欢迎访问中国科学院大学学报，今天是
RSS English

中国科学院大学学报 >

2024 , Vol. 41 >Issue 1: 107 - 116

DOI: https://doi.org/10.7523/j.ucas.2022.019

电子信息与计算机科学

一种结合局部与半全局几何保持的影像匹配算法

  • 郑美艳 ,
  • 陈俊 ,
  • 葛小青 ,
  • 张红
展开
  • 1. 中国科学院空天信息创新研究院, 北京 100094;
    2. 中国科学院大学电子电气与通信工程学院, 北京 100049;
    3. 中国科学院计算机网络信息中心, 北京 100083;
    4. 中国科学院大学计算机科学与技术学院, 北京 100049

收稿日期: 2022-01-13

  修回日期: 2022-03-16

  网络出版日期: 2022-03-16

基金资助

国家自然科学基金(41930110)资助

收起

An image matching algorithm combining local and semi-global geometry preservation

  • ZHENG Meiyan ,
  • CHEN Jun ,
  • GE Xiaoqing ,
  • ZHANG Hong
Expand
  • 1. Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China;
    2. School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China;
    3. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China;
    4. School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, China

Received date: 2022-01-13

  Revised date: 2022-03-16

  Online published: 2022-03-16

Fold

摘要

遥感影像匹配是众多遥感应用中数据处理的关键前置步骤，但高程差导致的影像局部畸变和影像匹配的复杂性严重限制了高分辨率影像的匹配精度。提出一种适用于局部畸变和高外点比例的鲁棒匹配算法，首先利用Delaunay剖分算法在假定匹配点集上施加几何约束，得到特征点局部邻接关系；然后基于邻接信息进行预过滤；采用多尺度的策略建立局部邻接关系一致约束模型；最后定义三角形相似度函数实现匹配恢复。利用3组高分辨率影像开展对比实验，实验结果表明该算法的平均精度比RANSAC提高7.69%，在外点率高于90%时仍旧稳健。

关键词： 高分辨率遥感影像; 图像匹配; Delaunay三角网; 几何保持; 多尺度

本文引用格式

郑美艳 , 陈俊 , 葛小青 , 张红 . 一种结合局部与半全局几何保持的影像匹配算法[J]. 中国科学院大学学报, 2024 , 41(1) : 107 -116 . DOI: 10.7523/j.ucas.2022.019

Abstract

Remote sensing image matching is an essential preprocessing step for many remote sensing applications. However, the distortions caused by elevation differences and the complexity of remote sensing image matching severely limit the matching precision of high-resolution remote sensing images. This paper proposes a robust feature matching algorithm suitable for local distortion and high outlier ratio. First, the Delaunay triangulation algorithm is used to impose geometric constraints on the initial matching point set, and the local adjacency relationship of the feature points is obtained. Second, pre-filter is conducted based on the adjacency information. Third, a multi-scale strategy is used to establish the local adjacency consistent model. Finally, a triangle similarity function is defined to achieve matching recovery. The experimental results on high-resolution images show that the average accuracy of our algorithm is 7.69% higher than that of RANSAC, and it is still robust when the outlier ratio is higher than 90%.

Key words： high resolution remote sensing image; image matching; Delaunay triangulation; geometry preservation; multi-scale

