计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (12): 175-184.doi: 10.11896/jsjkx.221100092

• 计算机图形学&多媒体 • 上一篇    下一篇

基于双空间共轭自编码器的多时相高光谱异常变化检测

李沙沙1, 邢红杰1, 李刚2,3   

  1. 1 河北大学数学与信息科学学院河北省机器学习与计算智能重点实验室 河北 保定 071002
    2 华北电力大学计算机系 河北 保定 071003
    3 复杂能源系统智能计算教育部工程研究中心 河北 保定 071003
  • 收稿日期:2022-11-14 修回日期:2023-02-15 出版日期:2023-12-15 发布日期:2023-12-07
  • 通讯作者: 邢红杰(hjxing@hbu.edu.cn)
  • 作者简介:(lss96133@163.com)
  • 基金资助:
    国家自然科学基金(61672205);河北省自然科学基金(F2017201020);河北大学高层次人才科研启动项目(521100222002);复杂能源系统智能计算教育部工程研究中心开放基金(ESIC202101)

Multi-temporal Hyperspectral Anomaly Change Detection Based on Dual Space Conjugate Autoencoder

LI Shasha1, XING Hongjie1, LI Gang2,3   

  1. 1 Hebei Key Laboratory of Machine Learning, Computational Intelligence, College of Mathematics, Information Science, Hebei University, Baoding, Hebei 071002, China
    2 Department of Computer,North China Electric Power University,Baoding,Hebei 071003,China
    3 Engineering Research Center of Intelligent Computing for Complex Energy Systems,Baoding,Hebei 071003,China
  • Received:2022-11-14 Revised:2023-02-15 Online:2023-12-15 Published:2023-12-07
  • About author:LI Shasha,born in 1996,postgraduate.Her main research interests include novelty detection,autoencoder and deep learning.
    XING Hongjie,born in 1976,Ph.D,professor,Ph.D supervisor.His main research interests include kernel me-thods,neural networks,novelty detection,and ensemble learning.
  • Supported by:
    National Natural Science Foundation of China(61672205),Natural Science Foundation of Hebei Province,China(F2017201020),High-Level Talents Research Start-up Project of Hebei University(521100222002) and Open Foundation of Engineering Research Center of Intelligent Computing for Complex Energy Systems(ESIC202101).

PDF (PC)

2033

摘要： 高光谱异常变化检测能够从多时相高光谱遥感图像中寻找到数量稀少、与整体背景变化趋势不同、难以发现且令人感兴趣的异常变化。数据集规模较小、存在噪声干扰以及线性预测模型存在局限性等问题,极大地降低了传统高光谱异常变化检测方法的检测性能。目前,自编码器已被成功地应用于高光谱异常变化检测。然而,单个自编码器在处理多时相高光谱图像时,仅关注图像的重构质量,在获取瓶颈特征时往往忽略了图像中复杂的光谱变化信息。为了解决该问题,提出了一种基于双空间共轭自编码器的多时相高光谱异常变化检测(Multi-temporal Hyperspectral Anomaly Change Detection Based on Dual Space Conjugate Autoencoder,DSCAE)方法。所提方法包含两个共轭的自编码器,即它们从不同方向构造各自的潜在特征。在该方法的训练过程中,首先,两幅不同时刻的高光谱图像经过各自的编码器分别获得相应的潜在空间特征表示,再分别经过各自的解码器获得另一时刻的预测图像;其次,在样本空间和潜在空间中施加不同的约束条件,并在两个空间中最小化相应的损失函数;最后,两幅输入图像经过共轭自编码器后获得各自的异常损失图,对所得的两幅异常损失图采用取小运算得到最终的异常变化强度图,以便在减小输入图像间背景光谱差异的同时突出异常变化。在高光谱异常变化检测基准数据集上的实验结果表明,与10种相关方法相比,DSCAE展现了更优的检测性能。

