基于相似性衡量函数优化的SAR时空极化信息一体化洪涝变化检测方法

doi:10.11947/j.AGCS.2024.20230355

测绘学报 ›› 2024, Vol. 53 ›› Issue (12): 2375-2390.doi: 10.11947/j.AGCS.2024.20230355

• 摄影测量学与遥感 • 上一篇

基于相似性衡量函数优化的SAR时空极化信息一体化洪涝变化检测方法

赵金奇¹^,²(), 李宇轩¹, 刘子蓉¹^,²(), 安庆³, 宋时雨¹, 牛玉芬⁴

^1.中国矿业大学环境与测绘学院，江苏　徐州　221116
^2.自然资源部地理国情监测重点实验室，湖北　武汉　430072
^3.武昌理工学院人工智能学院，湖北　武汉　430223
^4.河北工程大学矿业与测绘工程学院，河北　邯郸　056038

收稿日期:2023-08-24 发布日期:2025-01-06
通讯作者: 刘子蓉 E-mail:masurq@cumt.edu.cn;liuzirong2003@163.com
作者简介:赵金奇（1990—），男，副教授，研究方向为合成孔径雷达智能解译及应用。E-mail：masurq@cumt.edu.cn
基金资助:
国家自然科学基金(42307255);自然资源部地理国情监测重点实验室开放基金(2023NGCM12);河北省自然科学基金(D2023402033);江苏省双创博士资助项目(JSSCBS20221531)

Flood change detection method using optimized similarity measurement function with temporal-spatial-polarized SAR information

Jinqi ZHAO¹^,²(), Yuxuan LI¹, Zirong LIU¹^,²(), Qing AN³, Shiyu SONG¹, Yufen NIU⁴

^1.School of Environment and Spatial informatics, China University of Mining and Technology, Xuzhou 221116, China
^2.Key Laboratory of National Geographic Census Monitoring, Ministry of Natural Resources, Wuhan 430072, China
^3.Artificial Intelligence School, Wuchang University of Technology, Wuhan 430223, China
^4.School of Mining and Geomatics Engineering, Hebei University of Engineering, Handan 056038, China

Received:2023-08-24 Published:2025-01-06
Contact: Zirong LIU E-mail:masurq@cumt.edu.cn;liuzirong2003@163.com
About author:ZHAO Jinqi (1990—), male, associate professor, majors in synthetic aperture radar intelligent interpretation and its applications.　E-mail: masurq@cumt.edu.cn
Supported by:
The National Natural Science Foundation of China(42307255);Open Fund Project of Key Laboratory of National Geographic Census and Monitoring, Ministry of Natural Resources(2023NGCM12);Hebei Natural Science Foundation(D2023402033);The Jiangsu Provincial Double-Innovation Doctor Program(JSSCBS20221531)

摘要/Abstract

摘要：

合成孔径雷达（synthetic aperture radar，SAR）具备全天时、全天候的观测优势，能够在恶劣环境下进行洪涝监测。现有洪涝变化检测方法易受其他地物变化影响且对SAR数据特性针对性不强。针对以上问题，本文提出了一种基于相似性衡量函数优化的SAR时空极化信息一体化洪涝的变化检测方法。该方法融合多时相、多极化信息，构建“时-空-极化”SAR数据，并对K-means聚类方法进行改进，通过一体化处理减少先聚类后变化检测的误差累积；进一步顾及“时-空-极化”SAR影像数据特性，引入交叉熵对相似性衡量函数进行优化，能够对由于洪涝引起的水体变化进行准确区分。最后，利用武汉市全极化Radarsat-2数据和黄冈市黄梅县双极化Sentinel-1数据对本文方法的有效性进行试验，试验结果表明，本文方法在武汉两个试验区中虚警率（false alarm，FA）、总体错误率（total errors，TE）、总体正确率（overall accuracy，OA）和卡帕系数（Kappa）4个精度评价指标均优于其他对比方法，分别为5.06%、5.66%、94.34%、0.69，以及1.61%、2.61%、97.39%、0.65；在黄梅县的试验结果中TE、OA和Kappa表现最优，分别为1.67%，98.33%和0.73。本文方法可以有效抑制其他地物变化对洪涝变化检测的影响。同时具有较快的响应速度，且能够有效抑制城市变化和山区阴影对洪涝检测的影响。

关键词: 洪涝, 变化检测, 时-空-极化, 扩展K-means聚类, 交叉熵

Abstract:

