Automatic fast feature-level image registration for high-resolution remote sensing images

Mengmeng HE; Qing GUO; An LI; Jun CHEN; Bo CHEN; Xuxiang FENG

doi:10.11834/jrs.20186420

Technology and Methodology | Views : 0 下载量: 629 CSCD: 10

PDF
Export
Share
Collection
Album

Automatic fast feature-level image registration for high-resolution remote sensing images
Vol. 22, Issue 2, Pages: 277-292(2018)
Received：07 November 2016，

Accepted：18 September 2017，

Published：2018-03
DOI： 10.11834/jrs.20186420
稿件说明：

移动端阅览

何梦梦, 郭擎, 李安, 陈俊, 陈勃, 冯旭祥. 2018. 特征级高分辨率遥感图像快速自动配准. 遥感学报, 22(2): 277–292 DOI： 10.11834/jrs.20186420.

He M M, Guo Q, Li A, Chen J, Chen B and Feng X X. 2018. Automatic fast feature-level image registration for high-resolution remote sensing images. Journal of Remote Sensing, 22(2): 277–292 DOI： 10.11834/jrs.20186420.

摘要

随着遥感图像分辨率的日益提高，遥感图像的尺寸和数据量也不断地增大，同时随着遥感应用的发展，对图像配准的性能也提出越来越高的要求，基于此，提出一种特征级高分辨率遥感图像快速自动配准方法。首先，对图像进行Haar小波变换，基于小波变换后的近似图像进行配准以提高配准速度；其次，根据不同的遥感图像来源使用不同的特征提取方法(光学图像使用Canny边缘提取算子，SAR图像使用Ratio Of Averages算子)，并将线特征转化为点特征；然后，依据特征点间最小角与次小角的角度之比小于某一阈值来确定初始匹配点对；最后，利用改进的随机抽样一致性算法滤除错误匹配点对，并结合分块思想均匀选取匹配点对计算仿射变换参数，进一步提高配准精度。为了验证本文方法的有效性，选择高分辨率WorldView-2图像、Pleiades图像和TerraSAR图像进行了实验，并与典型的SIFT算法、SURF算法进行比较分析，采用匹配率、匹配效率、均方根误差和时间消耗4个定量评价指标来客观评价算法的配准性能。实验结果表明，本文方法具有较好的有效性，且在不同的情况下具有较高的配准精度。本文提出的特征级高分辨率遥感图像快速自动配准方法，多组高分辨率遥感图像数据的配准实验结果表明该方法能快速实现并具有较高的配准精度和较好的鲁棒性。

Abstract

The size and amount of remote sensing images constantly increase with the improving resolution of remote sensing images. Meanwhile

the development of remote sensing applications also requires high image registration performance. Therefore

an automatic fast feature-level image registration method for high-resolution remote sensing images is proposed. The method includes five steps. First

the reference image and the image to be registered are processed by Haar wavelet transform to obtain the low-frequency approximate images to match. Then

the original images are registered according to the matching result of the approximate images

thereby potentially effectively reducing calculation and improving registration speed. Second

edges in the optical image are extracted by the Canny operator

and edges in the SAR image are extracted by the Ratio Of Averages (ROA) operator. Then

the edge line features are transformed into point features. The use of edge point features can achieve positioning accuracy and acquire stable features. Third

in the feature matching session

the main and auxiliary directions of the point features are considered such that each point feature has multiple directions to enhance the robustness of image registration. Then

the initial matching points are determined by the ratio of the minimum angle to the second minimum angle

which is less than a threshold. Fourth

in the matching point pair filtering session

the random sample consensus is enhanced to improve registration accuracy by adding the constraint condition. The high-quality matching point pairs are selected to fit the model parameters. Finally

in the affine session

the block thought is used to uniformly select matching point pairs to be evenly distributed in the image to avoid the local optimal problem on the registration and further improve image registration accuracy. To verify the efficiency of the method

experiments are conducted under the following conditions: the same sensor optical image registration and sensor SAR image registration

image registration among different bands

image registration with different resolutions

and image registration of different satellite sensors with large size. High resolution WorldView-2

Pleiades

and TerraSAR images are used to perform the experiments. The proposed method is compared with the typical SIFT and SURF algorithms. Four quantitative evaluation indexes

namely

Matching Ratio (MR)

Matching Efficiency (ME)

Root Mean Square Error (RMSE)

and time consumed are used for the registration result evaluation. Experimental results show that the proposed method effectively achieves high registration accuracy under the different conditions. An automatic fast feature-level image registration method for high-resolution remote sensing images is proposed. Multiple datasets of registration experimental results for high-resolution remote sensing images indicate that the proposed method can be rapidly implemented and has high accuracy and strong robustness.

