基于可靠匹配点约束的遥感影像密集匹配

doi:10.12082/dqxxkx.2021.200660

地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (8): 1508-1523.doi: 10.12082/dqxxkx.2021.200660

基于可靠匹配点约束的遥感影像密集匹配

张鑫¹(), 王竞雪¹^,²^,^*(), 刘肃艳¹, 高嵩¹

1.辽宁工程技术大学测绘与地理科学学院,阜新 123000
2.西南交通大学地球科学与环境工程学院,成都 611756

收稿日期:2020-11-03 修回日期:2021-01-28 出版日期:2021-08-25 发布日期:2021-10-25
通讯作者: 王竞雪
作者简介:张鑫（1997— ）,女,山西临汾人,硕士生,主要从事遥感影像密集匹配理论与方法研究。E-mail: 1454579518@qq.com
基金资助:
国家自然科学基金项目(41871379);国家自然科学基金项目(42071343);辽宁省兴辽英才计划项目(XLYC2007026)

A Dense Matching Algorithm for Remote Sensing Images based on Reliable Matched Points Constraint

ZHANG Xin¹(), WANG Jingxue¹^,²^,^*(), LIU Suyan¹, GAO Song¹

1. School of Geomatics, Liaoning Technical University, Fuxin 123000, China
2. Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China

Received:2020-11-03 Revised:2021-01-28 Online:2021-08-25 Published:2021-10-25
Contact: WANG Jingxue
Supported by:
National Natural Science Foundation of China(41871379);National Natural Science Foundation of China(42071343);Liaoning Revitalization Talents Program(XLYC2007026)

摘要/Abstract

摘要：

针对现有由稀到密的加密匹配算法中,初始匹配点可靠性低将导致迭代匹配拓展过程存在较多误匹配的问题,提出一种基于可靠匹配点约束的遥感影像密集匹配算法。首先,利用SIFT匹配点约束直线匹配获得的同名直线构建虚拟匹配点集,结合虚拟匹配点集和SIFT匹配点集建立初始匹配点集;然后,依次采用局部影像信息和局部几何约束对初始匹配点集进行检核剔除错误匹配,主要体现在利用指纹信息和梯度信息构建匹配点局部区域约束剔除较为明显的误匹配点,利用匹配三角网构建局部几何约束剔除由相似纹理产生的误匹配点,得到优化后的可靠匹配点;最后,基于可靠匹配点构建的Delaunay三角网,以三角形重心为加密匹配基元,结合核线约束和仿射变换对其进行迭代匹配拓展,得到最终匹配点集。选取4组资源三号卫星前视数据和后视数据进行实验,结果表明：利用局部纹理特征和局部几何双重约束模型可有效剔除误匹配点得到可靠匹配点,通过可靠匹配点进行迭代匹配拓展得到的密集匹配结果相较于对比算法具有更高匹配精度,在4组数据上其平均匹配精度为95%,具有较好的匹配稳定性。

关键词: 可靠匹配点, 密集匹配, 遥感影像, 核线约束, 仿射变换, 资源三号, Delaunay三角网

Abstract:

To avoid the problem of mismatches caused by initial matched points that may contain false matches during iterative dense matching based on corresponding points, a dense matching algorithm for remote sensing images based on reliable matched point constraint is presented. Firstly, to increase the number of initial matching points and expand the covering range of initial matching points, the initial set of matched points containing the matched Scale-invariant Feature Transform (SIFT) points and virtual corresponding points is constructed, where the virtual corresponding points are generated from the intersections of corresponding lines obtained by the line matching algorithm based on the matched SIFT points constraint. Secondly, the initial set of matched points is checked to remove the false matches using local image information and local geometry constraints in turn. This process first uses the local texture feature constraint constructed based on fingerprint information and gradient information to eliminate the mismatched points with low similarity, and then uses the local geometric constraint constructed by Delaunay triangulation to remove the false matches generated by similar textures, thereby obtaining the optimized set of reliable matched points. Finally, the Delaunay triangulation is constructed using reliable matched points, and the gravity center of the triangles satisfying the areal threshold is used as the matching primitive during the dense matching process. The matching based on the epipolar constraint and affine transformation constraint is performed iteratively to obtain the dense matching results. This paper used four sets of forward and backward viewing data of ZY-3 to perform parameter analysis experiment and comparative analysis experiment to prove the effectiveness of the proposed dense matching algorithm. The results of parameter analysis experiment show that the reliable matched points can be obtained when the weighted index, texture feature similarity threshold, and local geometric similarity threshold are 0.3, 0.95, and 0.85, respectively. The average matching accuracy of the reliable matched points on the four sets of data is improved by 19% compared with the initial matched point. Meanwhile, the results of comparative analysis experiment show that the dense matching algorithm based on the reliable matched point constraint can effectively avoid the error propagation, which has higher matching accuracy compared with the comparison algorithms selected in this paper. The average matching accuracy of the four sets of data is 95%. Therefore, the algorithm can obtain better dense matching results by effectively eliminating mismatched points.

