利用PCA-SIFT进行特殊纹理航摄影像匹配  

Special Textural Aerial Image Matching Based on PCA-SIFT Feature Matching

作　　者：袁修孝[1,2] 陈时雨[1] 张勇[1] 

机构地区：[1]武汉大学遥感信息工程学院,湖北武汉430079 [2]地球空间信息技术协同创新中心,湖北武汉430079

出　　处：《武汉大学学报（信息科学版）》2016年第9期1137-1144,共8页Geomatics and Information Science of Wuhan University

基　　金：国家973计划(2012CB719902);国家自然科学基金(41371432);国家高分专项(民用部分)项目(50-H31D01-0508-13/15)~~

摘　　要：提出了一种基于主成分分析-尺度不变特征变换(principal component analysis,scale invariant feature transform,PCA-SIFT)的特殊纹理航摄影像匹配方法。首先,对影像降采样并进行PCA-SIFT特征匹配;然后利用得到的同名像点计算平面单应矩阵,并确定影像对间的同名区域;随后,在同名区域间再次进行PCASIFT特征匹配并剔除误匹配点;最后,采用改进的最小二乘影像匹配方法对PCA-SIFT匹配结果进行精化,从而自动识别出同名像点。实验结果表明,本文方法可以达到子像素级的影像匹配精度,即使是在纹理贫乏和重复区域也能够匹配出足够数量的特征点,完全可以满足空中三角测量的影像自动量测要求。This paper describes a novel method for special textural aerial image matching based on PCA-SIFT.Images are down sampled and subsequently,PCA-SIFT feature matching is applied.The matched points are used to calculate the homography matrix and the corresponding areas are determined between stereo image pairs.PCA-SIFT is performed again on the corresponding areas to get more matching points,and gross errors are detected.Finally,an improved least square image matching method is implemented to refine the PCA-SIFT matching results.Examples of special textural image matching demonstrate that the proposed match method can achieve subpixel accuracy and works well on images with poor texture and repetitive patterns.This method fully satisfies the requirements for automatic aerotriangulation image measurement.

关 键 词：特殊纹理 PCA-SIFT特征匹配 单应矩阵 最小二乘影像匹配 

分 类 号：P237.3[天文地球—摄影测量与遥感] TP751[天文地球—测绘科学与技术]