维坐标标准件的三维重建 ,证实了所提方法的有效性和可靠性。
引用
收藏
页码:74 / 77
页数:4
相关论文
共 9 条
[1]  
matching point features with ordered geometric, rigidity, and disparity constrains. Hu X and Ahuja N. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1994
[2]  
Learning and feature selection in stereo matching. Lew M S and Huang T S. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1994
[3]  
A multiple-baseline stereo. Okutomi M and Kanade T. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C], Osaka, Japan . 1991
[4]  
A Direct Method for Stereo Correspondence based on Singular Value Decomposition. Pilu M. In: Proceedings of 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C], San Juan, Puerto Rico . 1997
[5]  
Fast block matching algorithm based on the winner - update strategy. Chen Y S,Hung Y H and Fuh C S. IEEE Transactions on Image Processing . 2001
[6]  
A stereo matching algorithm with an adptive window: theory and experiment. Kanada T and Okutomi M. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1994
[7]  
Faster image template matching in the sum of the absolute value of differences measure. Atallah M J. IEEE Transactions on Image Processing . 2001
[8]  
A locally adaptive window for signal matching. Okutomi M,Kanade T. In: Proceedings of the Third International Conference on Computer Vision[C], Osaka, Japan . 1990
[9]  
Fast full-search block matching. Brunig M,Niehsen W. IEEE Transactions on Circuits and Systems for Video Technology . 2001