Please wait a minute...
 
Remote Sensing for Natural Resources    2023, Vol. 35 Issue (3) : 134-144     DOI: 10.6046/zrzyyg.2022205
|
Detection of changes in SAR images based on an improved fully-connected conditional random field
DONG Ting1,2(), FU Weiqi1,2, SHAO Pan1,2(), GAO Lipeng3, WU Changdong1,2
1. Hubei Key Laboratory of Intelligent Vision Monitoring for Hydropower Engineering, China Three Gorges University, Yichang 443002, China
2. College of Computer and Information Technology, China Three Gorges University, Yichang 443002, China
3. School of Software, Northwestern Polytechnical University, Xi’an 710129, China
Download: PDF(5646 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

Change detection is the research focus of remote sensing. To overcome the shortcomings of the existing conditional random field (CRF)-based change detection, this study proposed a novel change detection method for synthetic aperture Radar (SAR) images based on an improved fully connected CRF (FCCRF). Firstly, this study summarized the comparative algorithms for generating differential images from SAR images, which were divided into three levels, namely pixel, neighborhood, and super-neighborhood. Then, this study selected three typical comparative algorithms-log ratio (LR), neighborhood ratio (NR), and improved non-local graph (INLG)-to produce three sets of complementary differential images. Finally, this study improved the FCCRF by extending the number of Gaussian kernels of the pairwise potential function of FCCRF and generated the change detection maps using the improved FCCRF model. The change detection method proposed in this study integrated the two-phase original SAR images, three sets of complementary differential images, and the global spatial information of images. In addition, this study presented a simple and effective parameter determination strategy, which allows the FCCRF to perform the change detection automatically. Experimental results on four sets of real SAR image data confirmed the effectiveness of the change detection method proposed in this study.
Keywords remote sensing      unsupervised change detection      SAR image      differential image      conditional random field     
ZTFLH:  TP79  
Issue Date: 19 September 2023
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Ting DONG
Weiqi FU
Pan SHAO
Lipeng GAO
Changdong WU
Cite this article:   
Ting DONG,Weiqi FU,Pan SHAO, et al. Detection of changes in SAR images based on an improved fully-connected conditional random field[J]. Remote Sensing for Natural Resources, 2023, 35(3): 134-144.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2022205     OR     https://www.gtzyyg.com/EN/Y2023/V35/I3/134
Fig.1  Flowchart of IFCCRF change detection method
Fig.2  Taxonomy of the main generation algorithms for SAR difference image
Fig.3  Datasets
Fig.4  Change detection results on dataset 1 with different algorithms
Fig.5  Change detection results on dataset 2 with different algorithms
Fig.6  Change detection results on dataset 3 with different algorithms
Fig.7  Change detection results on dataset 4 with different algorithms
方法 数据1 数据2
MD FA OE Kappa MD FA OE Kappa
LR 981 4 046 5 027 0.586 2 569 2 241 2 810 0.753 3
NR 521 24 063 24 584 0.209 3 341 6 697 7 038 0.546 5
INLG 1 647 1 168 2 815 0.682 6 495 2 275 2 773 0.758 5
PCAKM 1 220 1 597 2 817 0.708 4 373 1 525 1 898 0.826 4
MRF 941 2 377 3 318 0.688 2 719 596 1 315 0.865 9
CRF 1 143 1 617 2 760 0.716 9 620 425 1 045 0.892 8
FCCRF 1 218 1 106 2 324 0.747 6 834 180 1 014 0.891 4
FRFCM 517 13 896 14 413 0.335 5 919 514 1 513 0.842 9
IFCCRF 1 196 652 1 848 0.790 2 409 358 767 0.922 3
方法 数据3 数据4
MD FA OE Kappa MD FA OE Kappa
LR 338 902 1 240 0.865 0 289 91 380 0.818 0
NR 40 32 288 32 328 0.110 3 73 351 424 0.833 8
INLG 762 149 911 0.888 6 288 212 500 0.773 4
PCAKM 25 1 618 1 643 0.836 8 143 355 498 0.799 8
MRF 328 843 1 171 0.871 9 44 533 577 0.790 7
CRF 499 460 959 0.889 3 261 63 324 0.844 8
FCCRF 700 177 877 0.893 7 181 174 355 0.843 9
FRFCM 423 830 1 253 0.861 5 114 640 754 0.730 1
IFCCRF 189 362 570 0.935 5 151 115 266 0.881 5
Tab.1  Quantitative indicators of four datasets for change detection
方法 数据2 数据3
MD FA OE Kappa MD FA OE Kappa
F-FCM 509 1 245 1 754 0.835 0 439 355 794 0.908 0
F-FCCRF 710 763 1473 0.852 2 376 294 670 0.922 4
IFCCRF 409 358 767 0.922 3 189 362 570 0.935 5
Tab.2  Change detection results obtained by F-FCM, F-FCCRF and IFCCRF
[1] 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):123-147.
