Anterior|Siguiente

A modified correlation alignment algorithm for the domain adaptation of GF-5 hyperspectral image

  • role： First author第一作者
  • Affiliation：

    Hubei Key Laboratory of Applied Mathematics, Facultyof Mathematicsand Statistics, Hubei University, Wuhan 430062， China

  • Email：pengjt1982@hubu.edu.cn
  • Introduction： 彭江涛, 1982年生， 男, 教授, 研究方向为高光谱图像处理。E-mail: pengjt1982@hubu.edu.cn
PENG Jiangtao1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Department of Geography and Spatial Information Techniques, Ningbo University, 818 Fenghua Road, Ningbo 315211， China

  • Email：sunweiwei@nbu.edu.cn
  • Introduction： 孙伟伟, 1985年生， 男, 教授, 研究方向为地理信息系统、遥感理论和方法。E-mail: sunweiwei@nbu.edu.cn
SUN Weiwei2*,  
  • Affiliation：

    Hubei Key Laboratory of Applied Mathematics, Facultyof Mathematicsand Statistics, Hubei University, Wuhan 430062， China

WEI Tianhui1,  
  • Affiliation：

    Hubei Key Laboratory of Applied Mathematics, Facultyof Mathematicsand Statistics, Hubei University, Wuhan 430062， China

FAN Wenqi1

resumen

GF-5 is the first full-spectrum hyperspectral satellite used to achieve comprehensive observations of the atmosphere and land. The hyperspectral sensors on the GF-5 have high spectral resolution and wide coverage. However, labeling all the materials on these wide ranges is extremely difficult in practical applications. Hyperspectral classification is extremely difficult when the number of labeled samples is limited or no labeled sample is available. In this study, we aim to present an effective unsupervised domain adaptation technique that uses labeled pixels in the existing old domain(source domain)to classify the scenes with limited or no labeled pixels (target domain).Correlation alignment (CORAL) is a simple and effective domain adaptation method. However, the covariance computation in CORAL may be inaccurate in the case of limited training samples.We propose a new CORAL algorithm on the basis of a sparse matrix transform technique (CORAL-SMT) to solve this problem. The proposed method first uses the sparse matrix transform technique to estimate the covariance matrices of the source and target domains and then performs the CORAL between the estimated covariance matrices. The SMT method can obtain an accurate covariance estimator, which is constantly positive and definite.In the experiment, we compare the proposed CORAL-SMT with some classical domain adaptation methods, such as subspace alignment, principal component analysis, CORAL, transfer component analysis, geodesic flow kernel, and information the oretical learning. After domain adaptation, we use the nearest neighbor and support vector machine as classifiers to classify the unlabeled data in the target domain. Two GF-5 hyperspectral datasets, namely, Huanghekou and Yancheng datasets, are used to evaluate the performance of different methods. Experimental results demonstrate the effectiveness of the proposed method compared with subspace-based alignment methods and CORAL.The GF-5 data have good spectral discriminative ability. In the case of bias sampling, the performance of classifying the target samples on the basis of the source model is acceptable. The distribution difference between source and target domains is decreased, and the classification performance is intensively improved using the domain adaptation technique. The SMT technique can improve the covariance estimation,thereby benefiting the following domain adaptation.

palabra clave

remote sensing;GF-5 satellite;hyperspectral image;domain adaptation;classification;correlation alignment;sparse matrix transform

