梁艳, 盛业华, 张卡, 杨林. 利用局部仿射不变及核线约束的近景影像直线特征匹配[J]. 武汉大学学报 ( 信息科学版), 2014, 39(2): 229-233. DOI: 10.13203/j.whugis20120611
引用本文: 梁艳, 盛业华, 张卡, 杨林. 利用局部仿射不变及核线约束的近景影像直线特征匹配[J]. 武汉大学学报 ( 信息科学版), 2014, 39(2): 229-233. DOI: 10.13203/j.whugis20120611
LIANG Yan, SHENG Yehua, ZHANG Ka, YANG Lin. Linear Feature Matching Method Based on Local Affine Invariant andEpipolar Constraint for Close-range Images[J]. Geomatics and Information Science of Wuhan University, 2014, 39(2): 229-233. DOI: 10.13203/j.whugis20120611
Citation: LIANG Yan, SHENG Yehua, ZHANG Ka, YANG Lin. Linear Feature Matching Method Based on Local Affine Invariant andEpipolar Constraint for Close-range Images[J]. Geomatics and Information Science of Wuhan University, 2014, 39(2): 229-233. DOI: 10.13203/j.whugis20120611

利用局部仿射不变及核线约束的近景影像直线特征匹配

Linear Feature Matching Method Based on Local Affine Invariant andEpipolar Constraint for Close-range Images

  • 摘要: 目的 针对近景影像中直线因遮挡、提取算法等带来的匹配问题,提出了一种基于局部仿射不变及核线约束的直线特征匹配方法。该方法在对立体近景影像进行同名点匹配及直线特征提取的基础上,首先利用直线特征与邻域内以同名点为端点的虚拟直线段的相交仿射不变性进行候选同名直线的搜索,再借助核线约束确定目标直线与候选同名直线的重叠部分,然后通过直线特征的角度及支撑域灰度的综合相似性测度进行匹配,得到正确的同名直线。利用该方法对不同几何变换下的近景影像进行实验,结果表明,本方法具有较好的可靠性和准确性。

     

    Abstract: Objective To solve the line matching problem caused by obstruction and extraction algorithm for close-range images,a novel algorithm of matching straight line based on local affine invariant and epipolarconstraint is presented in this paper.On the basis of straight line extraction and corresponding pointmatching on close-range image pairs,the linear feature’s candidate corresponding lines are firstlysearched based on the intersection affine invariant character of the lines including the extracted andvirtual straight ones,while endpoints of the virtual are corresponding points near the extracted lines.Then,the overlapping parts of the target lines and the matching candidates are calculated based onepipolar constraint.The right corresponding lines are finally acquired with the help of the comprehen-sive similarity measure derived from angle and neighborhood grey level of the straight line.Using theapproach proposed in this paper,experiments were carried out for the close-range images under differ-ent geometric transformation.The results show that this method has a good reliability and accuracy.

     

/

返回文章
返回