融合尺度和仿射不变特征的倾斜立体影像配准Registration of oblique stereo images by integrating scale and affine invariant features
于瑞鹏,金丽鸿,高宁,赵星涛
摘要(Abstract)：
针对倾斜立体影像通常存在较大的几何变形从而难以自动匹配的问题,该文提出了一种融合MSER特征和SIFT特征的自动配准算法:选取MSER特征获得初始匹配及其对应邻域的仿射几何关系,对MSER候选匹配邻域内SIFT的特征点进行局部几何约束的仿射不变归一化相关系数匹配,定义邻域内SIFT特征的匹配正确率为邻域支持度,并据此进行原始MSER误匹配进行剔除。对上述未能匹配的MSER和SIFT特征,采用基于局部单应约束进行迭代匹配传播以获得更多的配准控制点并用于精确估计投影变换模型,完成影像的配准。同现有方法相比,所提算法在匹配点数、匹配正确率和配准精度方面有较大优势。
关键词(KeyWords)： 影像配准;倾斜立体影像;最大稳定极值区域;尺度不变特征变换;单应映射
基金项目(Foundation): 国家自然科学基金项目(41371438)
作者(Author): 于瑞鹏,金丽鸿,高宁,赵星涛
DOI: 10.16251/j.cnki.1009-2307.2016.07.025
参考文献(References)：
- [1]ZITOVA B,FLUSSER J.Image registration methods:a survey[J].Image and Vision Computing,2003,21(11):977-1000.
- [2]BROWN L G.A survey of image registration techniques[J].ACM Computing Surveys,1992,24(4):325-376.
- [3]张迁,刘政凯,庞彦伟,等.基于SUSAN算法的航空影像的自动配准[J].测绘学报,2003,32(3):245-250.
- [4]韦燕凤,赵忠明,闫冬梅,等.基于特征的遥感图像自动配准算法[J].电子学报,2005,33(1):61-165.
- [5]李芳芳,肖本林,贾永红,等.SIFT算法优化及其用于遥感影像的自动配准[J].武汉大学学报:信息科学版,2009,34(10):1245-1249.
- [6]YANG Gang,STEWART C V,SOFKA M,et al.Registration of challenging image pairs:Initialization,estimation,and decision[J].IEEE Transactions on Pattern Analysis and Mach.Intelligence,2007,29(11):1973-1989.
- [7]LOWE D.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
- [8]MATAS J,CHUM O,URBAN M,et al.Robust widebaseline stereo from maximally stable extremal regions[J].Image and Vision Computing,2004,22(10):761-767.
- [9]MIKOLAJCZYK K,SCHMID C.Scale&affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86.
- [10]Mikolajczyk K,Tuytelaars T,Schmid C,et al.A comparison of affine region detectors[J].International Journal of Computer Vision,2005,65(1-2):43-72.
- [11]MONTOLIU R,PLA F.Generalized least squaresbased parametric motion estimation[J].Computer Vision and Image Understanding,2009,113:790-801.
- [12]YU Le,ZHANG Dengrong,HOLDEN E J.A fast and fully automatic registration approach based on point features for multi-source remote-sensing images[J].Computer&Geosciences,2008,34:838-848.
- [13]MA J L,CHEUNG W C,CENTERS F.Fully automatic subpixel image registration of Multiangle CHRIS/Proba data[J].IEEE Transactions oN Geoscience and Remote Sensing,2010,48(7):2829-2839.
- [14]ZHANG Qing,WANG Yabing,WANG Lin.Registration of images with affine geometric distortion based on maximally stable extremal regions and phase congruency[J].Image and Vision Computing,2015,36(12):23-39.
- [15]MOREL J M,YU G.ASIFT:a new framework for fully affine invariant image comparison[J].SIAM Journal of Imaging Science,2009,2(2):438-469.