Unsupervised change detection of man-made objects using coherent and incoherent features of multi-temporal SAR images

doi:10.23919/JSEE.2022.000087

Journal of Systems Engineering and Electronics ›› 2022, Vol. 33 ›› Issue (4): 896-906.doi: 10.23919/JSEE.2022.000087

收稿日期:2021-12-03 出版日期:2022-08-30 发布日期:2022-08-30

Unsupervised change detection of man-made objects using coherent and incoherent features of multi-temporal SAR images

Hao FENG¹(), Jianzhong WU^2,^3,⁴(), Lu ZHANG^1,*(), Mingsheng LIAO¹()

¹ State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
² Key Laboratory of Land Subsidence Monitoring and Prevention, Ministry of Land and Resources, Shanghai 200072, China
³ Shanghai Engineering Research Center of Land Subsidence, Shanghai 200072, China
⁴ Shanghai Institute of Geological Survey, Shanghai 200072, China

Received:2021-12-03 Online:2022-08-30 Published:2022-08-30
Contact: Lu ZHANG E-mail:fengh@whu.edu.cn;wjzhongsh@163.com;luzhang@whu.edu.cn;liao@whu.edu.cn
About author:|FENG Hao was born in 1992. He received his B.S. degree in geographic information system from Nanjing University of Posts and Telecommunications, Nanjing, China, in 2014, and M.E. degree in surveying and mapping engineering from Wuhan University, Wuhan, China, in 2016. He is currently pursuing his Ph.D. degree in photogrammetry and remote sensing with the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China. His research interests include multi-temporal synthetic aperture radar images processing and change detection. E-mail: fengh@whu.edu.cn||WU Jianzhong was born in 1977. He received his B.E. degree in hydrogeology and engineering geology from Chang’an University, Xi’an, China, in 1999, and M.E. degree in geological engineering from China University of Geosciences, Wuhan, China, in 2002. He has been with the Shanghai Institute of Geological Survey, Shanghai, where he became a senior engineer in 2011. Since 2016, he has been with the Key Laboratory of Land Subsidence Monitoring and Prevention, the Ministry of Nature Resources. His research interests include land subsidence monitoring and prevention technology.E-mail: wjzhongsh@163.com||ZHANG Lu was born in 1975. He received his B.E. and M.E. degrees in computer science and technology from Wuhan University of Hydraulic and Electrical Engineering, Wuhan, China, in 1997 and 2000, respectively, and Ph.D. degree in photogrammetry and remote sensing from Wuhan University, Wuhan, in 2005. From 2005 to 2007, he was a post-doctoral research fellow at the Institute of Space and Earth Information Science, Chinese University of Hong Kong, Hong Kong. Since 2007, he has been with the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, where he became a full professor in 2013. He has been involved in several research projects funded by the National Natural Science Foundation of China and the Ministry of Science and Technology. He has authored about 30 peer-reviewed scientific papers. His research interests include synthetic aperture radar interferometry as well as remote sensing classification and change detection. E-mail: luzhang@whu.edu.cn||LIAO Mingsheng was born in 1962. He received his B.S. degree in electronic engineering from Wuhan Technical University of Surveying and Mapping (WTUSM), Wuhan, China, in 1982, M.A. degree in electronic and information engineering from Huazhong University of Science and Technology, Wuhan, in 1985, and Ph.D. degree in photogrammetry and remote sensing from WTUSM, in 2000. He has been with the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, where he became a professor in 1997. He is the Principal Investigator (PI) of several projects funded by the Ministry of Science and Technology (MOST) China and the Natural Science Foundation of China. He is also the Co-PI of the ESA-MOST Cooperative Dragon I during 2004–2008, II during 2008–2012, III during 2012–2016, and IV during 2016–2020 projects. He has authored over 60 peer-reviewed journal papers and several book chapters focused on synthetic aperture radar interferometry techniques and applications. His research interests include remote sensing image processing and analysis, algorithms for interferometric synthetic aperture radar, integration and fusion of multisource spatial information, and applications of remote sensing data. E-mail: liao@whu.edu.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (41774006), the Comparative Study of Geo-environment and Geohazards in the Yangtze River Delta and the Red River Delta Project, and the Shanghai Science and Technology Development Foundation (20dz1201200).