[1] Gong M G, Su L Z, Li H, et al. A survey on change detection in synthetic aperture Radar imagery[J]. Journal of Computer Research and Development, 2016, 53(1):123-147.
[2] 王译著, 黄亮, 陈朋弟, 等. 联合显著性和多方法差异影像融合的遥感影像变化检测[J]. 自然资源遥感, 2021, 33(3):89-96.doi:10.6046/zrzyyg.2020312.
doi: 10.6046/zrzyyg.2020312
[2] Wang Y Z, Huang L, Chen P D, et al. Change detection of remote sensing images based on the fusion of co-saliency difference images[J]. Remote Sensing for Natural Resources, 2021, 33(3):89-96.doi:10.6046/zrzyyg.2020312.
doi: 10.6046/zrzyyg.2020312
[3] 吴柳青, 胡翔云. 基于多尺度多特征的高空间分辨率遥感影像建筑物自动化检测[J]. 国土资源遥感, 2019, 31(1):71-78.doi:10.6046/gtzyyg.2019.01.10.
doi: 10.6046/gtzyyg.2019.01.10
[3] Wu L Q, Hu X Y. Automatic building detection of high-resolution remote sensing images based on multi-scale and multi-feature[J]. Remote Sensing for Land and Resources, 2019, 31(1):71-78.doi:10.6046/gtzyyg.2019.01.10.
doi: 10.6046/gtzyyg.2019.01.10
[4] 何陈临秋, 程博, 陈金奋, 等. 基于GF-3全极化SAR数据的滨海湿地信息提取方法[J]. 自然资源遥感, 2021, 33(4):105-110.doi:10.6046/zrzyyg.2020353.
doi: 10.6046/zrzyyg.2020353
[4] He C L Q, Cheng B, Chen J F, et al. Information extraction methods of coastal wetland based on GF-3 fully polarimetric SAR data[J]. Remote Sensing for Natural Resources, 2021, 33(4):105-110.doi:10.6046/zrzyyg.2020353.
doi: 10.6046/zrzyyg.2020353
[5] Gong M G, Li Y, Jiao L C, et al. SAR change detection based on intensity and texture changes[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 93(7):123-135.
doi: 10.1016/j.isprsjprs.2014.04.010 url: https://linkinghub.elsevier.com/retrieve/pii/S0924271614001051
[6] 王建明, 史文中, 邵攀. 自适应距离和模糊拓扑优化的模糊聚类SAR影像变化检测[J]. 测绘学报, 2018, 47(5):611-619.
doi: 10.11947/j.AGCS.2018.20160607
[6] Wang J M, Shi W Z, Shao P. Change detection method for SAR image using adaptive distance and fuzzy topology optimization-based fuzzy clustering[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(5):611-619.
[7] 庄会富, 邓喀中, 余美, 等. 结合KI准则和逆高斯模型的SAR影像非监督变化检测[J]. 武汉大学学报(信息科学版), 2018, 43(2):282-288.
[7] Zhuang H F, Deng K Z, Yu M, et al. A novel approach combining KI criterion and inverse Gaussian model to unsupervised change detection in SAR images[J]. Geomatics and Information Science of Wuhan University, 2018, 43(2):282-288.
