一种基于卷积神经网络的SAR变化检测方法
|
摘要
为了降低合成孔径雷达(SAR)影像中相干斑对变化检测的影响、减少标注样本的人工成本,该文发展了一种联合分层模糊C均值聚类(FCM)与卷积神经网络的非监督SAR变化检测方法。首先,利用邻域均值比算子计算前后时相的差异图,并利用分层FCM将差异图非监督地初始分割为变化类、非变化类及待确定类别像素;然后,为解决非监督选取样本时出现的样本不均衡问题,提出一种频率不变降采样的数据抽样方法,选取高置信度的变化与非变化样本用于网络训练;最后,利用训练完成的神经网络对待确定类别像素进行分类,得到最终变化结果。采用真实SAR影像数据进行实验。结果表明,该文方法方便有效,具有较高的检测精度。
To reduce the influence of coherent plaque on change detection in synthetic aperture radar(SAR)images and reduce the labor cost of labeled samples,this paper developed an unsupervised SAR change detection method based on hierarchical fuzzy C-means(FCM)and convolutional neural networks.Firstly,the difference between the multitemporal images was calculated by using the neighborhood-based ratio(NR)operator,and the difference image was unsupervised initially segmented into the changed,unchanged and pixels to be determined by using the hierarchical FCM.Then,to solve the problem of sample imbalance during change detection,a data sampling method with frequency-invariant downsampling was proposed.High-confidence changed and unchanged samples were selected for network training.Finally,the trained neural network was used to classify the pixels of the determined to obtain the final change result.Experiments were performed by using SAR images and the results showed that the method was convenient and effective and showed a high accuracy.
To reduce the influence of coherent plaque on change detection in synthetic aperture radar(SAR)images and reduce the labor cost of labeled samples,this paper developed an unsupervised SAR change detection method based on hierarchical fuzzy C-means(FCM)and convolutional neural networks.Firstly,the difference between the multitemporal images was calculated by using the neighborhood-based ratio(NR)operator,and the difference image was unsupervised initially segmented into the changed,unchanged and pixels to be determined by using the hierarchical FCM.Then,to solve the problem of sample imbalance during change detection,a data sampling method with frequency-invariant downsampling was proposed.High-confidence changed and unchanged samples were selected for network training.Finally,the trained neural network was used to classify the pixels of the determined to obtain the final change result.Experiments were performed by using SAR images and the results showed that the method was convenient and effective and showed a high accuracy.
引文
[1]ZHANG Y H,WU H A,WANG H Q,et al.Distance measure based change detectors for polarimetric SARimagery[J].Photogrammetric Engineering&Remote Sensing,2016,82(9):719-727.
[2]YOUSIF O,BAN Y F.Improving urban change detection from multitemporal SAR images using PCA-NLM[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(4):2032-2041.
[3]HU H T,BAN Y F.Unsupervised change detection in multitemporal SAR images over large urban areas[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(8):3248-3261.
[4]LU J,GIUSTARINI L,XIONG B,et al.Automated flood detection with improved robustness and efficiency using multi-temporal SAR data[J].Remote Sensing Letters,2014,5(3):240-248.
[5]SCHLAFFER S,MATGEN P,HOLLAUS M,et al.Flood detection from multi-temporal SAR data using harmonic analysis and change detection[J].International Journal of Applied Earth Observation and Geoinformation,2015,38:15-24.
[6]PANTZE A,SANTORO M,FRANSSON J E S.Change detection of boreal forest using bi-temporal ALOS PALSAR backscatter data[J].Remote Sensing of Environment,2014,155:120-128.
[7]LONGBOTHAM N,PACIFICI F,GLENN T,et al.Multi-modal change detection,application to the detection of flooded areas:outcome of the 2009-2010data fusion contest[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012,5(1):331-342.
[8]DEKKER R J.Speckle filtering in satellite SARchange detection imagery[J].International Journal of Remote Sensing,1998,19(6):1133-1146.
[9]INGLADA J,MERCIER G.A new statistical similarity measure for change detection in multitemporal SARimages and its extension to multiscale change analysis[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(5):1432-1445.
[10]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,2012,9(2):307-311.
[11]HOU B,WEI Q,ZHENG Y G,et al.Unsupervised change detection in SAR image based on Gauss-Log ratio image fusion and compressed projection[J].IEEEJournal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(8):3297-3317.
[12]CUI B,ZHANG Y,YAN L,et al.A SAR change detection method based on the consistency of singlepixel difference and neighbourhood difference[J].Remote Sensing Letters,2019,10(5):488-495.