Thanks to its ability for all-weather and all-day observation, synthetic aperture radar (SAR) enables flood monitoring in harsh environments. Currently, flood change detection methods are easily affected by the changes of other ground objects and designed inadequacy for SAR data characteristics. To solve these problems, a novel change detection method using temporal characteristics and flood characteristic distribution is proposed. The proposed method integrates multi-temporal and multi-polarized information to construct temporal-spatial-polarized SAR data. Furthermore, the improved K-means clustering approach for constructed data reduces accumulated errors from different temporal clustering processing. In addition, considering the distribution characteristics of temporal-spatial-polarized SAR data, Cross Entropy is designed to optimize the similarity measurement function to accurately distinguish water body changes caused by flooding. Finally, multi-temporal fully polarimetric Radarsat-2 data from Wuhan and dual polarimetric Sentinel-1 data from Huangmei County in Huanggang are used to validate the effectiveness of the proposed method. The false alarm rate (FA), total errors rate (TE), overall accuracy (OA), and Kappa of our method in Wuhan applied are 5.06%, 5.66%, 94.34%, 0.69 and 1.61%, 2.61%, 97.39%, 0.65, which highlight the advantages of the proposed method. The TE, OA and Kappa of experimental results in Huangmei County have the best performance, which are 1.67%, 98.33% and 0.73. Our method effectively mitigates the effect of changes in other land features on the detection of changes in water bodies. Furthermore, our method not only effectively reduces the impact of other land cover changes but also boasts a swift response capability. It can effectively suppress the influence of urban changes and mountain shadow in flood detection.

Key words: flood, change detection, temporal-spatial-polarized, improved K-means, cross entropy

中图分类号:

P234

赵金奇, 李宇轩, 刘子蓉, 安庆, 宋时雨, 牛玉芬. 基于相似性衡量函数优化的SAR时空极化信息一体化洪涝变化检测方法[J]. 测绘学报, 2024, 53(12): 2375-2390.

Jinqi ZHAO, Yuxuan LI, Zirong LIU, Qing AN, Shiyu SONG, Yufen NIU. Flood change detection method using optimized similarity measurement function with temporal-spatial-polarized SAR information[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(12): 2375-2390.

