DEM辅助下的倾斜航摄影像匹配方法  

Matching method for oblique aerial image assisted by DEM

作　　者：常越[1] 邓非[1,2] 李天烁 

机构地区：[1]武汉大学测绘学院,湖北武汉430079 [2]国家领土主权与海洋权益协同创新中心,湖北武汉430079

出　　处：《测绘工程》2017年第11期18-22,共5页Engineering of Surveying and Mapping

基　　金：国家自然科学基金资助项目(41271431;41401536);国家科技支撑计划课题(2012BAJ23B03)

摘　　要：在倾斜航空摄影测量中,倾斜影像间由于视角差异较大,具有较大几何变形,而具备仿射尺度不变性的ASIFT算法存在效率较低的问题,提出一种DEM辅助下的倾斜航摄影像匹配方法。该方法通过利用影像的粗略外方位元素和测区的DEM数据,首先对倾斜影像进行仿射变换来减弱几何变形;然后通过SIFT特征匹配算法来获取同名点对,并使用RANSAC剔除误匹配;最后将同名点对根据单应矩阵反算回原影像,以基础矩阵估计法剔除误匹配,获得最终匹配点对。通过对多组数据进行实验,结果表明,该算法的计算效率较高,获得的匹配点对在数量和分布情况上也更为理想。In the oblique aerial photogrammetry, the oblique images have large geometric deformation due to the great differences of the viewing angles. However, the algorithm with affine scaling invariance like ASIFT algorithm is less efficient. Therefore, this paper presents a DEM-assisted oblique aerial image matching method. Firstly, the geometrical deformation is weakened by affine transformation of the oblique image by making full use of the rough Exterior Orientation （EO） elements and DEM data. Secondly, Scale Invariant Feature Transform （SIFT） algorithm is used to match the corrected images to get the corresponding points, and then the false matches in them are eliminated by using the RANdom SAmple Consensus （RANSAC） algorithm. Finally, the homography matrix is used to calculate the corresponding point coordinates on the original image, and the mismatches are eliminated with Fundamental Matrix Estimation method in order to obtain the final corresponding points. Experiments conducted on many sets of oblique images demonstrate that the corresponding points obtained by the proposed algorithm are significantly improved in the computation efficiency, quantity and distribution.

关 键 词：倾斜影像匹配 DEM 仿射变换 尺度不变特征变换算法 误匹配剔除 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]