基于几何约束的倾斜影像特征匹配方法  

Feature Matching Method of Oblique Images Based on Geometric Constraints

作　　者：韦春桃[1] 张冬梅 WEI Chuntao;ZHANG Dongmei(School of Architecture&Construction,Chongqing Jiaotong University,Chongqing 400074,China)

机构地区：[1]重庆交通大学土木工程学院,重庆400074

出　　处：《西南交通大学学报》2024年第2期353-360,共8页Journal of Southwest Jiaotong University

基　　金：重庆市基础科学与前沿技术研究专项重点项目(cstc2015jcyj BX0023)。

摘　　要：针对倾斜影像视角变换较大、重复纹理导致匹配数量少、匹配精度不高的问题,提出一种适用于倾斜影像的特征点、线分级匹配方法.首先,用直线提取(检测)算法(LSD)获取影像直线特征,并将直线特征以一定约束进行直线组对,构建直线对区域与改进的SIFT(scale-invariant feature transform)特征描述符进行匹配,使用RANSAC算法剔除误匹配,获得初始匹配结果后再进行核线约束;然后,利用已获得直线对区域进行影像局部纠正,在纠正后的局部影像上采用SIFT匹配并反算回原始影像,利用得到的同名点全局纠正倾斜影像,并进行特征点匹配与采用基于方格的运动统计算法(GMS)剔除误匹配,仍将匹配结果反算回原始影像上;最后,将仿射尺度不变特征变化结果与点拓展匹配结果进行合并,得到最终匹配结果.试验结果表明:本文方法匹配正确率与经典的仿射不变匹算法(ASIFT)的正确率相差不大,但匹配数量却是ASIFT算法的1倍~3倍.A feature point and line hierarchical matching method is proposed,suitable for oblique images to solve the challenges of large angle in view transformation,a few matches due to repeated texture,and low matching accuracy.Firstly,the line features of images derive from the line extraction(detection)algorithm(LineSegmentDector),follow constraints to pair,and construct line pair regions to match the improved SIFT feature descriptor.Secondly,after RANSAC algorithm eliminates mismatches,the epipolar constraint acts upon the initial matching results.Then,the obtained lines correct the local image,and the corrected local image uses SIFT matching,which contributes to calculating the original image reversely.The obtained matching points are used to globally correct the oblique image,and the feature points are matched;the grid-based motion statistics(GMS)algorithm eliminates the mismatches;the matching results go through reverse calculation and return to the original image.The line matching results and the point expanding matching results combine into final results,showing that the matching accuracy of the proposed method is close to that of ASIFT,but the number of matching is 1-3 times it.

关 键 词：倾斜影像 直线特征 核线约束 点拓展匹配 全局纠正 

分 类 号：P237[天文地球—摄影测量与遥感]