[8] Sun Y L, Lei L, Guan D D, et al. SAR image change detection based on nonlocal low-rank model and two-level clustering[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 1(99):1-14.
doi: 10.1109/JSTARS.4609443 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4609443
[9] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(4):874-887.
doi: 10.1109/TGRS.2004.842441 url: http://ieeexplore.ieee.org/document/1411993/
[10] Moser G, Serpico S B. Generalized minimum-error thresholding for unsupervised change detection from SAR amplitude imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(10):2972-2982.
doi: 10.1109/TGRS.2006.876288 url: http://ieeexplore.ieee.org/document/1704990/
[11] Celik T. Change detection in satellite images using a genetic algorithm approach[J]. IEEE Geoscience and Remote Sensing Letters, 2010, 7(2):386-390.
doi: 10.1109/LGRS.2009.2037024 url: http://ieeexplore.ieee.org/document/5395684/
[12] 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.
doi: 10.1109/TGRS.2007.893568 url: http://ieeexplore.ieee.org/document/4156318/
[13] Gong M G, Cao Y, Wu Q D. A neighborhood-based ratio approach for change detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 9(2):307-311.
doi: 10.1109/LGRS.2011.2167211 url: http://ieeexplore.ieee.org/document/6035757/
[14] 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.
doi: 10.1109/LGRS.2009.2025059 url: http://ieeexplore.ieee.org/document/5196726/
[15] Sun Y L, Lei L, Li X, et al. Nonlocal patch similarity based heterogeneous remote sensing change detection[J]. Pattern Recognition, 2020, 109:107598.
doi: 10.1016/j.patcog.2020.107598 url: https://linkinghub.elsevier.com/retrieve/pii/S0031320320304015
[16] Sun Y L, Lei L, Li X, et al. Structure consistency-based graph for unsupervised change detection with homogeneous and heterogeneous remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-21.
[17] Ma J J, Gong M G, Zhou Z Q. Wavelet fusion on ratio images for change detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(6):1122-1126.
doi: 10.1109/LGRS.2012.2191387 url: http://ieeexplore.ieee.org/document/6193123/
[18] Zheng Y, Zhang X, Hou B, et al. Using combined difference image and K-means clustering for SAR image change detection[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(3):691-695.
doi: 10.1109/LGRS.2013.2275738 url: http://ieeexplore.ieee.org/document/6587802/
[19] Zhang Y, Wang S G, Wang C, et al. SAR image change detection using saliency extraction and Shearlet transform[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(12):4701-4710.
doi: 10.1109/JSTARS.4609443 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4609443
[20] Bruzzone L, Prieto D F. Automatic analysis of the difference image for unsupervised change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(3):1171-1182.
doi: 10.1109/36.843009 url: http://ieeexplore.ieee.org/document/843009/
[21] Hao M, Shi W, Zhang H, et al. Unsupervised change detection with expectation-maximization-based level set[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(1):210-214.
doi: 10.1109/LGRS.2013.2252879 url: http://ieeexplore.ieee.org/document/6519319/
[22] Bazi Y, Melgani F, Al-Sharari H D. Unsupervised change detection in multispectral remotely sensed imagery with level set methods[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(8):3178-3187.
doi: 10.1109/TGRS.2010.2045506 url: http://ieeexplore.ieee.org/document/5454347/
[23] Shao P, Shi W, Liu Z, et al. Unsupervised change detection using fuzzy topology-based majority voting[J]. Remote Sensing, 2021, 13:3171.
doi: 10.3390/rs13163171 url: https://www.mdpi.com/2072-4292/13/16/3171
[24] Lyu P Y, Zhong Y F, Zhao J, et al. Unsupervised change detection based on hybrid conditional random field model for high spatial resolution remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(7):4002-4015.
doi: 10.1109/TGRS.2018.2819367 url: https://ieeexplore.ieee.org/document/8360128/
[25] Hedjam R, Kalacska M, Mignotte M, et al. Iterative classifiers combination model for change detection in remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(12):6997-7008.