Key words: reliable matched points, dense matching, remote sensing images, epipolar constraint, affine transformation, ZY-3, Delaunay triangulation network

张鑫, 王竞雪, 刘肃艳, 高嵩. 基于可靠匹配点约束的遥感影像密集匹配[J]. 地球信息科学学报, 2021, 23(8): 1508-1523.DOI:10.12082/dqxxkx.2021.200660

ZHANG Xin, WANG Jingxue, LIU Suyan, GAO Song. A Dense Matching Algorithm for Remote Sensing Images based on Reliable Matched Points Constraint[J]. Journal of Geo-information Science, 2021, 23(8): 1508-1523.DOI:10.12082/dqxxkx.2021.200660

图/表 21

图1

图2

图3

图4

图5

图6

图7

表1

表2

图8

图9

表3

图10

图11

表4

图12

表5

图13

图14

图15

表6

参考文献 33

[1]	Marr D, Poggio T. A computational theory of human stereo vision[J]. Proceedings of the Royal Society of London, 1979, 204(1156):301-328.
[2]	Mayhew J E W, Frisby J P. Psychophysical and computational studies towards a theory of human stereopsis[J]. Artificial Intelligence, 1981, 17(1-3):349-385. doi: 10.1016/0004-3702(81)90029-1
[3]	凌霄. 基于多重约束的多源光学卫星影像自动匹配方法研究[D]. 武汉:武汉大学, 2017.
	[Ling X. Automatic matching of multi-sources optical satellite images based on multiple constraints[D]. Wuhan: Wuhan University, 2017. ]
[4]	马方龙. 基于归一化积相关匹配的彩色图像灰度化研究[D]. 兰州:兰州大学, 2018.
	[Ma F L. Research on color-to-gray conversion based on normalized cross correlation[D]. Lanzhou: Lanzhou University, 2018. ]
[5]	杨佳宾, 姜永涛, 杨幸彬, 等. 基于Dense SIFT特征的无人机影像快速拼接方法[J]. 地球信息科学学报, 2019, 21(4):588-599. doi: 10.12082/dqxxkx.2019.190001
	[Yang J B, Jiang Y T, Yang X B, et al. A fast mosaic algorithm of UAV images based on dense SIFT feature matching[J]. Journal of Geo-information Science, 2019, 21(4):588-599. ]
[6]	Masry S E. An automatic method for height profile determination[J]. The Photogrammetric Record, 2006, 7(42):728-730. doi: 10.1111/j.1477-9730.1973.tb01212.x
[7]	Hel-Or Y, Hel-Or H, David E. Fast template matching in non-linear tone-mapped images[C]// 2011 International Conference on Computer Vision. IEEE, 2011:1355-1362.
[8]	Wang C, Wan T R, Palmer I J. A real-time dynamic simulation scheme for large-scale flood hazard using 3D real world data[C]// 2007 11th International Conference Information Visualization (IV '07). IEEE, 2007:607-612.
[9]	施颖琦, 顾力栩. 基于互信息多步骤优化的医学图像配准[J]. 计算机工程, 2006, 32(22):187-188.
	[Shi Y Q, Gu L X. Optimized multistage medical image registration method based on mutual information[J]. Computer Engineering, 2006, 32(22):187-188. ]
[10]	Valgren C, Lilienthal A J. SIFT, SURF & seasons: Appearance-based long-term localization in outdoor environments[J]. Robotics and Autonomous Systems, 2010, 58(2):149-156. doi: 10.1016/j.robot.2009.09.010
[11]	Vijayan V, Kp P. A comparative analysis of RootSIFT and SIFT methods for drowsy features extraction[J]. Procedia Computer Science, 2020, 171:436-445. doi: 10.1016/j.procs.2020.04.046
[12]	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.0000029664.99615.94
[13]	姜文聪, 张继贤, 程春泉, 等. SIFT与粗差剔除算法相结合的机载SAR影像匹配研究[J]. 地球信息科学学报, 2013, 15(3):440-445. doi: 10.3724/SP.J.1047.2013.00440
	[Jiang W C, Zhang J X, Cheng C Q, et al. Matching of airborne SAR images based on a combination of SIFT algorithm with mismatching points eliminated algorithm[J]. Journal of Geo-information Science, 2013, 15(3):440-445. ]
[14]	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
[15]	Chum O, Matas J. Matching with PROSAC - progressive sample consensus[C]// 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). IEEE, 2005:220-226.
[16]	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 pmid: 23787350
[17]	Sattler T, Leibe B, Kobbelt L. SCRAMSAC: Improving RANSAC's efficiency with a spatial consistency filter[C]// 2009 IEEE 12th International Conference on Computer Vision. IEEE, 2009:2090-2097.
