Hyperspectral Change Detection Using Collaborative Sparsity and Nonlocal Low-Rank Tensor

doi:10.3778/j.issn.1673-9418.2009009

Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (2): 448-457.DOI: 10.3778/j.issn.1673-9418.2009009

• Graphics and Image • Previous Articles Next Articles

Hyperspectral Change Detection Using Collaborative Sparsity and Nonlocal Low-Rank Tensor

ZHAN Tianming¹^,², SONG Bo¹^,⁺(), SUN Le³, WAN Minghua¹, YANG Guowei¹

1. School of Information Engineering, Nanjing Audit University, Nanjing 211815, China
2. Collaborative Innovation Center of Audit Information Engineering and Technology, Nanjing Audit University, Nanjing 211815, China
3. School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210094, China

Received:2020-09-04 Revised:2020-11-20 Online:2022-02-01 Published:2020-12-09
About author:ZHAN Tianming, born in 1984, Ph.D., associate professor, M.S. supervisor. His research interests include hyperspectral image processing and deep learning.
SONG Bo, born in 1997, M.S. candidate. His research interest is hyperspectral image processing.
SUN Le, born in 1987, Ph.D., associate professor, M.S. supervisor. His research interest is hyper-spectral image processing.
WAN Minghua, born in 1978, Ph.D., associate professor, M.S. supervisor. His research interests include pattern recognition and data processing.
YANG Guowei, born in 1964, Ph.D., professor, M.S. supervisor. His research interests include artificial intelligence and big data.
Supported by:
National Natural Science Foundation of China(61976117);National Natural Science Foundation of China(61876213);Natural Science Foundation of Jiangsu Province(BK20191409);Key Projects of University Natural Science Fund of Jiangsu Province(19KJA360001);Key Projects of University Natural Science Fund of Jiangsu Province(18KJA520005);Project of Collaborative Innovation Center of Audit Information Engineering and Technology(18CICA09);Cultivation Project of Nanjing Audit University(18QNPY015);Postgraduate Research and Practice Innovation Program of Jiangsu Province(KYCX20_1680)

高光谱协同稀疏与非局部低秩张量变化检测

詹天明¹^,², 宋博¹^,⁺(), 孙乐³, 万鸣华¹, 杨国为¹

1.南京审计大学信息工程学院,南京 211815
2.南京审计大学审计信息工程与技术协同创新中心,南京 211815
3.南京信息工程大学计算机学院,南京 210094

通讯作者: + E-mail: mg1909003@stu.nau.edu.cn
作者简介:詹天明（1984—）,男,江苏高邮人,博士,副教授,硕士生导师,主要研究方向为高光谱图像处理、深度学习。
宋博（1997—）,男,江苏南京人,硕士研究生,主要研究方向为高光谱图像处理。
孙乐（1987—）,男,江苏洋河人,博士,副教授,硕士生导师,主要研究方向为高光谱图像处理。
万鸣华（1978—）,男,江西南昌人,博士,副教授,硕士生导师,主要研究方向为模式识别、数据处理。
杨国为（1964—）,男,江西樟树人,博士,教授,硕士生导师,主要研究方向为人工智能、大数据。
基金资助:
国家自然科学基金面上项目(61976117);国家自然科学基金面上项目(61876213);江苏省自然科学基金面上项目(BK20191409);江苏省高校自然科学研究重大项目(19KJA360001);江苏省高校自然科学研究重大项目(18KJA520005);审计信息工程与技术协同创新中心2018年度研究课题(18CICA09);南京审计大学青年教师科研培育项目(18QNPY015);江苏省研究生科研与实践创新计划项目(KYCX20_1680)

Abstract

Abstract:

