浏览全部资源
扫码关注微信
Received：18 December 2020，
Revised：2021-3-15，
Accepted：22 March 2021，
Published：16 April 2022
移动端阅览
目的
2
图像匹配是遥感图像镶嵌拼接的重要环节，图像匹配技术通常采用两步法，首先利用高维描述子的最近和次近距离比建立初始匹配，然后通过迭代拟合几何模型消除错误匹配。尽管外点过滤算法大幅提高了时间效率，但其采用传统的两步法，构建初始匹配的方法仍然非常耗时，导致整个遥感图像拼接的速度提升仍然有限。为了提高遥感图像匹配的效率，本文提出了一种基于空间分治思想的快速匹配方法。
方法
2
首先，通过提取图像的大尺度特征生成少量的初始匹配，并基于初始匹配在两幅图像之间构建成对的分治空间中心点；然后，基于范围树搜索分治空间中心点一定范围内的相邻特征点，构造成对分治空间点集；最后，在各个分治空间点集内分别进行遥感图像特征的匹配。
结果
2
通过大量不同图像尺寸和相对旋转的遥感图像的实验表明，与传统的和其他先进方法相比，本文方法在保证较高精度的同时将匹配时间缩短到1/100~1/10。
结论
2
利用初始种子匹配构建分治匹配中心以将图像匹配分解在多个子区间进行的方法有助于提高遥感影像匹配的效率，该算法良好的时间性能对实时遥感应用具有实际价值。
Objective
2
Image matching is crucial to remote sensing. A number of feature matching algorithms have been designed to establish correspondences and filter outliers. The current remote sensing image matching methods have derived from region-based and feature based analyses. Feature-based methods illustrate greater robustness and accuracy in processing complex scenarios like brightness changes
homogeneous textures
and geometric distortions. Feature-based methods are implemented in at two stages as follows: First
robust feature points are extracted and nearest-neighbor distance ratios (NNDRs) is facilitated to clarify putative matches. Next
a geometric model or spatial structure is adopted to filter false matches. An initial putative matching step is time-consuming based on quick mismatches elimination and high inlier ratios. This initial matching step has challenged further for matching speeds improvement. Our new quick matching method decreases matching times significantly in terms of high inlier ratios.
Method
2
First
scale-invariant feature transform (SIFT) features are from image extraction and these feature points are sorted out in accordance with their scales to establish initial matches based on top 10 % feature scales derived of NNDR threshold. Top-scale SIFT features is identified to extract the initial matches due to small quantity and high quality. Qualified matches can be obtained based on these features. Next
it samples regularly spaced feature coordinates in the query image. Initial matches based affine model estimation is conducted to transform the sampled points to the target image. The extraction of initial match accuracy is relatively high in terms of top-scale feature points. Thus
accuracy of the affine model estimated from this match is also high. The virtual center point (VCP) is targeted as center of a neighboring feature point set. The VCP is not represented the extracted feature position well as a search center for the neighboring feature points. A set of pairwise neighbors is obtained in terms of an inner rectangular window based feature points search of these pairwise sample points. Finally
feature point matching is performed independently within each pair of windows. Following the set of VCP neighbors derived of the range tree
correspondence is to be established within pairwise windows. As most features are grouped in small windows
feature correspondence can be established rapidly through traditional brute force (BF) matching. Thus
BF matching is utilized to implement feature matching in pairwise windows instead of a k-dimensional tree (kd-tree). The number of points assumed for each window considerably affects the performance of spatial divide and conquer (SDC) algorithm and it determines the number of VCPs and the size of the windows
consequently regulating the average number of feature points per window. This is significant for BF image matching procedures operating within the windows. To analyze the effect of window size on matching time and inlier ratio
a group of images are optioned with resolutions between 795 × 530 and 3 976 × 2 652 pixels. The demonstrations indicate that the window size is inversely proportional to running speed and inlier ratio.