[18]	Liu Z, Marlet R. Virtual line descriptor and semi-local graph matching method for reliable feature correspondence[C]// Procedings of the British Machine Vision Conference 2012. British Machine Vision Association, 2012:1-11.
[19]	Hu H, Zhu Q, Du Z Q, et al. Reliable spatial relationship constrained feature point matching of oblique aerial images[J]. Photogrammetric Engineering & Remote Sensing, 2015, 81(1):49-58.
[20]	Li J Y, Hu Q W, Ai M Y. 4FP-structure: A robust local region feature descriptor[J]. Photogrammetric Engineering & Remote Sensing, 2017, 83(12):813-826.
[21]	李建晔. 点、线结合下的多源高分辨率遥感影像匹配[D]. 阜新:辽宁工程技术大学, 2012.
	[Li J Y. The matching of Multi-source high resolution image based on points and lines[D]. Fuxin: Liaoning Technical University, 2012. ]
[22]	刘肃艳, 王竞雪. 结合同名点及核线约束的近景影像直线匹配[J]. 测绘科学, 2019, 44(10):128-135.
	[Liu S Y, Wang J X. Line matching for close-range images by combining corresponding points and epipolar constraint[J]. Science of Surveying and Mapping, 2019, 44(10):128-135. ]
[23]	梁艳, 盛业华, 张卡, 等. 利用局部仿射不变及核线约束的近景影像直线特征匹配[J]. 武汉大学学报·信息科学版, 2014, 39(2):229-233.
	[Liang Y, Sheng Y H, Zhang K, et al. Linear feature matching method based on local affine invariant and epipolar constraint for close-range images[J]. Geomatics and Information Science of Wuhan University, 2014, 39(2):229-233. ]
[24]	鲜翠琼, 秦学, 朱道恒, 等. 一种图文组合相似度算法的设计与优化[J]. 软件工程, 2020, 23(8):9-12.
	[Xian C Q, Qin X, Zhu D H, et al. Design and optimization of a similarity algorithm for combination of graphics and text[J]. Software Engineering. 2020, 23(8):9-12. ]
[25]	Jain P, Dixit V S. Proposed similarity measure using Bhattacharyya coefficient for context aware recommender system[J]. Journal of Intelligent and Fuzzy Systems, 2018, 36(5):1-12. doi: 10.3233/JIFS-17063
[26]	Jiang S, Jiang W S. Reliable image matching via photometric and geometric constraints structured by Delaunay triangulation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 153:1-20. doi: 10.1016/j.isprsjprs.2019.04.006
[27]	Nguyen H V, Bai L. Cosine similarity metric learning for face verification[C]. Computer Vision-ACCV 2010, Lecture Notes in Computer Science, 2010:709-720.
[28]	张卡, 盛业华, 叶春. 基于数字视差模型和改进SIFT特征的数字近景立体影像匹配[J]. 测绘学报, 2010, 39(6):624-630.
	[Zhang K, Sheng Y H, Ye C. Digital close-range stereo image matching based on digital parallax model and improved SIFT feature[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(6):624-630. ]
[29]	吴波. 自适应三角形约束下的立体影像可靠匹配方法[D]. 武汉:武汉大学, 2006.
	[Wu B. A reliable stereo image matching method based on the self-adaptive triangle constraint[D]. WuHan: WuHan University, 2006. ]
[30]	王竞雪, 张晶, 张雪. 迭代三角网约束的近景影像密集匹配[J]. 信号处理, 2018, 34(3):347-356.
	[Wang J X, Zhang J, Zhang X. A dense matching algorithm of close-range images constrained by iterative triangle network[J]. Journal of Signal Processing, 2018, 34(3):347-356. ]
[31]	自然资源部国土卫星遥感应用中心. 自然资源卫星影像云服务平台[DB/OL]. http://sasclouds.com/chinese/normal/.
	[Land Satellite Remote Sensing Application Center, Ministry of Natural Resources. The Cloud Service Platform of Natural Resources Satellite Images[DB/OL]. http://sasclouds.com/chinese/normal/.]
[32]	欧阳欢, 范大昭, 纪松, 等. 结合离散化描述与同名点约束的线特征匹配[J]. 测绘学报, 2018, 47(10):1363-1371.
	[OuY H, Fan D Z, Ji S, et al. Line matching based on discrete description and conjugate point constrain[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(10):1363-1371. ]
[33]	Jia D, Wu S, Zhao M Y. Dense matching for wide baseline images based on equal proportion of triangulation[J]. Electronics Letters, 2019, 55(7):380-382. doi: 10.1049/el.2018.7659