参考文献

[1] Li J Y, Hu Q W, Ai M Y, et al. Robust feature matching via support-line voting and affine-invariant ratios[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 132: 61-76. DOI:10.1016/j.isprsjprs.2017.08.009.
[2] Ma J Y, Jiang X Y, Fan A X, et al. Image matching from handcrafted to deep features: a survey[J]. International Journal of Computer Vision, 2021, 129(1): 23-79. DOI:10.1007/s11263-020-01359-2.
[3] 贾迪, 朱宁丹, 杨宁华, 等. 图像匹配方法研究综述[J]. 中国图象图形学报, 2019, 24(5): 677-699. DOI：10.11834/jig.180501.
[4] Yan X H, Zhang Y J, Zhang D J, et al. Multimodal image registration using histogram of oriented gradient distance and data-driven grey wolf optimizer[J]. Neurocomputing, 2020, 392: 108-120. DOI:10.1016/j.neucom.2020.01.107.
[5] Le Moigne J, Campbell W J, Cromp R F. An automated parallel image registration technique based on the correlation of wavelet features[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(8): 1849-1864. DOI:10.1109/TGRS.2002.802501.
[6] 韩松来, 王钰婕, 王星, 等. 多尺度PCA-HOG遥感异源图像匹配算法[J]. 国防科技大学学报, 2022, 44(1): 146-155. DOI:10.11887/j.cn.202201021.
[7] Ye Y X, Shan J, Hao S Y, et al. A local phase based invariant feature for remote sensing image matching[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 142: 205-221. DOI:10.1016/j.isprsjprs.2018.06.010.
[8] Liu S Y, Jiang J. Registration algorithm based on line-intersection-line for satellite remote sensing images of urban areas[J]. Remote Sensing, 2019, 11(12): 1400. DOI:10.3390/rs11121400.
[9] Sedaghat A, Ebadi H. Remote sensing image matching based on adaptive binning SIFT descriptor[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(10): 5283-5293. DOI:10.1109/TGRS.2015.2420659.
[10] Jiang X Y, Ma J Y, Fan A X, et al. Robust feature matching for remote sensing image registration via linear adaptive filtering[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(2): 1577-1591. DOI:10.1109/TGRS.2020.3001089.
[11] Li J Y, Hu Q W, Ai M Y. Robust geometric model estimation based on scaled welsch q-norm[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(8): 5908-5921. DOI:10.1109/TGRS.2020.2972982.
[12] Liu Y Z, Li Y P, Dai L Y, et al. Robust feature matching via advanced neighborhood topology consensus[J]. Neuro-computing, 2021, 421: 273-284. DOI:10.1016/j.neucom.2020.09.047.
[13] Ma J Y, Zhao J, Tian J W, et al. Robust point matching via vector field consensus[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2014, 23(4): 1706-1721. DOI:10.1109/TIP.2014.2307478.
[14] Zhang K, Li X Z, Zhang J X. A robust point-matching algorithm for remote sensing image registration[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(2): 469-473. DOI:10.1109/LGRS.2013.2267771.
[15] Zhao J, Ma J Y, Tian J W, et al. A robust method for vector field learning with application to mismatch removing[C]//CVPR 2011. June 20-25, 2011, Colorado Springs, CO, USA. IEEE, 2011: 2977-2984. DOI:10.1109/CVPR.2011.5995336.
[16] Huber P J. Robust statistics[M]. New York: John Wiley & Sons, Inc., 1981.
[17] Hubert M, Debruyne M. Minimum covariance determinant[J]. WIREs Computational Statistics, 2010, 2(1): 36-43. DOI:10.1002/wics.61.
[18] Li J Y, Hu Q W, Ai M Y. Robust feature matching for remote sensing image registration based on Lq-estimator[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(12): 1989-1993. DOI:10.1109/LGRS.2016.2620147.
[19] Ma J Y, Zhou H B, Zhao J, et al. Robust feature matching for remote sensing image registration via locally linear transforming[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(12): 6469-6481. DOI:10.1109/TGRS.2015.2441954.
[20] Lin W Y, Wang F, Cheng M M, et al. CODE: coherence based decision boundaries for feature correspondence[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(1): 34-47. DOI:10.1109/TPAMI.2017.2652468.
[21] 李云红, 钟晓妮, 王延年, 等. 基于函数拟合的SIFT误匹配点剔除算法[J]. 激光与红外, 2018, 48(9): 1174-1180. DOI：10.3969/j.issn.1001-5078.2018.09.020.