Result
2
A multi-sensors based remote sensing data across China is obtained. These analyzed images are mentioned as bellows: 1) the Landsat 8 images of West Sichuan of China; 2) SPOT satellite images of Beijing; 3) GF-3 synthetic aperture radar (SAR) data for the southeast of Wuhan; 4) ZY-3 satellite data for Qingdao area of Shandong province. The images were sized between 816 × 716 and 2 976 × 2 273 pixels
and the maximum relative rotation angle was 30°. These images cover several types of geographical environment
including mountains
cities
coastal plains
forests
and farmland. Extensive experiments on various sizes and orientations of remote sensing images demonstrate that our proposed method is highly accurate and reduces the matching time by 1-2 orders of magnitude compared with traditional and the state-of-the-art methods.
Conclusion
2
A top-scale SIFT features based quick image matching method is illustrated and analyzed. Parallel computing can further improve the speed of our algorithm due to the independent matching procedures for separate windows.
Agarwal S, Snavely N, Simon I, Seitz S M and Szeliski R. 2009. Building Rome in a day//Proceedings of the 12th International Conference on Computer Vision (ICCV). Kyoto, Japan: IEEE: 72-79 [ DOI: 10.1109/ICCV.2009.5459148 http://dx.doi.org/10.1109/ICCV.2009.5459148 ]
Bian J W, Lin W Y, Matsushita Y, Yeung S K, Nguyen T D and Cheng M M. 2017. GMS: grid-based motion statistics for fast, ultra-robust feature correspondence//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE: 2828-2837 [ DOI: 10.1109/CVPR.2017.302 http://dx.doi.org/10.1109/CVPR.2017.302 ]
Brown M and Lowe D. 2002. Invariant features from interest point groups//Proceedings of the British Machine Vision Conference. [s.l.]: BMVA Press: #23 [ DOI: 10.5244/C.16.23 http://dx.doi.org/10.5244/C.16.23 ]
Chen C, Li Y Q, Liu W and Huang J Z. 2015. SIRF: simultaneous satellite image registration and fusion in a unified framework. IEEE Transactions on Image Processing, 24(11): 4213-4224 [DOI: 10.1109/TIP.2015.2456415]
Cheng J, Leng C, Wu J X, Cui H N and Lu H Q. 2014. Fast and accurate image matching with cascade hashing for 3D reconstruction//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE: 1-8 [ DOI: 10.1109/CVPR.2014.8 http://dx.doi.org/10.1109/CVPR.2014.8 ]
Chum O, Matas J and Kittler J. 2003. Locally optimized RANSAC//The 25th Joint Pattern Recognition Symposium. Magdeburg, Germany: Springer: 236-243 [ DOI: 10.1007/978-3-540-45243-0_31 http://dx.doi.org/10.1007/978-3-540-45243-0_31 ]
Crandall D, Owens A, Snavely N and Huttenlocher D. 2011. Discrete-continuous optimization for large-scale structure from motion//Proceedings of the CVPR 2011. Colorado Springs, USA: IEEE: #5995626 [ DOI: 10.1109/CVPR.2011.5995626 http://dx.doi.org/10.1109/CVPR.2011.5995626 ]
de Berg M, van Kreveld M, Overmars M and Schwarzkopf O C. 2000. Orthogonal range searching//de Berg M, van Kreveld M, Overmars M and Schwarzkopf O C, eds. Computational Geometry. Berlin, Heidelberg: Springer: 95-120 [ DOI: 10.1007/978-3-662-04245-8_5 http://dx.doi.org/10.1007/978-3-662-04245-8_5 ]