Hyperspectral image change detection can provide timely change information on the surface of the earth, which is essential for urban and rural planning and management. Due to the higher spectral resolution, hyperspectral images are often used to detect finer changes. Aiming at the problem of change detection by using hyperspectral image, a hyperspectral change detection method based on collaborative sparsity and nonlocal low-rank tensor is proposed. This method first obtains hyperspectral differential image at different time points, and then extracts different nonlocal similar block tensor clusters according to the nonlocal distribution characteristics of the image blocks in the differential image. Then, based on collaborative sparse regularization and low-rank regularization, a change detection model using collaborative sparsity and non-local low-rank tensor is established, and the representa-tion coefficient is obtained by solving the model using the alternating direction method of multipliers. Finally, the projection residuals of the tensor in different categories are obtained according to the representation coefficients, and then the projection residual minimization criterion is judged whether the tensor has changed. Experiments on Farm-land and Urban area in San Francisco City datasets demonstrate that the proposed method can achieve much better changes detection accuracy.

Key words: hyperspectral, change detection, collaborative sparsity, non-local low-rank, tensor decomposition

摘要：

高光谱图像变化检测可提供地球表面的时间维变化信息,对城乡规划和管理至关重要。因具有较高的光谱分辨率,高光谱图像常被用于检测更精细的变化。针对高光谱变化检测的问题,提出一种基于协同稀疏与非局部低秩张量的高光谱图像变化检测方法。该方法首先求得前后时间点的高光谱差分图像,再根据差分图像中图像块的非局部分布特点,提取不同的非局部张量簇。然后基于协同稀疏正则化和低秩正则化建立协同稀疏与非局部低秩张量变化检测模型,并采用交替方向乘子法对模型求解得到表示系数。最后根据表示系数求得张量在不同类别中的投影残差,进而根据投影残差最小准则判断该张量块是否发生变化。在Farm-land数据集和Urban area in San Francisco City数据集上进行实验,实验结果表明该方法取得较好的高光谱变化检测精度。

关键词: 高光谱, 变化检测, 协同稀疏, 非局部低秩, 张量分解

CLC Number:

TP391

ZHAN Tianming, SONG Bo, SUN Le, WAN Minghua, YANG Guowei. Hyperspectral Change Detection Using Collaborative Sparsity and Nonlocal Low-Rank Tensor[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(2): 448-457.

詹天明, 宋博, 孙乐, 万鸣华, 杨国为. 高光谱协同稀疏与非局部低秩张量变化检测[J]. 计算机科学与探索, 2022, 16(2): 448-457.