关键词: 高光谱图像异常变化检测, 自编码器, 深度学习, 异常检测, 多时相高光谱图像

Abstract: Hyperspectral anomaly change detection can find anomaly changes from multi-temporal hyperspectral remote sensing images.These anomaly changes are rare,different from the overall background change trend,difficult to be found,but very intere-sting.For the problems of small-sized data sets,existing noise disturbance,and limitation of linear prediction models,the detection performance of the conventional hyperspectral anomaly change detection methods are greatly degraded.At present,Autoencoder has been successfully applied to hyperspectral anomaly change detection.However,when processing multi-temporal hyperspectral images,a single autoencoder only focuses on the reconstruction quality of images,while usually ignores the complex spectral changes in these images as it obtains bottleneck features.To tackle this problem,the multi-temporal hyperspectral anomaly change detection based on dual space conjugate Autoencoder(DSCAE) method is proposed.The proposed method contains two conjugate autoencoders that construct their own latent features from different directions.In the training process of the proposed method,first,two hyperspectral images at different times respectively obtain their corresponding feature representation in the latent space by their encoders.Then,the predicted image at another time can be obtained by their decoders.Second,different constraints are imposed in the sample space and the latent space,respectively.Moreover,the corresponding loss functions are minimized in the two spaces.Finally,the anomaly loss maps are obtained by the conjugate autoencoders for the two images.The minimization operation is conducted on the two obtained anomaly loss maps to derive the final anomaly change intensity maps to simultaneously decrease the background spectral difference between the two input images and highlight anomaly changes.Experimental results on the benchmark data sets for the hyperspectral anomaly change detection demonstrate that DSCAE achieves better detection performance in comparison with its 10 pertinent methods.

Key words: Hyperspectral image anomaly change detection, Autoencoder, Deep learning, Anomaly detection, Multi-temporal hyperspectral images

中图分类号: 