关键词

Keywords

references

Bay H, Ess A, Tuytelaars T and Van Gool L. 2008. Speeded-up robust features (SURF). Computer Vision and Image Understanding, 110(3): 346–359

Bay H, Tuytelaars T and Van Gool L. 2006. Surf: speeded up robust features//Proceedings of the 9th European Conference on Computer Vision. Graz, Austria: Springer: 404–417 [DOI: 10.1007/11744023_32]

蔡铁峰, 朱枫, 郝颖明, 范慧杰. 2015. 面向人眼探测识别的灰度图像伪彩色化方法. 红外与激光工程, 44(S1): 213–219

Cai T F, Zhu F, Hao Y M and Fan H J. 2015. Pseudo-color processing of gray images for human visual detection and recognition. Infrared and Laser Engineering, 44(S1): 213–219 (

Canny J. 1986. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8(6): 679–698 [DOI: 10.1109/TPAMI.1986.4767851]

Chen H M, Varshney P K and Arora M K. 2003. Performance of mutual information similarity measure for registration of multitemporal remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 41(11): 2445–2454

Eastman R D, Le Moigne J and Netanyahu N S. 2007. Research issues in image registration for remote sensing//Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN, USA: IEEE: 1–8 [DOI: 10.1109/CVPR.2007.383423]

Fan B, Huo C L, Pan C H and Kong Q Q. 2013. Registration of optical and SAR satellite images by exploring the spatial relationship of the improved sift. IEEE Geoscience and Remote Sensing Letters, 10(4): 657–661

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

Gu Y J, Ren K, Wang P C and Gu G H. 2016. Polynomial fitting-based shape matching algorithm for multi-sensors remote sensing images. Infrared Physics and Technology, 76: 386–392

Holia M S and Thakar V K. 2012. Mutual information based image registration for MRI and CT SCAN brain images//Proceedings of 2012 International Conference on Audio, Language and Image Processing. Shanghai, China: IEEE: 78–83 [DOI: 10.1109/ICALIP.2012.6376590]

Huang F H, Mao Z Y and Shi W Z. 2016. ICA-ASIFT-based multi-temporal matching of high-resolution remote sensing urban images. Cybernetics and Information Technologies, 16(5): 34–49

Ke Y and Sukthankar R. 2004. PCA-SIFT: a more distinctive representation for local image descriptors//Proceedings of 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC, USA: IEEE: 506–513 [DOI: 10.1109/CVPR.2004.1315206]

Kupfer B, Netanyahu N S and Shimshoni I. 2015. An efficient SIFT-based mode-seeking algorithm for sub-pixel registration of remotely sensed images. IEEE Geoscience and Remote Sensing Letters, 12(2): 379–383

Lei T J, Li L, Kan G Y, Zhang Z B, Sun T, Zhang X L, Ma J W and Huang S F. 2016. Automatic registration of unmanned aerial vehicle remote sensing images based on an improved sift algorithm//Proceedings of SPIE Volume 10033, Eighth International Conference on Digital Image Processing. Chengdu, China: SPIE: 10033 [DOI: 10.1117/12.2245126]

Li J Y, Hu Q W and Ai M Y. 2016. Robust feature matching for remote sensing image registration based on L q -estimator. IEEE Geoscience and Remote Sensing Letters, 13(12): 1989–1993

李晓明, 郑链, 胡占义. 2006. 基于SIFT特征的遥感影像自动配准. 遥感学报, 10(6): 885–892

Li X M, Zheng L and Hu Z Y. 2006. SIFT based automatic registration of remotely-sensed imagery. Journal of Remote Sensing, 10(6): 885–892 (

Liu F Q, Bi F K, Chen L, Shi H and Liu W. 2016. Feature-area optimization: a novel SAR image registration method. IEEE Geoscience and Remote Sensing Letters, 13(2): 242–246

刘小军, 周越, 凌建国, 沈红斌, 杨杰. 2007. 基于轮廓特征的SAR图像自动配准. 计算机工程, 33(4): 176–178

Liu X J, Zhou Y, Ling J G, Shen H B and Yang J. 2007. Patch-based SAR image automatic registration. Computer Engineering, 33(4): 176–178 (

Lowe D G. 1999. Object recognition from local scale-invariant features. Proceeding of the 7th International Conference on Computer Vision. Kerkyra, Greece: IEEE: 1150–1157 [DOI: 10.1109/ICCV.1999.790410]