有效载荷	光谱范围/μm	空间分辨率/m	幅宽/km	侧摆能力	重访时间/d
前视相机	0.50~0.80	3.5	52	±32°	5
后视相机	0.50~0.80	3.5	52	±32°	5

T_gh	λ=0.1			λ=0.2			λ=0.3			λ=0.4			λ=0.5
T_gh	I_match/对	I_cor/对	I_acc	I_match/对	I_cor/对	I_acc	I_match/对	I_cor/对	I_acc	I_match/对	I_cor/对	I_acc	I_match/对	I_cor/对	I_acc
0.75	2591	133	0.05	2592	240	0.09	2591	305	0.11	2591	99	0.03	2585	89	0.03
0.80	2595	280	0.10	2596	444	0.17	2593	480	0.19	2587	219	0.08	2588	188	0.07
0.85	2592	702	0.27	2592	753	0.29	2597	816	0.31	2590	534	0.20	2589	482	0.19
0.90	2586	1786	0.69	2599	1996	0.76	2622	2170	0.80	2586	1691	0.65	2588	1609	0.62
0.95	2374	2190	0.92	2379	2210	0.93	2367	2225	0.94	2398	2221	0.93	2449	2271	0.92

T_geo	λ=0.3,T_gh=0.95
T_geo	I_match/对	I_cor/对	I_acc
0.75	2463	2370	0.96
0.80	2451	2378	0.97
0.85	2438	2387	0.98
0.90	2344	2301	0.98
0.95	2231	2180	0.98

数据	第1组		第2组		第3组		第4组
数据	初始匹配点	可靠匹配点	初始匹配点	可靠匹配点	初始匹配点	可靠匹配点	初始匹配点	可靠匹配点
I_match /对	622	154	1943	382	712	176	224	121
I_cor /对	406	133	1534	379	547	173	190	116
I_acc	0.65	0.87	0.79	0.99	0.77	0.98	0.85	0.97

T₁	文献[30]算法			r	文献[33]算法			T_s	本文算法
T₁	I_match/对	I_cor/对	I_acc	r	I_match/对	I_cor/对	I_acc	T_s	I_match/对	I_cor/对	I_acc
85	1584	1251	0.78	15	1506	1451	0.96	80	1449	1423	0.98
53	2569	1987	0.76	20	2907	2803	0.96	50	2438	2366	0.97
20	6358	4810	0.75	30	6198	5984	0.96	18	6409	6287	0.98
15	8385	6478	0.77	45	8194	7817	0.95	14	8241	8082	0.98