[13]ZHENG Y G,ZHANG X R,HOU B,et al.Using combined difference image and k-means clustering for SAR image change detection[J].IEEE Geoscience&Remote Sensing Letters,2013,11(3):691-695.
[14]BAZI Y,BRUZZONE L,MELGANI F.An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SARimages[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(4):874-887.
[15]BAZI Y,BRUZZONE L,MELGANI F.Image thresholding based on the EM algorithm and the generalized Gaussian distribution[J].Pattern Recognition,2007,40(2):619-634.
[16]KRINIDIS S,CHATZIS V.A robust fuzzy local information C-means clustering algorithm[J].IEEETransactions on Image Processing,2010,19(5):1328-1337.
[17]GAO F,LIU X P,DONG J Y,et al.Change detection in SAR images based on deep semi-NMF and SVD networks[J].Remote Sensing,2017,9(5):435.
[18]GONG M G,ZHAO J J,LIU J,et al.Change detection in synthetic aperture radar images based on deep neural networks[J].IEEE Transactions on Neural Networks and Learning Systems,2016,27(1):125-138.
[19]GAO F,DONG J Y,LI B,et al.Change detection from synthetic aperture radar images based on neighborhoodbased ratio and extreme learning machine[J].Journal of Applied Remote Sensing,2016,10(4):046019.
[2]YOUSIF O,BAN Y F.Improving urban change detection from multitemporal SAR images using PCA-NLM[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(4):2032-2041.
[3]HU H T,BAN Y F.Unsupervised change detection in multitemporal SAR images over large urban areas[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(8):3248-3261.
[4]LU J,GIUSTARINI L,XIONG B,et al.Automated flood detection with improved robustness and efficiency using multi-temporal SAR data[J].Remote Sensing Letters,2014,5(3):240-248.
[5]SCHLAFFER S,MATGEN P,HOLLAUS M,et al.Flood detection from multi-temporal SAR data using harmonic analysis and change detection[J].International Journal of Applied Earth Observation and Geoinformation,2015,38:15-24.
[6]PANTZE A,SANTORO M,FRANSSON J E S.Change detection of boreal forest using bi-temporal ALOS PALSAR backscatter data[J].Remote Sensing of Environment,2014,155:120-128.
[7]LONGBOTHAM N,PACIFICI F,GLENN T,et al.Multi-modal change detection,application to the detection of flooded areas:outcome of the 2009-2010data fusion contest[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012,5(1):331-342.
[8]DEKKER R J.Speckle filtering in satellite SARchange detection imagery[J].International Journal of Remote Sensing,1998,19(6):1133-1146.
[9]INGLADA J,MERCIER G.A new statistical similarity measure for change detection in multitemporal SARimages and its extension to multiscale change analysis[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(5):1432-1445.
[10]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,2012,9(2):307-311.
[11]HOU B,WEI Q,ZHENG Y G,et al.Unsupervised change detection in SAR image based on Gauss-Log ratio image fusion and compressed projection[J].IEEEJournal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(8):3297-3317.
[12]CUI B,ZHANG Y,YAN L,et al.A SAR change detection method based on the consistency of singlepixel difference and neighbourhood difference[J].Remote Sensing Letters,2019,10(5):488-495.
[13]ZHENG Y G,ZHANG X R,HOU B,et al.Using combined difference image and k-means clustering for SAR image change detection[J].IEEE Geoscience&Remote Sensing Letters,2013,11(3):691-695.
[14]BAZI Y,BRUZZONE L,MELGANI F.An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SARimages[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(4):874-887.
[15]BAZI Y,BRUZZONE L,MELGANI F.Image thresholding based on the EM algorithm and the generalized Gaussian distribution[J].Pattern Recognition,2007,40(2):619-634.
[16]KRINIDIS S,CHATZIS V.A robust fuzzy local information C-means clustering algorithm[J].IEEETransactions on Image Processing,2010,19(5):1328-1337.
[17]GAO F,LIU X P,DONG J Y,et al.Change detection in SAR images based on deep semi-NMF and SVD networks[J].Remote Sensing,2017,9(5):435.
[18]GONG M G,ZHAO J J,LIU J,et al.Change detection in synthetic aperture radar images based on deep neural networks[J].IEEE Transactions on Neural Networks and Learning Systems,2016,27(1):125-138.
[19]GAO F,DONG J Y,LI B,et al.Change detection from synthetic aperture radar images based on neighborhoodbased ratio and extreme learning machine[J].Journal of Applied Remote Sensing,2016,10(4):046019.