Eastman R D, Netanyahu N S and Moigne J L. 2011. Survey of image registration methods//Le Moigne J, Netanyahu N S and Eastman R D, eds. Image Registration for Remote Sensing. Cambridge: Cambridge University Press
Feng R, Li X and Shen H. 2019a. Mountainous remote sensing images registration based on improved optical flow estimation//Proceedings of the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Enschede, the Netherlands: ISPRS: 479-484 [ DOI: 10.5194/isprs-annals-IV-2-W5-479-2019 http://dx.doi.org/10.5194/isprs-annals-IV-2-W5-479-2019 ]
Feng R T, Du Q Y, Li X H and Shen H F. 2019b. Robust registration for remote sensing images by combining and localizing feature-and area-based methods. ISPRS Journal of Photogrammetry and Remote Sensing, 151: 15-26 [DOI: 10.1016/j.isprsjprs.2019.03.002]
Fischler M A and Bolles R C. 1981. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6): 381-395 [DOI: 10.1145/358669.358692]
Geng J, He C L and Liu X X. 2016. Image matching based on CSIFT feature. Remote Sensing for Land and Resources, 28(1): 93-100
耿娟, 何成龙, 刘宪鑫. 2016. 基于CSIFT特性的无人机影像匹配. 国土资源遥感, 28(1): 93-100 [DOI: 10.6046/gtzyyg.2016.01.14]
Hartley R and Zisserman A. 2000. Multiple View Geometry in Computer Vision. Cambridge: Cambridge University Press
Hu Y T, Lin Y Y, Chen H Y, Hsu K J and Chen B Y. 2015. Matching images with multiple descriptors: an unsupervised approach for locally adaptive descriptor selection. IEEE Transactions on Image Processing, 24(12): 5995-6010 [DOI: 10.1109/TIP.2015.2496305]
Izadi M and Saeedi P. 2012. Robust weighted graph transformation matching for rigid and nonrigid image registration. IEEE Transactions on Image Processing, 21(10): 4369-4382 [DOI: 10.1109/TIP.2012.2208980]
Jia D, Zhu N D, Yang N H, Wu S, Li Y X and Zhao M Y. 2019. Image matching methods. Journal of Image and Graphics, 24(5): 677-699
贾迪, 朱宁丹, 杨宁华, 吴思, 李玉秀, 赵明远. 2019. 图像匹配方法研究综述. 中国图象图形学报, 24(5): 677-699 [DOI: 10.11834/jig.180501]
Kurz D and Himane S B. 2011. Inertial sensor-aligned visual feature descriptors//Proceedings of the CVPR 2011. Colorado Springs, USA: IEEE: 161-166 [ DOI: 10.1109/CVPR.2011.5995339 http://dx.doi.org/10.1109/CVPR.2011.5995339 ]
Li D P. 2015. A novel method for multi-angle SAR image matching. Chinese Journal of Aeronautics, 28(1): 240-249 [DOI: 10.1016/j.cja.2014.12.019]
Li X R and Hu Z Y. 2010. Rejecting mismatches by correspondence function. International Journal of Computer Vision, 89(1): 1-17 [DOI: 10.1007/s11263-010-0318-x]
Lowe D G. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2): 91-110 [DOI: 10.1023/b:visi.0000029664.99615.94]
Ma J Y, Jiang J J, Zhou H B, Zhao J and Guo X J. 2018. Guided locality preserving feature matching for remote sensing image registration. IEEE Transactions on Geoscience and Remote Sensing, 56(8): 4435-4447 [DOI: 10.1109/TGRS.2018.2820040]
Ma J Y, Zhao J, Jiang J J, Zhou H B and Guo X J. 2019. Locality preserving matching. International Journal of Computer Vision, 127(5): 512-531 [DOI: 10.1007/s11263-018-1117-z]
Ma J Y, Zhao J, Tian J W, Yuille A L and Tu Z W. 2014. Robust point matching via vector field consensus. IEEE Transactions on Image Processing, 23(4): 1706-1721 [DOI: 10.1109/TIP.2014.2307478]
