摘要
针对有云遥感影像间常规匹配效果不佳的问题,提出了一种考虑云检测的遥感影像匹配方法,主要包括有云区域的探测、特征点提取和相位匹配三个部分。通过对影像局部区域的高亮度像素的统计,在特征点提取时避开有云区域,最后通过物方空间的相位相关获取同名点对。实验表明本方法在包含大量云团的影像之间能够明显改善匹配效果。
To overcome the matching difficulties between remote sensing images with cloud, we proposed a remote sensing image matching method considering cloud detection. This method mainly includes cloud area detection, feature point extraction and phase correlation. Through the statistics of high-brightness pixelsin the local area, we exclude the cloud regions during feature point extraction. We then obtain the corresponding point pairs by the phase correlation in the object space. The result shows that this method can obviously improve the matching effect between images with a large number of clouds.
引文
[1]张剑清,潘励,王树根.摄影测量学[M].武汉:武汉大学出版社,2009
[2]David G,Lowe.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of Computer Vision,2004,60(2):91-110
[3]Bay H,Ess A,Tuytelaars T,et al.Speeded-Up Robust Features(SURF)[J].Computer Vision and Image Understanding,2008,110(3):346-359
[4]Stone H S,Orchard M T,Chang E C,et al.A fast Direct Fourier-based Algorithm for Subpixel Registration of Images[J].Geoscience&Remote Sensing IEEE Transactions on,2001,39(10):2 235-2 243
[5]Harris C.A Combined Corner and Edge Detector[C].Proceedings of the 4th Alvey Vision Conference,1988:147-151
[6]F?rstner W,Gülch E.A Fast Operator for Detection and Precise Location of Distinct Points,Corners and Circular Features[J].ISPRS Intercommission Workshop Interlaken,1987:281-305
[7]Rosten E,Porter R,Drummond T.Faster and Better:A Machine Learning Approach to Corner Detection[M].IEEE Computer Society,2010
[8]韦春桃,吴平,张祖勋,等.一种改进的相位相关的影像配准方法[J].测绘通报,2011(4):19-22
[9]Harris F J.On the Use of Harmonic Analysis with the Discrete Fourier Transform[J].IEEE Proceedings,1978,66(1):51-83
[10]孙辉,李志强,孙丽娜,等.基于相位相关的亚像素配准技术及其在电子稳像中的应用[J].中国光学,2010,3(5):480-485