doi: 10.1109/TGRS.2016.2593982 url: http://ieeexplore.ieee.org/document/7548313/
[26] Gong M G, Su L Z, Jia M, et al. Fuzzy clustering with a modified MRF energy function for change detection in synthetic aperture Radar images[J]. IEEE Transactions on Fuzzy Systems, 2013, 22(1):98-109.
doi: 10.1109/TFUZZ.2013.2249072 url: http://ieeexplore.ieee.org/document/6471198/
[27] Hao M, Zhang H, Shi W Z, et al. Unsupervised change detection using fuzzy C-means and MRF from remotely sensed images[J]. Remote Sensing Letters, 2014, 4(12):1185-1194.
doi: 10.1080/2150704X.2013.858841 url: http://www.tandfonline.com/doi/abs/10.1080/2150704X.2013.858841
[28] Subudhi B N, Bovolo F, Ghosh A, et al. Spatio-contextual fuzzy clustering with Markov random field model for change detection in remotely sensed images[J]. Optics and Laser Technology, 2014, 57:284-292.
doi: 10.1016/j.optlastec.2013.10.003 url: https://linkinghub.elsevier.com/retrieve/pii/S003039921300368X
[29] 范奎奎, 王中元, 欧阳斯达, 等. DT-CWT结合MRF的遥感图像变化检测[J]. 遥感学报, 2017, 21(3):375-385.
[29] Fan K K, Wang Z Y, Ouyang S D, et al. Change detection of remote sensing images through DT-CWT and MRF[J]. Journal of Remote Sensing, 2017, 21(3):375-385.
[30] Hoberg T, Rottensteiner F, Feitosa R Q, et al. Conditional random fields for multitemporal and multiscale classification of optical satellite imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 53(2):659-673.
doi: 10.1109/TGRS.2014.2326886 url: http://ieeexplore.ieee.org/document/6841049/
[31] Cao G, Zhou L C, Li Y P. A new change-detection method in high-resolution remote sensing images based on a conditional random field model[J]. International Journal of Remote Sensing, 2016, 37(5):1173-1189.
doi: 10.1080/01431161.2016.1148284 url: https://www.tandfonline.com/doi/full/10.1080/01431161.2016.1148284
[32] Zhou L C, Cao G, Li Y P, et al. Change detection based on conditional random field with region connection constraints in high-reso-lution remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(8):3478-3488.
doi: 10.1109/JSTARS.4609443 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4609443
[33] Lafferty J, McCallum A, Pereira F C. Conditional random fields:Probabilistic models for segmenting and labeling sequence data[C]// International Conference on Machine Learning(ICML), 2001:282-289.
[34] Kumar S, Hebert M. Discriminative random fields:A discriminative framework for contextual interaction in classification[C]// Ninth IEEE International Conference on Computer Vision.IEEE, 2003:1150-1157.
[35] Krähenbühl P, Koltun V. Efficient inference in fully connected CRFs with Gaussian edge potentials[J]. Advances in Neural Information Processing Systems, 2011, 24(1):109-117.
[36] Bezdek J C. Pattern recognition with fuzzy objective function algorithms[M]. New York: Plenum Press, 1981:43-93.
[37] Shao P, Yi Y Q, Dong T, et al. Novel multiscale decision fusion approach to unsupervised change detection for high-resolution images[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19(1):1-5.
[38] Lei T, Jia X H, Zhang Y N, et al. Significantly fast and robust fuzzy C-means clustering algorithm based on morphological reconstruction and membership filtering[J]. IEEE Transactions on Fuzzy Systems, 2018, 26(5):3027-3041.
doi: 10.1109/TFUZZ.91 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=91
[1] NIU Xianghua, HUANG Wei, HUANG Rui, JIANG Sili. A high-fidelity method for thin cloud removal from remote sensing images based on attentional feature fusion[J]. Remote Sensing for Natural Resources, 2023, 35(3): 116-123.