Lowe D G. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2): 91–110

Ma J L, Chan J C W and Canters F. 2010. Fully automatic subpixel image registration of multiangle CHRIS/proba data. IEEE Transactions on Geoscience and Remote Sensing, 48(7): 2829–2839

Ma J Y, Zhou H B, Zhao J, Gao Y, Jiang J J and Tian J W. 2015. Robust feature matching for remote sensing image registration via locally linear transforming. IEEE Transactions on Geoscience and Remote Sensing, 53(12): 6469–6481

Merkle N, Müller R, Schwind P, Palubinskas G and Reinartz P. 2015. A new approach for optical and SAR satellite image registration. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, II-3/W4: 119–126 [DOI: 10.5194/isprsannals-II-3-W4-119–2015]

Murphy J M, Moigne J L, Harding D J. 2016. Automatic image registration of multimodal remotely sensed data with global shearlet features. IEEE Transactions on Geoscience and Remote Sensing, 54(3): 1685–1704

Nagarajan S and Schenk T. 2016. Feature-based registration of historical aerial images by Area Minimization. ISPRS Journal of Photogrammetry and Remote Sensing, 116: 15–23

Paul S and Pati U C. 2016. Remote sensing optical image registration using modified uniform robust SIFT. IEEE Geoscience and Remote Sensing Letters, 13(9): 1300–1304

Pramote O U and Piamsa-nga P. 2015. Improve accuracy of disparity map for stereo images using sift and weighted color model//Proceedings of the 7th International Conference on Knowledge and Smart Technology. Chonburi, Thailand: IEEE: 109–114 [DOI: 10.1109/KST.2015.7051470]

Rong W B, Li Z J, Zhang W and Sun L N. 2014. An improved canny edge detection algorithm//Proceedings of 2014 IEEE International Conference on Mechatronics and Automation. Tianjin, China: IEEE: 577–582 [DOI: 10.1109/ICMA.2014.6885761]

Sedaghat A and Ebadi H. 2015a. Distinctive order based self-similarity descriptor for multi-sensor remote sensing image matching. ISPRS Journal of Photogrammetry and Remote Sensing, 108: 62–71

Sedaghat A and Ebadi H. 2015b. Remote sensing image matching based on adaptive binning SIFT descriptor. IEEE Transactions on Geoscience and Remote Sensing, 53(10): 5283–5293

Suri S and Reinartz P. 2010. Mutual-information-based registration of terraSAR-X and Ikonos imagery in urban areas. IEEE Transactions on Geoscience and Remote Sensing, 48(2): 939–949

Touzi R, Lopes A and Bousquet P. 1988. A statistical and geometrical edge detector for SAR images. IEEE Transactions on Geoscience and Remote Sensing, 26(6): 764–773

项盛文, 文贡坚, 高峰, 伍颖佳. 2015. 基于多模型表示的高分辨率遥感图像配准方法. 传感器与微系统, 34(10): 22–24, 28

Xiang S W, Wen G J, Gao F and Wu Y J. 2015. High resolution remote sensing image registration method based on multi-model representation. Transducer and Microsystem Technologies, 34(10): 22–24, 28 (

尤红建, 胡岩峰. 2014. SAR和光学图像精配准技术的研究. 雷达学报, 3(1): 78–84

You H J and Hu Y F. 2014. Investigation on fine registration for SAR and optical image. Journal of Radars, 3(1): 78–84 (

Zhang Q, Cao Z G, Hu Z W, Jia Y H and Wu X L. 2015. Joint image registration and fusion for panchromatic and multispectral images. IEEE Geoscience and Remote Sensing Letters, 12(3): 467–471

Zhao C Y and Goshtasby A A. 2016. Registration of multitemporal aerial optical images using line features. ISPRS Journal of Photogrammetry and Remote Sensing, 117: 149–160

Zhu H, Li Y F, Yu J M, Leung H and Li Y H. 2014. Ensemble registration of multisensor images by a variational bayesian approach. IEEE Sensors Journal, 14(8): 2698–2705

Zitová B and Flusser J. 2003. Image registration methods: a survey. Image and Vision Computing, 21(11): 977–1000

Alert me when the article has been cited

提交

Convolutional self-attention network for automated rock detection in complex martian terrain

Review of cross-view image geo-localization datasets

Point cloud contour feature point extraction method on the basis of domain feature parameter fusion

Edge-perception enhanced segmentation method for high-resolution remote sensing image

Multiscale feature extraction model for remote sensing identification of erosion gullies in Northeast China’s black soil region： A case study of Hailun City