基于双向邻域过滤策略的图形匹配类遥感图像配准算法

针对遥感图像由于较大仿射变换关系、相似图案和多源性等导致图形匹配时出现伪同构现象，提出了一种基于双向邻域过滤策略的图形匹配方法.本方法采用双向邻域的图形特征描述子来表示特征点的邻域关系.当误配点的双向邻域任意顶点在后期迭代中被视为误配点时，将与匹配点集具有稳定双向邻域结构的点恢复至匹配点集，同时剔除伪同构中残留的误配点.通过与Random Sample Consensus (RANSAC)、Graphing Transformation Matching(GTM)算法以及提出的双向邻域匹配方式比较得出，基于双向邻域过滤策略的匹配方式能够处理空间顺序匹配时存在的伪同构问题，同时获得更高的召回率和匹配率.

Abstract

In this paper, a novel graph matching algorithm, called Filtering Bi-directional K-Nearest-Neighbors Strategy (Filtering BiKNN Strategy) is presented to solve the pseudo isomorphic graph matching for remote sensing images with large affine transformation, similar patterns or from multisource sensors. BiKNN was proposed to describe the adjacent relationships of feature points. Filtering strategy is used to eliminate dubious matches of pseudo isomorphism for restrict constraints. Any BiKNN vertices of candidate outliers treated as outliers in latter iterations are rechecked with the expanded BiKNN respectively. Candidate outliers with stable graph structures are recovered to the residual sets. Three typical remote sensing images and twenty image pairs were utilized to evaluate the performance. Compared with random sample consensus (RANSAC), graphing transformation matching (GTM) and the proposed BiKNN matching, Filtering BiKNN Strategy can deal with pseudo isomorphism and obtain the highest recall and precision.

参考文献

[1] Zitova B, Flusser B. Image registration methods: a survey［J]. Image and vision computing, 2003,21(11):9771000.

[2] Liu Z X, An J B, Jing Y. A simple and robust feature point matching algorithm based on restricted spatial order constraints for aerial image registration［J]. IEEE Transactions on Geoscience and Remote Sensing, 2012,50(2):514527.

[3] Caetano T S, McAuley J J. Learning graph matching［J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31(6):10481058.

[4] Goshtasby A A. 2-D and 3-D image registration: for medical, remote sensing and industrial applications［M]. New Jersey. John Wiley&Sons Inc, 2005,759.

[5] Dain X, Khorram S. A feature-based image registration algorithm using improved chain-code representation combined invariant moments［J]. IEEE Transactions on Geoscience and Remote Sensing, 2005,43(9):21272137.

[6] ]Zhang Z X, Li J Z, Li D D. Research of automated image registration technique for infrared images based on optical flow field analysis［J]. J.Infrared Millim.Waves(基于光流场分析的红外图像自动配准方法研究，红外与毫米波学报)，2003,22(4):307312.

[7] Wen G J, Lv J J, Yu W X. A high-performance feature-matching method for image registration by combining spatial and similarity information［J]. IEEE Transactions on Geoscience and Remote Sensing, 2008,46(4): 12061277.

[8] Lowe D G. Distinctive image features from scale-invariant keypoints［J]. International Journal of Computer Vision, 2004,60(2):91110.

[9] Fichler M A, Bolles R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography［J]. Communications of the ACM, 1981,24(6):381395.

[10] Aguilar W, Frauel Y, Escolano F, et al. A robust graph transformation matching for non-rigid registration［J]. Image and vision computing, 2009,27(7):897910.

[11] Beis J, Lowe D G. Shape indexing using approximate nearest-neighbor search in high-dimensional space［C]. Proceeding of computer vision and pattern recognition, Pueto Rico, 1997:10001006.

[12] Zhao M, An B, Wu Y, et al. Bi-SOGC: A graph Matching Approach based on bilateral KNN Spation Orders around geometric centers for remote sensing image registration［J]. IEEE Geoscience and Remote Sensing Letters, 2013,10(6): 14291433.第33卷第1期2014年2月红外与毫米波学报J. Infrared Millim. WavesVol. 33, No.1February,2014

赵明, 安博文, 王天真, 许媛媛, 林长青, 孙胜利. 基于双向邻域过滤策略的图形匹配类遥感图像配准算法[J]. 红外与毫米波学报, 2014, 33(1): 78. ZHAO Ming, AN Bo-Wen, WANG Tian-Zhen, XU Yuan-Yuan, LIN Chang-Qing, SUN Sheng-Li. A graph matching algorithm based on filtering strategy of Bi-directional K-Nearest-Neighbors[J]. Journal of Infrared and Millimeter Waves, 2014, 33(1): 78.

基于双向邻域过滤策略的图形匹配类遥感图像配准算法

关于本站 Cookie 的使用提示

全站搜索

基于双向邻域过滤策略的图形匹配类遥感图像配准算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索