[2] WANG Jianqiang, ZOU Zhaohui, LIU Rongbo, LIU Zhisong. A method for extracting information on coastal aquacultural ponds from remote sensing images based on a U2-Net deep learning model[J]. Remote Sensing for Natural Resources, 2023, 35(3): 17-24.
[3] TANG Hui, ZOU Juan, YIN Xianghong, YU Shuchen, HE Qiuhua, ZHAO Dong, ZOU Cong, LUO Jianqiang. River and lake sand mining in the Dongting Lake area: Supervision based on high-resolution remote sensing images and typical case analysis[J]. Remote Sensing for Natural Resources, 2023, 35(3): 302-309.
[4] YU Hang, AN Na, WANG Jie, XING Yu, XU Wenjia, BU Fan, WANG Xiaohong, YANG Jinzhong. High-resolution remote sensing-based dynamic monitoring of coal mine collapse areas in southwestern Guizhou: A case study of coal mine collapse areas in Liupanshui City[J]. Remote Sensing for Natural Resources, 2023, 35(3): 310-318.
[5] WANG Jing, WANG Jia, XU Jiangqi, HUANG Shaodong, LIU Dongyun. Exploring ecological environment quality of typical coastal cities based on an improved remote sensing ecological index: A case study of Zhanjiang City[J]. Remote Sensing for Natural Resources, 2023, 35(3): 43-52.
[6] XU Xinyu, LI Xiaojun, ZHAO Heting, GAI Junfei. Pansharpening algorithm of remote sensing images based on NSCT and PCNN[J]. Remote Sensing for Natural Resources, 2023, 35(3): 64-70.
[7] LIU Li, DONG Xianmin, LIU Juan. A performance evaluation method for semantic segmentation models of remote sensing images considering surface features[J]. Remote Sensing for Natural Resources, 2023, 35(3): 80-87.
[8] FANG He, ZHANG Yuhui, HE Yue, LI Zhengquan, FAN Gaofeng, XU Dong, ZHANG Chunyang, HE Zhonghua. Spatio-temporal variations of vegetation ecological quality in Zhejiang Province and their driving factors[J]. Remote Sensing for Natural Resources, 2023, 35(2): 245-254.
[9] ZHANG Xian, LI Wei, CHEN Li, YANG Zhaoying, DOU Baocheng, LI Yu, CHEN Haomin. Research progress and prospect of remote sensing-based feature extraction of opencast mining areas[J]. Remote Sensing for Natural Resources, 2023, 35(2): 25-33.
[10] MA Shibin, PI Yingnan, WANG Jia, ZHANG Kun, LI Shenghui, PENG Xi. High-efficiency supervision method for green geological exploration based on remote sensing[J]. Remote Sensing for Natural Resources, 2023, 35(2): 255-263.
[11] WANG Ping. Application of thermal infrared remote sensing in monitoring the steel overcapacity cutting[J]. Remote Sensing for Natural Resources, 2023, 35(2): 271-276.
[12] LI Tianchi, WANG Daoru, ZHAO Liang, FAN Renfu. Classification and change analysis of the substrate of the Yongle Atoll in the Xisha Islands based on Landsat8 remote sensing data[J]. Remote Sensing for Natural Resources, 2023, 35(2): 70-79.
[13] DIAO Mingguang, LIU Yong, GUO Ningbo, LI Wenji, JIANG Jikang, WANG Yunxiao. Mask R-CNN-based intelligent identification of sparse woods from remote sensing images[J]. Remote Sensing for Natural Resources, 2023, 35(2): 97-104.
[14] ZHAO Hailan, MENG Jihua, JI Yunpeng. Application status and prospect of remote sensing technology in precise planting management of apple orchards[J]. Remote Sensing for Natural Resources, 2023, 35(2): 1-15.
[15] XIONG Dongyang, ZHANG Lin, LI Guoqing. MaxEnt-based multi-class classification of land use in remote sensing image interpretation[J]. Remote Sensing for Natural Resources, 2023, 35(2): 140-148.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech