A Multi-temporal SAR Coherent Change Detection Method Based on Probabilistic Graphical Models
JI Guangyu①② DONG Yongwei① LI Yanlei① LIANG Xingdong①
①(Key Laboratory of Science and Technology on Microwave Imaging, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China) ②(University of Chinese Academy of Sciences, Beijing 100049, China)
Abstract：Coherent Change Detection (CCD) has good performance on detecting change regions with low coherence in the scene by using repeat-pass Synthetic Aperture Radar (SAR) data. However, some regions as vegetation, radar shadows, sidelobes of strong reflectivity and low reflectivity areas show low coherent character as well, which disturbs the result of change detection, especially in high frequency band SAR CCD with more evident disturbance. This paper proposes a multi-temporal CCD method by establishing a probabilistic graphical model using CCD images formed by multi-temporal SAR data. In this method, multi-temporal CCD images are used as observations to calculate a posterior probability of objective change region via choosing appropriate number of processing CCD images and optimizing the classification of change regions in the scene. The proposed method can reduce the disturbance of low coherence disturb regions effectively. The simulated and experimental results demonstrate the validity and effectiveness of the proposed method.
冀广宇,董勇伟,李焱磊,梁兴东. 一种基于概率图模型的多时相SAR相干变化检测方法[J]. 电子与信息学报, 2017, 39(12): 2912-2920.
JI Guangyu, DONG Yongwei, LI Yanlei, LIANG Xingdong. A Multi-temporal SAR Coherent Change Detection Method Based on Probabilistic Graphical Models. JEIT, 2017, 39(12): 2912-2920.
LIAO Mingsheng, JIANG Liming, LIN Hui, et al. Urban change detection based on coherence and intensity characteristics of SAR imagery[J]. Photogrammetric Engineering & Remote Sensing, 2008, 74(8): 999-1006. doi: 10.14358/PERS.74.8.999.
[2]
PREISS M and STACY N J S. Coherent change detection: Theoretical description and experimental results[R]. DSTO- TR-1851, 2006.
[3]
JOHNSEN T. Coherent change detection in SAR images of harbors with emphasis on findings from container backscattering[C]. IEEE National Radar Conference, Kansas City, Missouri, USA, 2011: 118-123. doi: 10.1109/RADAR. 2011.5960512.
[4]
JUNG J, KIM D, LAVALLE M, et al. Coherent change detection using InSAR temporal decorrelation model: A case study for volcanic ash detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(10): 5765-5775. doi: 10.1109/TGRS.2016.2572166.
[5]
YIN Qiang, LI Yang, HUANG Pingping, et al. Analysis of InSAR coherence loss caused by soil moisture variation [J]. Journal of Radars, 2015, 4(6): 689-697. doi: 10.12000/ JR15075.
[6]
NEWEY M, BENITZ G, and KOGON S. A generalized likelihood ratio test for SAR CCD[C]. Asilomar Conference on Signals, Systems and Computers (ASILOMAR), Pacific Grove, California, USA, 2012: 1727-1730. doi: 10.1109/ ACSSC.2012.6489328.
ZHAO Junxiang, LIANG Xingdong, and LI Yanlei. Change detection in SAR CCD based on the likelihood change Statistics[J]. Journal of Radars, 2017, 6(2): 186-194. doi: 10.12000/JR16065.
[8]
CHA M, PHILLIPS R D, and WOLFE P J. Test statistics for synthetic aperture radar coherent change detection[C]. IEEE Statistical Signal Processing Workshop (SSP), Ann Arbor, Michigan, USA, 2012: 856-859. doi: 10.1109/SSP.2012. 6319841.
[9]
CHA M, PHILLIPS R D, WOLFE P J, et al. Two-stage change detection for synthetic aperture radar[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(12): 6547-6560. doi: 10.1109/TGRS.2015.2444092.
YANG Xiangli, XU Dewei, HUANG Pingping, et al. Change detection of high resolution SAR images by the fusion of coherent/incoherent information[J]. Journal of Radars, 2015, 4(5): 582-590. doi: 10.12000/JR15073.
[11]
WAHL D E, YOCKY D A, JAKOWATZ C V, et al. A new maximum-likelihood change estimator for two-pass SAR coherent change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(4): 2460-2469. doi: 10.1109/TGRS.2015.2502219.
[12]
SCARBOROUGH S M, GORHAM L, MINARDI M J, et al. A challenge problem for SAR change detection and data compression[J]. SPIE Proceedings, 2010, 7699: 1-5. doi: 10. 1117/12.855378.
[13]
AN Lin, LI Ming, ZHANG Peng, et al. Discriminative random fields based on maximum entropy principle for semisupervised SAR image change detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(8): 3395-3404. doi: 10.1109/ JSTARS.2015.2483320.
[14]
ZHOU Licun, CAO Guo, LI Yupeng, et al. Change detection based on conditional random field with region connection constraints in high-resolution 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.2016.2514610.
[15]
BARBER J and KOGON S. Probabilistic three-pass SAR coherent change detection[C]. Asilomar Conference on Signals, Systems and Computers (ASILOMAR), Pacific Grove, California, USA, 2012: 1723-1726. doi: 10.1109/ ACSSC.2012.6489327.
DENG Yuan. Research on highly precise registration algorithm of airborne repeat-pass interferometric SAR[D]. [Master dissertation], University of Chinese Academy of Sciences, 2014: 41-54.
[18]
KOLLER D and FRIEDMAN N. Probabilistic Graphical Models: Principles and Techniques[M]. Cambridge, Massachusetts, USA & London, England, The MIT Press, 2009: 45-102.
[19]
TOIZI R, LOPES A, BRUNIQUEL J, et al. Coherence estimation for SAR imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(1): 135-149. doi: 10.1109/36.739146.