摘要/Abstract

Abstract:

Constrained by complex imaging mechanism and extraordinary visual appearance, change detection with synthetic aperture radar (SAR) images has been a difficult research topic, especially in urban areas. Although existing studies have extended from bi-temporal data pair to multi-temporal datasets to derive more plentiful information, there are still two problems to be solved in practical applications. First, change indicators constructed from incoherent feature only cannot characterize the change objects accurately. Second, the results of pixel-level methods are usually presented in the form of the noisy binary map, making the spatial change not intuitive and the temporal change of a single pixel meaningless. In this study, we propose an unsupervised man-made objects change detection framework using both coherent and incoherent features derived from multi-temporal SAR images. The coefficients of variation in time-series incoherent features and the man-made object index (MOI) defined with coherent features are first combined to identify the initial change pixels. Afterwards, an improved spatiotemporal clustering algorithm is developed based on density-based spatial clustering of applications with noise (DBSCAN) and dynamic time warping (DTW), which can transform the initial results into noiseless object-level patches, and take the cluster center as a representative of the man-made object to determine the change pattern of each patch. An experiment with a stack of 10 TerraSAR-X images in Stripmap mode demonstrated that this method is effective in urban scenes and has the potential applicability to wide area change detection.

Key words: change detection, multi-temporal synthetic aperture radar (SAR) data, coherent and incoherent features, clustering

. [J]. Journal of Systems Engineering and Electronics, 2022, 33(4): 896-906.

Hao FENG, Jianzhong WU, Lu ZHANG, Mingsheng LIAO. Unsupervised change detection of man-made objects using coherent and incoherent features of multi-temporal SAR images[J]. Journal of Systems Engineering and Electronics, 2022, 33(4): 896-906.