References

  1. 1.
    Bioucas-Dias J M, Plaza A, Camps-Valls G, Scheunders P, Nasrabadi N, and Chanussot J . 2013.Hyperspectralremote sensing data analysis and future challenges. IEEE Geoscience and Remote Sensing Magazine, 1(2): 6-36
  2. 2.
    Bruzzone L, Chi M and Marconcini M . 2006.A novel transductive SVM for semisupervised classification of remote-sensing images.IEEE Transactions on Geoscience and Remote Sensing, 44(11): 3363-3373
  3. 3.
    Bruzzone L and Prieto D F . 2001.Unsupervised retraining of a maximum-likelihood classifier for the analysis of multitemporal remote-sensing images.IEEE Transactions on Geoscience and Remote Sensing, 39(2): 456-460
  4. 4.
    Cao G Z, Bachega L R and Bouman C A . 2011.The sparse matrix transform for covariance estimation and analysis of high dimensionalsignals. IEEE Transactions on Image Processing, 20(3): 625-640
  5. 5.
    Cao G Z and Bouman C A . 2009.Covariance estimation for high dimensional data vectors using the sparsematrix transform//Proceedings of the 21st International Conference on Neural Information Processing Systems. Red Hook, NY. NIPS,: ACM:225-232
  6. 6.
    Fernando B, Habrard A, Sebban M and Tuytelaars T . 2013.Unsupervised visual domain adaptation using subspace alignment//Proceedings of 2013 IEEE International Conference on Computer Vision， ICCV. Sydney, NSW, Australia: IEEE:2960-2967 [DOI: 10.1109/ICCV.2013.368]
  7. 7.
    Gong B Q, Shi Y, Sha F and Grauman K . 2012. Geodesic flow kernel for unsupervised domain adaptation//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA， CVPR,: IEEE:2066-2073 [DOI: 10.1109/CVPR.2012.6247911]
  8. 8.
    Hoffbeck J P and Landgrebe D A . 1996.Covariance matrix estimation andclassification with limited training data.IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(7): 763-767
  9. 9.
    Izquierdo-Verdiguier E, Laparra V, Góomez-Chova L and Camps-Valls G . 2013. Encoding invariances in remote sensing image classification with SVM.IEEE Geoscience and Remote Sensing Letters, 10(5): 981-985
  10. 10.
    Long M S, Wang J M, Ding G G, Sun J G and Yu P S . 2013. Transfer feature learning with joint distribution adaptation//Proceedings of 2013 IEEE International Conference on Computer Vision. Sydney, NSW, Australia， ICCV: IEEE:2200-2207 [DOI: 10.1109/ICCV.2013.274]
  11. 11.
    Ma L, Crawford M M, Zhu L and Liu Y . 2019.Centroid and covariance alignment-based domain adaptation for unsupervised classification of remote sensing images.IEEE Transactions on Geoscience and Remote Sensing, 57(4): 2305-2323
  12. 12.
    Pan S J, Tsang I W, Kwok J T and Yang Q . 2011.Domain adaptation via transfer componentanalysis.IEEE Transactions on Neural Networks, 22(2): 199-210
  13. 13.
    Peng J T and Luo T . 2016.Sparse matrix transform-based linear discriminant analysis for hyperspectral image classification.Signal, Image and Video Processing, 10(4): 761-768
  14. 14.
    Peng J T, Sun W W, Ma L and Du Q . 2019.Discriminative transfer joint matching for domain adaptation in hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 16(6): 972-976
  15. 15.
    Persello C and Bruzzone L . 2016.Kernel-based domain -invariant feature selection in hyperspectral images for transfer learning. IEEE Transactions on Geoscience and Remote Sensing, 54(5): 2615-2626
  16. 16.
    Shi Y and Sha F . 2012.Information-theoretical learning of discriminative clusters for unsupervised domain adaptation//Proceedings of the 29th International Conference on International Conference on Machine Learning. Madison, WI， ICML, USA: ACM: 1275-1282.
  17. 17.
    Sun B C, Feng J S and Saenko K . 2016. Return of， frustratingly easy domain adaptation//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix Convention Center, Phoenix, Arizona, USA: IEEE: 2058-2065
  18. 18.
    Sun H, Liu S, Zhou S L, and Zou H X . 2016. Unsupervised cross-view semantic transfer for remote sensing image classification.IEEE Geoscience and Remote Sensing Letters, 13(1): 13-17
  19. 19.
    Theiler J, Cao G Z, Bachega L R and Bouman C A . 2011.Sparse matrix transform for hyperspectral image processing. IEEE Journal of Selected Topics in Signal Processing, 5(3): 424-437
  20. 20.
    Tong Q X, Zhang B and Zhang L F . 2016. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 20(5): 689-707
  21. 21.
    Tuia D, Persello C and Bruzzone L . 2016.Domain adaptation for the classification of remote sensing data: an overview of recent advances. IEEE Geoscience and Remote Sensing Magazine, 4(2): 41-57
  22. 22.
    Zhang L P and Li J Y . 2016.Development and prospect of sparse representation-based hyperspectral image processing and analysis.Journal of Remote Sensing, 20(5): 1091-1101.

Leer el texto completo

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website