图/表 22

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

图10

图11

图12

表2

图13

图14

表3

图15

图16

表4

图17

表5

参考文献 43

[1]	YAN Pu, FANG Yue, CHEN Jie, et al. Automated extraction for water bodies using new water index from landsat 8 OLI images[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(1): 59-75.
[2]	田国珍, 刘新立, 王平, 等. 中国洪水灾害风险区划及其成因分析[J]. 灾害学, 2006, 21(2): 1-6.
	TIAN Guozhen, LIU Xinli, WANG Ping, et al. Flood risk zoning and causal analysis in China[J]. Journal of Catastrophology, 2006, 21(2): 1-6.
[3]	刘彤, 闫天池. 我国的主要气象灾害及其经济损失[J]. 自然灾害学报, 2011, 20(2): 90-95.
	LIU Tong, YAN Tianchi. Main meteorological disasters in China and their economic losses[J]. Journal of Natural Disasters, 2011, 20(2): 90-95.
[4]	赵金奇. 多时相极化SAR影像变化检测方法研究[J]. 测绘学报, 2019, 48(4): 536. DOI:. doi: 10.11947/J.AGCS.2019.20180281
	ZHAO Jinqi. Research on change detection method in multi-temporal polarimetric SAR imagery[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(4): 536. DOI:. doi: 10.11947/J.AGCS.2019.20180281
[5]	CHEN Zhanlong, LI Shuangjiang, XU Yongyang, et al. Correg-Yolov3: a method for dense buildings detection in high-resolution remote sensing images[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(2): 51-61.
[6]	眭海刚, 赵博飞, 徐川, 等. 多模态序列遥感影像的洪涝灾害应急信息快速提取[J]. 武汉大学学报(信息科学版), 2021, 46(10): 1441-1449.
	SUI Haigang, ZHAO Bofei, XU Chuan, et al. Rapid extraction of flood disaster emergency information with multi-modal sequence remote sensing images[J]. Geomatics and Information Science of Wuhan University, 2021, 46(10): 1441-1449.
[7]	SUN Sun, WU Tao, SUN Sun, et al. Object detection research of SAR image using improved faster region-based convolutional neural network[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(3): 18-28.
[8]	李树涛, 李聪妤, 康旭东. 多源遥感图像融合发展现状与未来展望[J]. 遥感学报, 2021, 25(1): 148-166.
	Li Shutao, Li Congyu, Kang Xudong. Development status and future prospects of multi-source remote sensing image fusion[J]. National Remote Sensing Bulletin, 2021, 25(1): 148-166.
[9]	李丹, 吴保生, 陈博伟, 等. 基于卫星遥感的水体信息提取研究进展与展望[J]. 清华大学学报(自然科学版), 2020, 60(2): 147-161.
	LI Dan, WU Baosheng, CHEN Bowei, et al. Review of water body information extraction based on satellite remote sensing[J]. Journal of Tsinghua University (Science and Technology), 2020, 60(2): 147-161.
[10]	眭海刚, 冯文卿, 李文卓, 等. 多时相遥感影像变化检测方法综述[J]. 武汉大学学报(信息科学版), 2018, 43(12): 1885-1898.
	SUI Haigang, FENG Wenqing, LI Wenzhuo, et al. Review of change detection methods for multi-temporal remote sensing imagery[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12): 1885-1898.
[11]	公茂果, 苏临之, 李豪, 等. 合成孔径雷达影像变化检测研究进展[J]. 计算机研究与发展, 2016, 53(1): 123-137.
	GONG Maoguo, SU Linzhi, LI Hao, et al. A survey on change detection in synthetic aperture radar imagery[J]. Journal of Computer Research and Development, 2016, 53(1): 123-137.
[12]	WANG Min, WANG Peidong. CFM-UNet: a joint CNN and transformer network via cross feature modu-lation for remote sensing images segmentation[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(4): 40-47.
[13]	ZHANG Kaiyu, LÜ Xiaolei, GUO Bin, et al. Unsupervised SAR image change detection based on histogram fitting error minimization and convolutional neural network[J]. Remote Sensing, 2023, 15(2): 470.
[14]	DONG Zhen, LIANG Zifan, WANG Guojie, et al. Mapping inundation extents in Poyang Lake area using Sentinel-1 data and transformer-based change detection method[J]. Journal of Hydrology, 2023, 620: 129455.
[15]	张鑫龙, 陈秀万, 李飞, 等. 高分辨率遥感影像的深度学习变化检测方法[J]. 测绘学报, 2017, 46(8): 999-1008. DOI:. doi: 10.11947/J.AGCS.2017.20170036
	ZHANG Xinlong, CHEN Xiuwan, LI Fei, et al. Change detection method for high resolution remote sensing images using deep learning[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(8): 999-1008. DOI:. doi: 10.11947/J.AGCS.2017.20170036
[16]	ZHANG Yun. Smart photogrammetric and remote sensing image processing for very high resolution optical images— examples from the CRC-AGIP lab at UNB[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(2): 17-26.
[17]	冷英, 李宁. 一种改进的变化检测方法及其在洪水监测中的应用[J]. 雷达学报, 2017, 6(2): 204-212.
	LENG Ying, LI Ning. Improved change detection method for flood monitoring[J]. Journal of Radars, 2017, 6(2): 204-212.
[18]	LIU Liu, JI Xinyuan, LIU Liu, et al. A novel unsupervised change detection method with structure consistency and GFLICM based on UAV images[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(1): 91-102.