Ma J Y, Zhao J, Zhou Y and Tian J W. 2012. Mismatch removal via coherent spatial mapping//Proceedings of the 19th IEEE International Conference on Image Processing. Orlando, USA: IEEE: 1-4 [ DOI: 10.1109/ICIP.2012.6466780 http://dx.doi.org/10.1109/ICIP.2012.6466780 ]
Moisan L, Moulon P and Monasse P. 2012. Automatic homographic registration of a pair of images, with a contrario elimination of outliers. Image Processing on Line, 2: 56-73 [DOI: 10.5201/ipol.2012.mmm-oh]
Raguram R, Frahm J M and Pollefeys M. 2008. A comparative analysis of RANSAC techniques leading to adaptive real-time random sample consensus//Proceedings of the 10th European Conference on Computer Vision. Marseille, France: Springer: 500-513 [ DOI: 10.1007/978-3-540-88688-4_37 http://dx.doi.org/10.1007/978-3-540-88688-4_37 ]
Strecha C, Bronstein A, Bronstein M and Fua P. 2012. LDAHash: improved matching with smaller descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(1): 66-78 [DOI: 10.1109/TPAMI.2011.103]
Wang X H, Deng S X, He Z W, Cao L X and Yan X G. 2018. Study of UAV image matching based on SURF algorithm and homography matrix. Bulletin of Surveying and Mapping, (7): 38-42
王晓红, 邓仕雄, 何志伟, 曹留霞, 闫星光. 2018. 结合SURF算法和单应性矩阵的无人机影像匹配. 测绘通报, (7): 38-42 [DO1: 10.13474/j.cnki.11-2246.2018.0206]
Wei Z Q, Han Y F, Li M Y, Yang K, Yang Y, Luo Yand Ong S H. 2017. A small UAV based multi-temporal image registration for dynamic agricultural terrace monitoring. Remote Sensing, 9(9): #904 [DOI: 10.3390/rs9090904]
Wu C C. 2013. Towards linear-time incremental structure from motion//Proceedings of 2013 International Conference on 3D Vision — 3DV 2013. Seattle, USA: IEEE: 127-134 [ DOI: 10.1109/3DV.2013.25 http://dx.doi.org/10.1109/3DV.2013.25 ]
Xi W F, Shi Z T and Li G Z. 2020. UAV image matching feature point coarse error elimination based on image theory algorithm. Bulletin of Surveying and Mapping, (4): 6-10
喜文飞, 史正涛, 李国柱. 2020. 图论算法的无人机影像匹配特征点粗差剔除. 测绘通报, (4): 6-10 [DOI: 10.13474/j.cnki.11-2246.2020.0103]
Xu B, Lei B, Sun T and Lu X J. 2018. A multi-feature matching algorithm for visible light and SAR images registration. Remote Sensing Information, 33(3): 85-90
许斌, 雷斌, 孙韬, 卢晓军. 2018. 一种多特征匹配的可见光与SAR图像配准算法. 遥感信息, 33(3): 85-90 [DOI: 10.3969/j.issn.1000-3177.2018.03.013]
Yang K, Pan A N, Yang Y, Zhang S, Ong S H and Tang H L. 2017. Remote sensing image registration using multiple image features. Remote Sensing, 9(6): #581 [DOI: 10.3390/rs9060581]
Yuan X X, Chen S Y, Yuan W and Cai Y. 2017. Poor textural image tie point matching via graph theory. ISPRS Journal of Photogrammetry and Remote Sensing, 129: 21-31 [DOI: 10.1016/j.isprsjprs.2017.04.015]
Zhang K, Li X Z and Zhang J X. 2014. A robust point-matching algorithm for remote sensing image registration. IEEE Geoscience and Remote Sensing Letters, 11(2): 469-473 [DOI: 10.1109/LGRS.2013.2267771]
Zhang Q P and Cao Y. 2019. Image matching algorithm based on exposure and color information. Laser and Optoelectronics Progress, 56(19): #191004
张庆鹏, 曹宇. 2019. 一种融合光照和彩色信息的图像匹配算法. 激光与光电子学进展, 56(19): #191004 [DOI: 10.3788/LOP56.191004]
Zhao X, Li H, Wang P and Jing L H. 2020. An image registration method for multisource high-resolution remote sensing images for earthquake disaster assessment. Sensors, 20(8): #2286 [DOI: 10.3390/s20082286]
相关文章
相关作者
相关机构
京公网安备11010802024621
