结合离散化描述与同名点约束的线特征匹配

Line Matching Based on Discrete Description and Conjugate Point Constraint

由于受到多重因素的影响,影像中提取的线特征经常出现断裂、变形、遮挡等问题。为克服上述问题对线特征匹配的影响,本文提出一种结合离散化描述与同名点约束的航空影像线特征匹配算法。算法首先利用单应性约束结合核线约束精简候选线特征数量;然后采用"以点代线"的方式,通过统计线上同名点的分布情况确定线特征初匹配结果;最后根据线特征与其邻域内同名点间的距离关系对匹配结果进行核验,以保证匹配的可靠性。选取AMC580相机系统所获得的航空影像进行线特征匹配试验,结果表明,本文算法匹配正确率高,匹配速度相对较快,并可实现曲线匹配及断裂线特征的多对多匹配。与已有匹配算法进行比较,本文算法在影像间存在有尺度、亮度、旋转变换等复杂条件下的匹配正确率均高于90%,具有较好的匹配稳定性。

Many unfavorable factors may hinder the line matching,such as fracture,deformation or occlusion occurred in line extraction.In order to overcome these problems,a novel method for line matching based on discrete description and conjugate point constraint is proposed.Firstly,the method employs the homography constraint together with epipolar constraint to determine candidate lines.Then,the initial line matching results are obtained by the distribution statistics of the conjugate points on the line.Finally,the mismatching in matched line pairs is eliminated by the similarity verification of line-point affine invariant.Extensive experiments on AMC580 aerial image set demonstrate the better performance of the proposed method as well as its superiority in curve matching and many-to-many matching.Compared with existing line matching methods,the proposed method can obtain more accurate line matching results under changes of image scale,brightness,occlusion,rotation,and achieves a performance of 90%higher matching correctness.