Figures/Tables 11

References 27

[1]	董燕妮, 杜博, 张乐飞, 等. 基于局域自适应信息理论测度学习的高光谱目标探测方法[J]. 武汉大学学报(信息科学版), 2018, 43(8):1271-1277.
	DONG Y N, DU B, ZHANG L F, et al. Hyperspectral target detection based on locally adaptive information-theoretic metric learning method[J]. Geomatics and Information Science of Wuhan University, 2018, 43(8):1271-1277.
[2]	佟国峰, 李勇, 丁伟利, 等. 遥感影像变化检测算法综述[J]. 中国图象图形学报, 2015, 20(12):1561-1571.
	TONG G F, LI Y, DING W L, et al. Review of remote sensing image change detection[J]. Journal of Image and Graphics, 2015, 20(12):1561-1571.
[3]	LUO F, DU B, ZHAN G L, et al. Feature learning using spatial-spectral hypergraph discriminant analysis for hyper-spectral image[J]. IEEE Transactions on Cybernetics, 2019, 49(7):2406-2419. DOI URL
[4]	ZHANG L F, ZHANG L P, DU B, et al. Hyperspectral image unsupervised classification by robust manifold matrix factori-zation[J]. Information Sciences, 2019, 485:154-169. DOI URL
[5]	ZHANG L F, ZHANG Q, DU B, et al. Simultaneous spectral-spatial feature selection and extraction for hyperspectral images[J]. IEEE Transactions on Cybernetics, 2018, 48(1):16-28. DOI URL
[6]	MALILA W A. Change vector analysis: an approach for detecting forest changes with landsat[C]//Proceedings of the 1980 Machine Processing of Remotely Sensed Data Symposium, Jun 3-6, 1980. Piscataway: IEEE, 1980: 326-335.
[7]	BAISANTRY M, NEGI D S, MANOCHA O P. Change vector analysis using enhanced PCA and inverse triangular function-based thresholding[J]. Defence Science Journal, 2012, 62(4):236-242. DOI URL
[8]	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. DOI URL
[9]	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. DOI URL
[10]	BOVOLO F, MEMBER S, BRUZZONE L. A framework for automatic and unsupervised detection of multiple changes in multitemporal images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(6):2196-2212. DOI URL
[11]	NEMMOUR H, CHIBANI Y. Multiple support vector machines for land cover change detection: an application for mapping urban extensions[J]. IEEE Journal of Photog-rammetry & Remote Sensing, 2007, 61(2):125-133.
[12]	WANG Q, YUAN Z H, 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 Sensing, 2019, 57(1):3-13. DOI URL
[13]	AN J L, ZHANG X R, JIAO L C. Dimensionality reduction based on group-based tensor model for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(10):1497-1501. DOI URL
[14]	LI X T, NG M K, CONG G, et al. MR-NTD: manifold regularization nonnegative tucker decomposition for tensor data dimension reduction and representation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(8):1787-1800. DOI URL
[15]	SUN L, WU F Y, ZHAN T M, et al. Weighted nonlocal low-rank tensor decomposition method for sparse unmixing of hyperspectral images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13:1174-1188. DOI URL
[16]	XIONG F C, QIAN Y T, ZHOU J, et al. Hyperspectral unmixing via total variation regularized nonnegative tensor factorization[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(4):2341-2357. DOI URL
[17]	YANG L X, WANG M, YANG S Y, et al. Hybrid proba-bilistic sparse coding with spatial neighbor tensor for hyper-spectral imagery classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(5):2491-2502. DOI URL
[18]	SUN W W, YANG G, PENG J T, et al. Lateral-slice sparse tensor robust principal component analysis for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(1):107-111. DOI URL
[19]	LIU J J, WU Z B, XIAO L, et al. Generalized tensor regression for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(2):1244-1258. DOI URL
[20]	QIN Y, BRUZZONE L, LI B. Tensor alignment based domain adaptation for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(11):9290-9307. DOI URL
[21]	XU Y, WU Z B, CHANUSSOT J, et al. Nonlocal patch tensor sparse representation for hyperspectral image super-resolution[J]. IEEE Transactions on Image Processing, 2019, 28(6):3034-3047. DOI URL
[22]	KANATSOULIS C I, FU X, SIDIROPOULOS N D, et al. Hyperspectral super-resolution: a coupled tensor factorization approach[J]. IEEE Transactions on Signal Processing, 2018, 66(24):6503-6517. DOI URL
[23]	LI J, LIU X, YUAN Q, et al. Antimoise hyperspectral image fusion by mining tensor low-multilinear-rank and variational properties[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(10):7832-7848. DOI URL
[24]	DABOV K, FOI A, KATKOVNIK V, et al. Image denoising by sparse 3-D transform-domain collaborative filtering[J]. IEEE Transactions on Image Processing, 2007, 16(8):2080-2095. DOI URL
[25]	刘建军, 吴泽彬, 韦志辉, 等. 基于约束非负矩阵分解的高光谱图像解混快速算法[J]. 电子学报, 2013, 41(3):432-437. DOI
	LIU J J, WU Z B, WEI Z H, et al. Fast algorithm for hyperspectral image unmixing based on constrained non-negative matrix decomposition[J]. Acta Electronica Sinica, 2013, 41(3):432-437.
[26]	ZHANG L P, ZHANG L F, DU B. Deep learning for remote sensing data: a technical tutorial on the state of the art[J]. IEEE Geoscience and Remote Sensing Magazine, 2016, 4(2):22-40. DOI URL
[27]	ZHENG Y H, WU F Y, SHIM H J, et al. Sparse unmixing for hyperspectral image with nonlocal low-rank prior[J]. Remote Sensing, 2019, 11(24):2897. DOI URL

数据集	3×3	5×5	7×7
Farmland	0.981 5	0.981 0	0.976 4
UASFC1	0.986 0	0.982 6	0.979 5
UASFC2	0.994 5	0.992 0	0.983 6