[19]	BAN Yifang, YOUSIF O A. Multitemporal spaceborne SAR data for urban change detection in China[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(4): 1087-1094.
[20]	INGLADA J, MERCIER G. A new statistical similarity measure for change detection in multitemporal SAR images and its extension to multiscale change analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(5): 1432-1445.
[21]	GONG Maoguo, CAO Yu, WU Qiaodi. A neighborhood-based ratio approach for change detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(2): 307-311.
[22]	刘本强, 赵争, 魏钜杰. 一种利用邻域相对熵的SAR影像变化检测方法[J]. 遥感信息, 2018, 33(3): 91-97.
	LIU Benqiang, ZHAO Zheng, WEI Jujie. A method of SAR image change detection based on relative entropy within neighborhood[J]. Remote Sensing Information, 2018, 33(3): 91-97.
[23]	CONRADSEN K, NIELSEN A A, SKRIVER H. Determining the points of change in time series of polarimetric SAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(5): 3007-3024.
[24]	GAO Gui, LIU Li, ZHAO Lingjun, et al. An adaptive and fast CFAR algorithm based on automatic censoring for target detection in high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(6): 1685-1697.
[25]	OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
[26]	KAPUR J N, SAHOO P K, WONG A K C. A new method for gray-level picture thresholding using the entropy of the histogram[J]. Computer Vision, Graphics, and Image Processing, 1985, 29(3): 273-285.
[27]	KITTLER J, ILLINGWORTH J. Minimum error thresholding[J]. Pattern Recognition, 1986, 19(1): 41-47.
[28]	KANUNGO T, MOUNT D M, NETANYAHU N S, et al. An efficient k-means clustering algorithm: analysis and implementation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 881-892.
[29]	CELIK T. Unsupervised change detection in satellite images using principal component analysis and k-means clustering[J]. IEEE Geoscience and Remote Sensing Letters, 2009, 6(4): 772-776.
[30]	GONG M, ZHOU Z, MA J. Change detection in synthetic aperture radar images based on image fusion and fuzzy clustering[J]. IEEE Transactions on Image Processing, 2012, 21(4): 2141-2151.
[31]	ZHANG Minghui, LIU Di, WANG Siyuan, et al. Multisource remote sensing data-based flood monitoring and crop damage assessment: a case study on the 20 July 2021 extraordinary rainfall event in Henan, China[J]. Remote Sensing, 2022, 14(22): 5771.
[32]	AVENDANO J, MORA S F, VERA J E, et al. Flood monitoring and change detection based on unsupervised image segmentation and fusion in multitemporal SAR imagery[C]//Proceedings of the 12th International Conference on Electrical Engineering, Computing Science and Automatic Control. Mexico City: IEEE, 2015: 1-6.
[33]	ZHANG Zhang, MARINO M, NUNZIATA N, et al. Marine target detection using dual-polarimetric SAR imagery[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(1): 63-69.
[34]	SEN L J, ERIC P. Polarimetric radar imaging: from basics to applications[M]. Boca Raton: CRC Press, 2009.
[35]	CONRADSEN K, NIELSEN A, SKRIVER H. Determining the points of change in time series of polarimetric SAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(5): 3007-3024.
[36]	张立福, 陈浩, 孙雪剑, 等. 多维遥感数据时空谱一体化存储结构设计[J]. 遥感学报, 2017, 21(1): 62-73.
	ZHANG Lifu, CHEN Hao, SUN Xuejian, et al. Designing spatial-temporal-spectral integrated storage structure of multi-dimensional remote sensing images[J]. Journal of Remote Sensing, 2017, 21(1): 62-73.
[37]	SHANNON C. A mathematical theory of communication[J]. The Bell System Technical Journal, 1948, 27(1): 379-423.
[38]	陈超, 梁锦涛, 杨刚, 等. 面向土地覆盖精准分类的遥感特征参数优选方法[J]. 测绘学报, 2024, 53(7): 1401-1416. DOI:. doi: 10.11947/J.AGCS.2024.20230327
	CHEN Chao, LIANG Jintao, YANG Gang, et al. Remote sensing parameters optimization for accurate land cover classifi-cation[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(7): 1401-1416. DOI:. doi: 10.11947/J.AGCS.2024.20230327
[39]	HARIS K, EFSTRATIADIS S N, MAGLAVERAS N, et al. Hybrid image segmentation using watersheds and fast region merging[J]. IEEE Transactions on Image Processing, 1998, 7(12): 1684-1699.
[40]	SHI Jianbo, MALIK J. Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905.
[41]	YANG Le, SHI Lei, YANG Jie, et al. PolSAR additive noise estimation based on shadow regions[J]. International Journal of Remote Sensing, 2021, 42(1): 259-273.
[42]	VAN ZYL J, KIM Y. Synthetic aperture radar polarimetry[M]. Hoboken: Wiley, 2011.
[43]	CARRARA W G, GOODMAN R S, MAJEWSKI R M. Spotlight synthetic aperture radar: signal processing algorithms[M]. Boston: Artech House, 1995.