图/表 14

参考文献 30

1	ZHANG W W, LI J, ZHANG F, et al. Unsupervised change detection of multispectral images based on PCA and low-rank prior. IEEE Geoscience and Remote Sensing Letters, 2021. DOI: 10.1109/LGRS.2021.3090407.
2	HAO M, ZHOU M C, CAI L P An improved graph-cut-based unsupervised change detection method for multispectral remote sensing images. International Journal of Remote Sensing, 2021, 42 (11): 4005- 4022. doi: 10.1080/01431161.2021.1881182
3	SAHA S, BOVOLO F, BRUZZONE L Building change detection in VHR SAR images via unsupervised deep transcoding. IEEE Trans. on Geoscience and Remote Sensing, 2021, 59 (3): 1917- 1929. doi: 10.1109/TGRS.2020.3000296
4	MIAN A, COLLAS A, BRELOY A, et al Robust low-rank change detection for multivariate SAR image time series. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13, 3545- 3556. doi: 10.1109/JSTARS.2020.2999615
5	RIGNOT E J M, ZYL J J V Change detection techniques for ERS-1 SAR data. IEEE Trans. on Geoscience and Remote Sensing, 1993, 31 (4): 896- 906. doi: 10.1109/36.239913
6	HU H T, BAN Y F Unsupervised change detection in multitemporal SAR images over large urban areas. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7 (8): 3248- 3261. doi: 10.1109/JSTARS.2014.2344017
7	CUI S Y, LUO C F Feature-based non-parametric estimation of Kullback–Leibler divergence for SAR image change detection. Remote Sensing Letters, 2016, 7 (11): 1102- 1111. doi: 10.1080/2150704X.2016.1212418
8	XIONG B L, CHEN J M, KUANG G Y A change detection measure based on a likelihood ratio and statistical properties of SAR intensity images. Remote Sensing Letters, 2012, 3 (3): 267- 275. doi: 10.1080/01431161.2011.572093
9	GAMBA P, DELL’ACQUA F, LISINI G Change detection of multitemporal SAR data in urban areas combining feature-based and pixel-based techniques. IEEE Trans. on Geoscience and Remote Sensing, 2006, 44 (10): 2820- 2827. doi: 10.1109/TGRS.2006.879498
10	MARIN C, BOVOLO F, BRUZZONE L Building change detection in multitemporal very high resolution SAR images. IEEE Trans. on Geoscience and Remote Sensing, 2015, 53 (5): 2664- 2682. doi: 10.1109/TGRS.2014.2363548
11	HONG C, SUN G Q, LING F L Urban dynamic change detection in southeastern China based on interferometric SAR. Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2009, 3, 432- 435.
12	LIAO M S, JIANG L M, LIN H, et al Urban change detection based on coherence and intensity characteristics of SAR imagery. Photogrammetric Engineering and Remote Sensing, 2008, 74 (8): 999- 1006. doi: 10.14358/PERS.74.8.999
13	WANG Y F, ZHAO F F, CHENG L, et al Framework for monitoring the conversion of cultivated land to construction land using SAR image time series. Remote Sensing Letters, 2015, 6 (10): 794- 803. doi: 10.1080/2150704X.2015.1081304
14	WASHAY P, BALZ T, MOHAMADI B Coherence change-detection with Sentinel-1 for natural and anthropogenic disaster monitoring in urban areas. Remote Sensing, 2018, 10 (7): 1026. doi: 10.3390/rs10071026
15	KOENIGUER E C, NICOLAS J M Change detection based on the coefficient of variation in SAR time-series of urban areas. Remote Sensing, 2020, 12 (13): 2089. doi: 10.3390/rs12132089
16	ZHANG K Y, FU X K, LYU X L, et al Unsupervised multitemporal building change detection framework based on cosegmentation using time-series SAR. Remote Sensing, 2021, 13 (3): 471. doi: 10.3390/rs13030471
17	YUAN J L, LYU X L, DOU F J, et al Change analysis in urban areas based on statistical features and temporal clustering using TerraSAR-X time-series images. Remote Sensing, 2019, 11 (8): 926. doi: 10.3390/rs11080926
18	ZHANG X Z, SU H, ZHANG C, et al Robust unsupervised small area change detection from SAR imagery using deep learning. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 173, 79- 94. doi: 10.1016/j.isprsjprs.2021.01.004
19	GONG M G, YANG H L, ZHANG P Z Feature learning and change feature classification based on deep learning for ternary change detection in SAR images. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 129, 212- 225. doi: 10.1016/j.isprsjprs.2017.05.001
20	LIU F, JIAO L C, TANG X, et al Local restricted convolutional neural network for change detection in polarimetric SAR images. IEEE Trans. on Neural Networks and Learning Systems, 2019, 30 (3): 818- 833. doi: 10.1109/TNNLS.2018.2847309
21	LI X H, DU Z S, HUANG Y Y, et al A deep translation (GAN) based change detection network for optical and SAR remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 179, 14- 34. doi: 10.1016/j.isprsjprs.2021.07.007
22	LOPES A, TOUZI R, NEZRY E Adaptive speckle filters and scene heterogeneity. IEEE Trans. on Geoscience and Remote Sensing, 1990, 28 (6): 992- 1000. doi: 10.1109/36.62623
23	AIRBUS. Calculation of beta naught and sigma naught for TerraSAR-X data. https://www.intelligence-airbusds.com/en/228-terrasar-x-technical-documents.
24	MAUS V, CAMARA G, CARTAXO R, et al A time-weighted dynamic time warping method for land-use and land-cover mapping. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9 (8): 3729- 3739. doi: 10.1109/JSTARS.2016.2517118
25	YAN J N, WANG L Z, SONG W J, et al A time-series classification approach based on change detection for rapid land cover mapping. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 158, 249- 262. doi: 10.1016/j.isprsjprs.2019.10.003
26	CSILLIK O, BELGIU M, ASNER G P, et al Object-based time-constrained dynamic time warping classification of crops using sentinel-2. Remote Sensing, 2019, 11 (10): 1257. doi: 10.3390/rs11101257
27	PETITJEAN F, INGLADA J, GANCARSKI P Satellite image time series analysis under time warping. IEEE Geoscience and Remote Sensing Letters, 2012, 50 (8): 3081- 3095. doi: 10.1109/TGRS.2011.2179050
28	ESTER M, KRIEGEL H P, SANDER J, et al A density-based algorithm for discovering clusters in large spatial databases with noise. Proc. of the 2nd International Conference on Knowledge Discovery and Data Mining, 1996, 226- 231.
29	ZHU L J, WALKER J P, YE N, et al Roughness and vegetation change detection: a pre-processing for soil moisture retrieval from multi-temporal SAR imagery. Remote Sensing of Environment, 2019, 225, 93- 106. doi: 10.1016/j.rse.2019.02.027
30	JUNKE M, HOCH R, DENGEL A On the evaluation of document analysis components by recall, precision, and accuracy. Journal of Natural Products, 1999, 74 (4): 80- 85.

Parameter	TerraSAR-X dataset
Acquisition date (YYYYMMDD)	20150216 20150504
	20150606 20150709
	20150811 20151016
	20151118 20151210
	20160101 20160203
Imaging mode	Stripmap
Polarization	VV
Pass direction	Descending
Incident angle/(°)	41.06
Slant range spacing/m	1.36
Azimuth spacing/m	1.89

Parameter	Value
Window size of enhanced-Lee filtering	3×3
Window size of coherence estimation	3×3
Threshold of change feature	0.3
Threshold of MOI	0.6
(?, MinPts)	(20,40)
Threshold of iterative convergence	0.25

Method	PR	ACC	RE	KAPPA
Proposed method	0.905	0.815	0.864	0.675
SFTC	0.829	0.611	0.659	0.593

Unsupervised change detection of man-made objects using coherent and incoherent features of multi-temporal SAR images

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 30

相关文章 0

编辑推荐

Metrics

本文评价