数据集	3×3	5×5	7×7
Farmland	0.981 5	0.981 0	0.976 4
UASFC1	0.986 0	0.982 6	0.979 5
UASFC2	0.994 5	0.992 0	0.983 6

方法		指标	数据集
方法		指标	Farmland	UASFC1	UASFC2
SVM^[11]		OA	0.937 6	0.942 4	0.881 0
		Kappa	0.848 3	0.706 6	0.684 8
		时间/s	504	99	16
CNN^[26]		OA	0.918 5	0.913 9	0.890 2
		Kappa	0.794 9	0.558 5	0.669 9
		时间/s	931	449	137
GETNET^[12]		OA	0.975 3	0.949 9	0.943 0
		Kappa	0.939 4	0.747 2	0.824 9
		时间/s	515	268	82
NLLRSU^[27]		OA	0.955 5	0.941 5	0.951 5
		Kappa	0.896 0	0.710 5	0.797 0
		时间/s	3 517	1 439	409
GTR^[19]		OA	0.980 5	0.969 2	0.963 0
		Kappa	0.953 2	0.845 6	0.831 0
		时间/s	62	46	15
本文方法	CST	OA	0.971 2	0.972 5	0.981 9
		Kappa	0.931 5	0.844 7	0.919 1
		时间/s	1 628	634	203
	CSNLRT	OA	0.981 5	0.986 0	0.994 5
		Kappa	0.959 0	0.939 0	0.978 4
		时间/s	3 426	1 328	394

方法		指标	数据集
方法		指标	Farmland	UASFC1	UASFC2
SVM^[11]		OA	0.937 6	0.942 4	0.881 0
		Kappa	0.848 3	0.706 6	0.684 8
		时间/s	504	99	16
CNN^[26]		OA	0.918 5	0.913 9	0.890 2
		Kappa	0.794 9	0.558 5	0.669 9
		时间/s	931	449	137
GETNET^[12]		OA	0.975 3	0.949 9	0.943 0
		Kappa	0.939 4	0.747 2	0.824 9
		时间/s	515	268	82
NLLRSU^[27]		OA	0.955 5	0.941 5	0.951 5
		Kappa	0.896 0	0.710 5	0.797 0
		时间/s	3 517	1 439	409
GTR^[19]		OA	0.980 5	0.969 2	0.963 0
		Kappa	0.953 2	0.845 6	0.831 0
		时间/s	62	46	15
本文方法	CST	OA	0.971 2	0.972 5	0.981 9
		Kappa	0.931 5	0.844 7	0.919 1
		时间/s	1 628	634	203
	CSNLRT	OA	0.981 5	0.986 0	0.994 5
		Kappa	0.959 0	0.939 0	0.978 4
		时间/s	3 426	1 328	394

Hyperspectral Change Detection Using Collaborative Sparsity and Nonlocal Low-Rank Tensor

高光谱协同稀疏与非局部低秩张量变化检测

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 27

Related Articles 4

Recommended Articles

Metrics

[1]	XU Chao, ZHAN Tianming. Hyperspectral Anomaly Detection Method Based on Low Rank Total Variation Regu-larization [J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(12): 2140-2149.
[2]	HUANG Wei, XU Meng'en, XU Guoming, HUANG Qinchao. Bayesian Sparse Representation for Hyperspectral Image Super Resolution [J]. Journal of Frontiers of Computer Science and Technology, 2018, 12(12): 1987-1995.
[3]	ZHANG Juping, GAO Guanglai, SU Xiangdong. Fusion Spectral Filter in Deep Feature Learning Net on Hyperspectral Image Classification [J]. Journal of Frontiers of Computer Science and Technology, 2018, 12(11): 1806-1814.
[4]	WU Hao¹, LI Shijin¹⁺, LIN Lin², WAN Dingsheng¹. Multiple-strategy Combination Based Approach to Band Selection for Hyper-spectral Image Classification* [J]. Journal of Frontiers of Computer Science and Technology, 2010, 4(5): 464-472.