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

Jiangtao PENG; Weiwei SUN; Tianhui WEI; Wenqi FAN

doi:10.11834/jrs.20209212

Views : 0 下载量: 251 CSCD: 3 更多指标

PDF
Export
Share
Collection
Album

A modified correlation alignment algorithm for the domain adaptation of GF-5 hyperspectral image
Vol. 24, Issue 4, Pages: 417-426(2020)
Published： 07 April 2020 ，
DOI： 10.11834/jrs.20209212

扫描看全文

彭江涛,孙伟伟,魏天慧,范文琦.2020.高分五号高光谱影像的关联对齐域适应与分类.遥感学报,24(4): 417-426

PENG Jiangtao,SUN Weiwei,WEI Tianhui,FAN Wenqi. 2020. A modified correlation alignment algorithm for the domain adaptation of GF-5 hyperspectral image. Journal of Remote Sensing(Chinese). 24(4): 417-426
彭江涛,孙伟伟,魏天慧,范文琦.2020.高分五号高光谱影像的关联对齐域适应与分类.遥感学报,24(4): 417-426 DOI： 10.11834/jrs.20209212.

PENG Jiangtao,SUN Weiwei,WEI Tianhui,FAN Wenqi. 2020. A modified correlation alignment algorithm for the domain adaptation of GF-5 hyperspectral image. Journal of Remote Sensing(Chinese). 24(4): 417-426 DOI： 10.11834/jrs.20209212.

摘要

高分五号（GF-5）搭载的高光谱传感器兼顾宽覆盖和高分辨率的特性

但在实际应用中宽覆盖范围内各种地物类别的标注十分困难。当标记样本很少甚至没有标记样本时，遥感图像分类异常困难。此时，可以采用域适应方法，借助已标记的历史数据（源域）实现对未标记数据（目标域）的分类。本文提出了一种基于稀疏矩阵变换的关联对齐域适应分类算法。首先，利用稀疏矩阵变换估计源域和目标域的协方差矩阵；然后，运用协方差关联对齐方法估计源域到目标域的变换矩阵；接着，运用估计得到的变换矩阵将源域数据进行变换，使得其与目标域对齐；最后，在变换后的源域数据上建立分类器，实现对目标域数据的分类。本文的算法在两个真实的GF-5高光谱数据集上进行了验证。实验结果表明，本文算法要优于常用的子空间对齐算法和关联对齐算法。特别地，在黄河口GF-5数据上，本文算法比原始关联对齐方法的最近邻分类准确率提升了3.5%，支持向量机分类准确率提升了2.3%。

Abstract

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.

关键词

遥感高分五号高光谱图像域适应分类关联对齐法稀疏矩阵变换

Keywords

remote sensingGF-5 satellitehyperspectral imagedomain adaptationclassificationcorrelation alignmentsparse matrix transform

references

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 [DOI: 10.1109/MGRS.2013.2244672http://dx.doi.org/10.1109/MGRS.2013.2244672 ]

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 [DOI: 10.1109/TGRS.2006.877950http://dx.doi.org/10.1109/TGRS.2006.877950 ]

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 [DOI: 10.1109/36.905255http://dx.doi.org/10.1109/36.905255 ]

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 [DOI: 10.1109/TIP.2010.2071390http://dx.doi.org/10.1109/TIP.2010.2071390 ]

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

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]

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]

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 [DOI: 10.1109/34.506799http://dx.doi.org/10.1109/34.506799 ]

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 [DOI: 10.1109/LGRS.2012.2227297http://dx.doi.org/10.1109/LGRS.2012.2227297 ]

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]

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 [DOI: 10.1109/TGRS.2018.2872850http://dx.doi.org/10.1109/TGRS.2018.2872850 ]

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 [DOI: 10.1109/TNN.2010.2091281http://dx.doi.org/10.1109/TNN.2010.2091281 ]

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 [DOI: 10.1007/s11760-015-0808-yhttp://dx.doi.org/10.1007/s11760-015-0808-y ]

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 [DOI: 10.1109/LGRS.2018.2889789http://dx.doi.org/10.1109/LGRS.2018.2889789 ]

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 [DOI: 10.1109/TGRS.2015.2503885http://dx.doi.org/10.1109/TGRS.2015.2503885 ]

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.

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

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 [DOI: 10.1109/LGRS.2015.2491605http://dx.doi.org/10.1109/LGRS.2015.2491605 ]

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 [DOI: 10.1109/JSTSP.2010.2103924http://dx.doi.org/10.1109/JSTSP.2010.2103924 ]

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

童庆禧, 张兵, 张立福. ,2016. 中国高光谱遥感的前沿进展. 遥感学报, 20(5): 689-707） [DOI: 10.11834/jrs.20166264http://dx.doi.org/10.11834/jrs.20166264 ]

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 [DOI: 10.1109/MGRS.2016.2548504http://dx.doi.org/10.1109/MGRS.2016.2548504 ]

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.

张良培, 李家艺 . 2016. 高光谱图像稀疏信息处理综述与展望. 遥感学报, 20(5): 1091-1101 [DOI: 10.11834/jrs.20166050http://dx.doi.org/10.11834/jrs.20166050 ]

Alert me when the article has been cited

提交

Class-independent domain adaptation for hyperspectral image classification

CNN with local binary patterns for hyperspectral images classification

Hyperspectral remote sensing image classification based on multidirectional adaptive aware network

Hyperspectral unmixing based on adversarial autoencoder network