方法	FA/（%）	TE/（%）	OA/（%）	Kappa
传统方法+欧氏距离	5.49	7.13	92.87	0.59
传统方法+交叉熵	5.30	6.40	93.60	0.64
扩展方法+KL散度	5.71	6.33	93.67	0.66
扩展方法+JS散度	5.56	6.83	93.17	0.62
扩展方法+卡方距离	5.72	6.69	93.31	0.63
扩展方法+Bray Curtis距离	6.35	8.55	91.45	0.51
本文方法	5.06	5.66	94.34	0.69

方法	FA/（%）	TE/（%）	OA/（%）	Kappa
传统方法+欧氏距离	5.89	6.53	93.47	0.43
传统方法+交叉熵	4.55	5.12	94.88	0.51
扩展方法+KL散度	2.14	2.95	97.05	0.62
扩展方法+JS散度	1.83	2.91	97.09	0.62
扩展方法+卡方距离	8.05	9.57	90.43	0.24
扩展方法+Bray Curtis距离	2.30	4.14	95.86	0.44
本文方法	1.61	2.61	97.39	0.65

数据类别	严东湖				严西湖
数据类别	FA/（%）	TE/（%）	OA/（%）	Kappa	FA/（%）	TE/（%）	OA/（%）	Kappa
HH	5.64	8.51	91.49	0.49	0.88	3.34	96.66	0.40
HV	7.97	8.97	91.03	0.54	10.66	11.66	88.34	0.24
VV	4.73	7.67	92.33	0.51	0.20	2.83	97.17	0.41
HH+HV	5.28	6.92	93.08	0.60	5.80	6.67	93.33	0.41
VV+HV	5.05	6.60	93.40	0.62	3.52	4.65	95.35	0.49
全极化	5.06	5.66	94.34	0.69	1.61	2.61	97.39	0.65

方法	FA/（%）	TE/（%)	OA/（%）	Kappa
传统方法+欧氏距离	2.43	3.18	96.82	0.63
传统方法+交叉熵	1.04	2.83	97.17	0.56
扩展方法+KL散度	1.14	2.35	97.65	0.67
扩展方法+JS散度	0.43	1.91	98.09	0.68
扩展方法+卡方距离	0.22	1.88	98.12	0.68
扩展方法+Bray Curtis距离	0.69	2.25	97.75	0.63
本文方法	0.38	1.67	98.33	0.73

基于相似性衡量函数优化的SAR时空极化信息一体化洪涝变化检测方法

Flood change detection method using optimized similarity measurement function with temporal-spatial-polarized SAR information

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 22

参考文献 43

相关文章 15

编辑推荐

Metrics

本文评价

[1]	鄢薪, 慎利, 潘俊杰, 戴延帅, 王继成, 郑晓莉, 李志林. 多尺度特征融合与空间优化的弱监督高分遥感建筑变化检测[J]. 测绘学报, 2024, 53(8): 1586-1597.
[2]	宁晓刚, 张翰超, 张瑞倩. 遥感影像高可信智能不变检测技术框架与方法实践[J]. 测绘学报, 2024, 53(6): 1098-1112.
[3]	顾海燕, 杨懿, 李海涛, 孙立坚, 丁少鹏, 刘世琦. 高分辨率遥感影像样本库动态构建与智能解译应用[J]. 测绘学报, 2024, 53(6): 1165-1179.
[4]	彭代锋, 翟晨晨, 周顶蔚, 张永军, 管海燕, 臧玉府. 基于金字塔语义token全局信息增强的高分光学遥感影像变化检测[J]. 测绘学报, 2024, 53(6): 1195-1211.
[5]	丁少鹏, 卢秀山, 刘如飞, 杨懿, 顾海燕, 李海涛. 联合目标特征引导与多重注意力的建筑物变化检测[J]. 测绘学报, 2024, 53(6): 1224-1235.
[6]	庞世燕, 郝京京, 左志奇, 兰晶晶, 胡翔云. 融合密集连接和自注意力机制的高分辨率遥感影像变化检测方法[J]. 测绘学报, 2024, 53(12): 2244-2253.
[7]	韦春桃, 龚成, 周永绪. 一种联合空间约束与差异特征聚合的变化检测网络[J]. 测绘学报, 2023, 52(9): 1538-1547.
[8]	王超, 王帅, 陈晓, 李俊勇, 谢涛. 联合UNet++和多级差分模块的多源光学遥感影像对象级变化检测[J]. 测绘学报, 2023, 52(2): 283-296.
[9]	姜明, 张新长, 孙颖, 冯炜明, 阮永俭. 全尺度特征聚合的高分辨率遥感影像变化检测网络[J]. 测绘学报, 2023, 52(10): 1738-1748.
[10]	叶沅鑫, 孙苗苗, 周亮, 杨超, 刘天逸, 郝思媛. 面向建筑物变化检测的主体边缘分解与重组神经网络[J]. 测绘学报, 2023, 52(1): 71-81.
[11]	张祖勋, 姜慧伟, 庞世燕, 胡翔云. 多时相遥感影像的变化检测研究现状与展望[J]. 测绘学报, 2022, 51(7): 1091-1107.
[12]	林珲, 吴贤宇, 潘家祎, 邹海波. 中国城市洪涝实时预报研究:现状与挑战[J]. 测绘学报, 2022, 51(7): 1306-1316.
[13]	梁哲恒, 黎宵, 邓鹏, 盛森, 姜福泉. 融合多尺度特征注意力的遥感影像变化检测方法[J]. 测绘学报, 2022, 51(5): 668-676.
[14]	罗卿莉, 崔峰志, 魏钜杰, 明磊. SAR影像变化检测的前景特征流形排序法[J]. 测绘学报, 2022, 51(11): 2365-2378.
[15]	王昶, 张永生, 纪松, 张磊. 建筑物变化的多特征融和及随机多图综合检测法[J]. 测绘学报, 2021, 50(2): 235-247.