  • TP391.4
[1]FANG L,LIU G,LI S,et al.Hyperspectral Image Classification with Squeeze Multibias Network[J].IEEE Transactions on Geoscience and Remote Sensing,2018,57(3):1291-1301.
[2]WANG Q,YUAN Z,DU Q,et al.GETNET:A General end-to-end 2-D CNN Framework for Hyperspectral Image Change Detection[J].IEEE Transactions on Geoscience and Remote Sen-sing,2018,57(1):3-13.
[3]STEIN D W J,BEAVEN S G,HOFF L E,et al.Anomaly Detection from Hyperspectral Imagery[J].IEEE Signal Processing Magazine,2002,19(1):58-69.
[4]CAMPS-VALLS G,TUIA D,BRUZZONE L,et al.Advances in Hyperspectral Image Classification:Earth Monitoring with Statistical Learning Methods[J].IEEE Signal Processing Magazine,2013,31(1):45-54.
[5]FAUVEL M,TARABALKA Y,BENEDIKTSSON J A,et al.Advances in Spectral-spatial Classification of Hyperspectral Images[J].Proceedings of the IEEE,2012,101(3):652-675.
[6]SINGH A.Review Article Digital Change Detection Techniques using Remotely-sensed Data[J].International Journal of Remote Sensing,1989,10(6):989-1003.
[7]LU D,MAUSEL P,BRONDIZIO E,et al.Change DetectionTechniques[J].International Journal of Remote Sensing,2004,25(12):2365-2401.
[8]COPPIN P,JONCKHEERE I,NACKAERTS K,et al.Review Article Digital Change Detection Methods in Ecosystem Monitoring:A Review[J].International Journal of Remote Sensing,2004,25(9):1565-1596.
[9]EISMANN M T,MEOLA J,STOCKER A D,et al.Airborne Hyperspectral Detection of Small Changes[J].Applied Optics,2008,47(28):27-45.
[10]RESTA S,ACITO N,DIANI M,et al.Detection of Small Changes in Airborne Hyperspectral Imagery:Experimental Results over Urban Areas[C]//2011 6th International Workshop on the Analysis of Multi-temporal Remote Sensing Images (Multi-Temp).Trento:IEEE,2011:5-8.
[11]ACITO N,DIANI M,ROSSI A,et al.Hyperspectral Anomalous Change Detection in the Presence of Non-stationary Atmosphe-ric/Illumination Conditions[C]//Image and Signal Processing for Remote Sensing XX.Amsterdam:SPIE,2014:254-263.
[12]WU C,DU B,ZHANG L.Hyperspectral Anomalous ChangeDetection Based on Joint Sparse Representation[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018,146:137-150.
[13]BOVOLO F,BRUZZONE L.A Theoretical Framework for Un-supervised Change Detection Based on Change Vector Analysis in the Polar Domain[J].IEEE Transactions on Geoscience and Remote Sensing,2006,45(1):218-236.
[14]PIEPER M,MANOLAKIS D,COOLEY T,et al.New Insights and Practical Considerations in Hyperspectral Change Detection[C]//2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).Milan:IEEE,2015:4161-4164.
[15]DU Q,YOUNAN N,KING R.Change Analysis for Hyperspectral Imagery[C]//2007 International Workshop on the Analysis of Multi-temporal Remote Sensing Images.Leuven:IEEE,2007:1-4.
[16]SCHAUM A P,STOCKER A.Hyperspectral Change Detection and Supervised Matched Filtering Based on Covariance Equalization[C]//Algorithms and technologies for multispectral,Hyperspectral,and Ultraspectral Imagery X.Orlando:SPIE,2004:77-90.
[17]MAYER R,BUCHOLTZ F,SCRIBNER D.Object Detection by Using “Whitening/Dewhitening” to Transform Target Signatures in Multitemporal Hyperspectral and Multispectral Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(5):1136-1142.
[18]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImagenetClassification with Deep Convolutional Neural Networks[J].Communications of the ACM,2017,60(6):84-90.
[19]LECUN Y,BENGIO Y,HINTON G.Deep Learning[J].Na-ture,2015,521(7553):436-444.
[20]ZARE A,JIAO C,GLENN T.Discriminative Multiple Instance Hyperspectral Target Characterization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,40(10):2342-2354.
[21]JIANG K,XIE W,LI Y,et al.Semi-supervised Spectral Lear-ning with Generative Adversarial Network for Hyperspectral Anomaly Detection[J].IEEE Transactions on Geoscience and Remote Sensing,2020,58(7):5224-5236.
[22]XIE W,LIU B,LI Y,et al.Autoencoder and Adversarial-lear-ning-based semi-supervised Background Estimation for Hyperspectral Anomaly Detection[J].IEEE Transactions on Geo-science and Remote Sensing,2020,58(8):5416-5427.
[23]BARLOW H B.Unsupervised Learning[J].Neural Computa-tion,1989,1(3):295-311.
[24]HINTON G E,SALAKHUTDINOV R R.Reducing the Dimensionality of Data with Neural Networks[J].Science,2006,313(5786):504-507.
[25]NOH H,JU J,SEO M,et al.Unsupervised Change Detection Based on Image Reconstruction Loss[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans:IEEE,2022:1352-1361.
[26]LEI J,LI M,XIE W,et al.Spectral Mapping with Adversarial Learning for Unsupervised Hyperspectral Change Detection[J].Neurocomputing,2021,465:71-83.
[27]HU M,WU C,ZHANG L,et al.Hyperspectral Anomaly Change Detection Based on Autoencoder[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2021,14:3750-3762.
[28]ROBBINS H,MONRO S.A Stochastic Approximation Method[J].The Annals of Mathematical Statistics,1951,22(3):400-407.
[29]WU C,DU B,ZHANG L.Slow Feature Analysis for Change Detection in Multispectral Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2013,52(5):2858-2874.
[30]WU C,ZHANG L,DU B.Hyperspectral Anomaly Change Detection with Slow Feature Analysis[J].Neurocomputing,2015,151(1):175-187.
[31]ACITO N,MATTEOLI S,ROSSI A,et al.Hyperspectral Airborne “Viareggio 2013 Trial” Data Collection for Detection Algorithm Assessment[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(6):2365-2376.
[32]HE K,ZHANG X,REN S,et al.Delving Deep into Rectifiers:Surpassing Human-level Performance on Imagenet Classification[C]//Proceedings of the IEEE International Conference on Computer Vision.Santiago:IEEE,2015:1026-1034.
[33]KINGMA D P,BA J.Adam:A Method for Stochastic Optimization[C]//International Conference on Learning Representations.San Diego:IEEE,2015:1-15.
[34]NIELSEN A A,CONRADSEN K,SIMPSON J J.Multivariate Alteration Detection (MAD) and MAF Postprocessing in Multispectral,Bitemporal Image Data:New Approaches to Change Detection Studies[J].Remote Sensing of Environment,1998,64(1):1-19.
[35]NIELSEN A A.The Regularized Iteratively Reweighted MAD Method for Change Detection in Multi-and Hyperspectral Data[J].IEEE Transactions on Image processing,2007,16(2):463-478.
[36]HOU Z,LI W,LI L,et al.Hyperspectral Change DetectionBased on Multiple Morphological Profiles[J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-12.
[37]DU P,LIU S,GAMBA P,et al.Fusion of Difference Images for Change Detection over Urban Areas[J].IEEE Journal of Selec-ted Topics in Applied Earth Observations and Remote Sensing,2012,5(4):1076-1086.
[38]CLIFTON C.Change Detection in Overhead Imagery UsingNeural Networks[J].Applied Intelligence,2003,18(2):215-234.
[39]CHEN H,QI Z,SHI Z.Remote Sensing Image Change Detection with Transformers[J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-14.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发