基于可靠匹配点约束的遥感影像密集匹配

A Dense Matching Algorithm for Remote Sensing Images based on Reliable Matched Points Constraint

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 21

参考文献 33

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	戴俊杰, 董婧雯, 杨晟, 孙毅中. 基于空间突变特征的城市边缘区提取方法[J]. 地球信息科学学报, 2021, 23(8): 1401-1421.
[2]	张春森, 贾欣, 吴蓉蓉, 崔卫红, 史书, 郭丙轩. 面向对象高分遥感影像典型自然地物半自动提取[J]. 地球信息科学学报, 2021, 23(6): 1050-1062.
[3]	唐璎, 刘正军, 杨懿, 顾海燕, 杨树文. 基于特征增强和ELU的神经网络建筑物提取研究[J]. 地球信息科学学报, 2021, 23(4): 692-709.
[4]	朱盼盼, 李帅朋, 张立强, 李洋. 基于多任务学习的高分辨率遥感影像建筑提取[J]. 地球信息科学学报, 2021, 23(3): 514-523.
[5]	郭紫甜, 王春梅, 刘欣, 庞国伟, 朱梦阳, 王晋卿. 基于小流域抽样单元的中国FROM-GLC30数据精度评价[J]. 地球信息科学学报, 2021, 23(3): 524-535.
[6]	何腕营, 王竞雪. 基于直线间几何属性特征相似性约束的组直线匹配算法[J]. 地球信息科学学报, 2020, 22(9): 1766-1778.
[7]	赵青松, 兰安军, 范泽孟, 杨青. 贵州省不同地貌形态类型土壤侵蚀强度变化的定量分析[J]. 地球信息科学学报, 2020, 22(7): 1555-1566.
[8]	赵尚民, 程维明, 蒋经天, 沙文娟. 资源三号卫星DEM数据与全球开放DEM数据的误差对比[J]. 地球信息科学学报, 2020, 22(3): 370-378.
[9]	何红术, 黄晓霞, 李红旮, 倪凌佳, 王新歌, 陈崇, 柳泽. 基于改进U-Net网络的高分遥感影像水体提取[J]. 地球信息科学学报, 2020, 22(10): 2010-2022.
[10]	郭子慧, 刘伟. 深度学习和遥感影像支持的矢量图斑地类解译真实性检查方法[J]. 地球信息科学学报, 2020, 22(10): 2051-2061.
[11]	吴瑞娟, 何秀凤, 王静. 结合像元级与对象级的滨海湿地变化检测方法[J]. 地球信息科学学报, 2020, 22(10): 2078-2087.
[12]	蔡博文,王树根,王磊,邵振峰. 基于深度学习模型的城市高分辨率遥感影像不透水面提取[J]. 地球信息科学学报, 2019, 21(9): 1420-1429.
[13]	王兴,康俊锋,刘学军,王美珍,张超. 设施农业典型地物改进Faster R-CNN识别方法[J]. 地球信息科学学报, 2019, 21(9): 1444-1454.
[14]	李泽宇,明冬萍,范莹琳,赵林峰,刘思民. 遥感影像监督分割评价指标比较与分析[J]. 地球信息科学学报, 2019, 21(8): 1265-1274.
[15]	张刚, 刘文彬, 张男. 基于区域特征分割的密集匹配点云渐进形态学滤波[J]. 地球信息科学学报, 2019, 21(4): 615-622.

数据	文献[30]算法				文献[33]算法				本文算法
数据	I_match/对	I_cor/对	I_acc	Times/s	I_match/对	I_cor/对	I_acc	Times/s	I_match/对	I_cor/对	I_acc	Times/s
第1组	2577	1933	0.75	25	6466	5341	0.82	98	2490	2283	0.91	68
第2组	2455	2055	0.83	24	1479	1325	0.89	77	2482	2403	0.97	65
第3组	2569	1987	0.76	26	2907	2803	0.96	85	2438	2387	0.98	65
第4组	2218	1796	0.81	21	2318	2109	0.91	84	2175	2068	0.95	47
均值统计	2454	1618	0.79	24	3292	2894	0.90	86	2396	2285	0.95	61