[22] Ma J Y, Zhao J, Zhou Y, et al. Mismatch removal via coherent spatial mapping[C]//2012 19th IEEE International Conference on Image Processing. September 30-October 3, 2012, Orlando, FL, USA. IEEE, 2012: 1-4. DOI:10.1109/ICIP.2012.6466780.
[23] Fischler 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): 381-395. DOI：10.1145/358669.358692.
[24] Chum O, Matas J. Matching with PROSAC-progressive sample consensus[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. June 20-25, 2005, San Diego, CA, USA. IEEE, 2005: 220-226. DOI:10.1109/CVPR.2005.221.
[25] Ni K, Jin H L, Dellaert F. GroupSAC: efficient consensus in the presence of groupings[C]//2009 IEEE 12th International Conference on Computer Vision. September 29-October 2, 2009, Kyoto. IEEE, 2009: 2193-2200. DOI:10.1109/ICCV.2009.5459241.
[26] Li R, Sun J Q, Gong D, et al. ARSAC: efficient model estimation via adaptively ranked sample consensus[J]. Neurocomputing, 2019, 328: 88-96. DOI:10.1016/j.neucom.2018.02.103.
[27] Raguram R, Chum O, Pollefeys M, et al. USAC: a universal framework for random sample consensus[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 2022-2038. DOI:10.1109/TPAMI.2012.257.
[28] 甄艳, 刘学军, 王美珍. 一种改进RANSAC的基础矩阵估计方法[J]. 测绘通报, 2014(4): 39-43. DOI:10.13474/j.cnki.11-2246.2014.0120.
[29] Chen H Y, Lin Y, Chen B Y. Robust feature matching with alternate Hough and inverted Hough transforms[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. June 23-28, 2013, Portland, OR, USA. IEEE, 2013: 2762-2769. DOI:10.1109/CVPR.2013.356.
[30] 谢亮, 陈姝, 张钧, 等. 利用Hough变换的匹配对提纯[J]. 中国图象图形学报, 2015, 20(8): 1017-1025. DOI:10.11834/jig.20150804.
[31] Sedaghat A, Mokhtarzade M, Ebadi H. Uniform robust scale-invariant feature matching for optical remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(11): 4516-4527. DOI:10.1109/TGRS.2011.2144607.
[32] Chin T J, Suter D. The maximum consensus problem: recent algorithmic advances[J]. Synthesis Lectures on Computer Vision, 2017, 7(2): 1-194. DOI:10.2200/s00757ed1v01y201702cov011.
[33] Cho M, Lee J, Lee K M. Reweighted random walks for graph matching[M]//Computer Vision-ECCV 2010. Berlin, Heidelberg: Springer Berlin Heidelberg, 2010: 492-505. DOI:10.1007/978-3-642-15555-0_36.
[34] Cho M, Lee K M. Mode-seeking on graphs via random walks[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. June 16-21, 2012, Providence, RI, USA. IEEE, 2012: 606-613. DOI:10.1109/CVPR.2012.62 47727.
[35] Xiao G B, Luo H, Zeng K, et al. Robust feature matching for remote sensing image registration via guided hyperplane fitting[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-14. DOI:10.1109/TGRS.2020.3041270.
[36] 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): 897-910. DOI:10.1016/j.imavis.2008.05.004.
[37] Ma J Y, Zhao J, Jiang J J, et al. Locality preserving matching[J]. International Journal of Computer Vision, 2019, 127(5): 512-531. DOI:10.1007/s11263-018-1117-z.
[38] Ma J Y, Jiang J J, Zhou H B, et al. Guided locality preserving feature matching for remote sensing image registration[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(8): 4435-4447. DOI:10.1109/TGRS.2018.2820040.
[39] 姜三, 江万寿. Delaunay三角网约束下的影像稳健匹配方法[J]. 测绘学报, 2020, 49(3): 322-333. DOI：10.11947/j.AGCS.2020.20190089.
[40] 毛克乐. 改进SURF和Delaunay三角网在图像匹配中应用[J]. 沈阳工业大学学报, 2021, 43(4): 432-438. DOI：10.7688/j.issn.1000-1646.2021.04.13.
[41] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110. DOI:10.1023/b: visi.00000 29664.99615.94.
[42] Vedaldi A, Fulkerson B. Vlfeat: an open and portable library of computer vision algorithms[C]//MM’10: Proceedings of the 18th ACM international conference on Multimedia. October 25-29, 2010, Firenze, Italy. ACM, 2010: 1469-1472. DOI:10.1145/1873951.1874249.
Options
文章导航

/

〈 〉

首页 | 期刊介绍 | 编委会 | 投稿指南 | 期刊浏览 | 期刊订阅 | 联系我们

版权所有 © 《中国科学院大学学报》编辑部

本系统由北京玛格泰克科技发展有限公司设计开发

技术支持：support@magtech.com.cn

访问统计

总访问量： 今日访问： 当前在线：

联系我们

通讯地址：北京玉泉路19号（甲）中国科学院大学科研楼410

联系电话:（010）88256013