Computer Science and Information Systems 2023 Volume 20, Issue 2, Pages: 551-572
https://doi.org/10.2298/CSIS220828009L
Full text (
2438 KB)
Adaptive multiscale sparse unmixing for hyperspectral remote sensing image
Li Yalan (Xiangnan University, Chenzhou, China + Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems, Chenzhou, China), liyalan@xnu.edu.cn
Du Qian (Linyi University, Linyi, China), duqian@lyu.edu.cn
Li Yixuan (Hunan Institute of Science and Technology, Yueyang, China), 812011120131-vip@hnist.edu.cn
Xie Wenwu (Hunan Institute of Science and Technology, Yueyang, China), gavinxie@hnist.edu.cn
Yuan Jing (Institute of Disaster Prevention, Beijing, China), yuanjing@sina.com
Li Lin Shang (AF Xiangnan University, Chenzhou, China + Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems, Chenzhou, China), lsl@xnu.edu.cn
Qi Chen (Hubei Normal University, Huangshi, China), chenqi@hbnu.edu.cn
Sparse unmixing of hyperspectral images aims to separate the endmembers and estimate the abundances of mixed pixels. This approach is the essential step for many applications involving hyperspectral images. The multi-scale spatial sparse hyperspectral unmixing algorithm (MUA) could achieve higher accuracy than many state-of-the-art algorithms. The regularization parameters, whose combinations markedly influence the unmixing accuracy, are determined by manually searching in the broad parameter space, leading to time consuming. To settle this issue, the adaptive multi-scale spatial sparse hyperspectral unmixing algorithm (AMUA) is proposed. Firstly, the MUA model is converted into a new version by using of a maximum a posteriori (MAP) system. Secondly, the theories indicating that andnorms are equivalent to Laplacian and multivariate Gaussian functions, respectively, are applied to explore the strong connections among the regularization parameters, estimated abundances and estimated noise variances. Finally, the connections are applied to update the regularization parameters adaptively in the optimization process of unmixing. Experimental results on both simulated data and real hyperspectral images show that the AMUA can substantially improve the unmixing efficiency at the cost of negligible accuracy. And a series of sensitive experiments were undertook to verify the robustness of the AMUA algorithm.
Keywords: adaptive multiscale sparse hyperspectral unmixing algorithm, loss functions, regularization parameters, maximum a posteriori
Show references
Zhang T., Hou M., Zhou T., Liu Z., Cheng W., and Cheng Y.,“Land-use classification via ensemble dropout information discriminative extreme learning machine based on deep convolution feature,”Computer Science and Infomation Systems., vol. 17, no.2, pp.427-443,2020.
Liu H., Li C., and Xu L.,“Dimension Reduction and Classification of Hype special images based on Neural Network Sensitivity Analysis and Multi-instance Learning,”Computer Science and Information Systems . , vol. 16, no.2, pp.443-468,2019.
Cheng, R., Yu, W., Song, Y., Chen, D., Ma, X. and Cheng, Y. Intelligent Safe Driving Methods Based on Hybrid Automata and Ensemble CART Algorithms for Multihigh-Speed Trains[J]. IEEE Transactions on Cybernetics,vol. 49, no.10, pp. 3816-3826,2019.
Liu, G., Chen, X., Zhou, R., Xu, S., Chen, Y.C. and Chen, G. Social learning discrete Particle Swarm Optimization based two-stage X-routing for IC design under Intelligent Edge Computing architecture[J]. Applied Soft Computing. 10, 10721,2021
Liu, G., Zhang, X., Guo, W., Huang, X., Liu, W., Chao, K. and Wang, T. Timing-Aware Layer Assignment for Advanced Process Technologies Considering Via Pillars. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 41, no.6, pp. 1957-1970,2022.
Cheng, H., Wu, L., Li, R., Huang, F., Tu, C. and Yu, Z. Data recovery in wireless sensor networks based on attribute correlation and extremely randomized trees [J]. Journal of Ambient Intelligence and Humanized Computing, vol. 12, no.1, pp245-259,2021.
Liu, G., Zhu, Y., Xu, S., Chen, Y.C. and Tang H. PSO-Based Power-Driven X-Routing Algorithm in Semiconductor Design for Predictive Intelligence of IoT Applications. Applied Soft Computing, 114: 108-114,2022.
Li F. “Low-Rank and Spectral-Spatial Sparse Unmixing for Hyperspectral Remote Sensing imagery,” Wireless Communications and Mobile Computing., vol. 2021, no.1, pp.1-14, 2021.
Yu, Z., Zheng, X., Huang, F., Guo, W., Sun, L. and Yu, Z. A framework based on sparse representation model for time series prediction in smart city[J]. Frontiers of Computer Science, 15(1): 1-13,2021.
Lu, Z., Liu, G. and Wang, S. Sparse neighbor constrained co-clustering via category consistency learning [J]. Knowledge-Based Systems, 201, 105987,2020.
Shen, S., Yang, Y. and Liu, X. Toward data privacy preservation with ciphertext update and key rotation for IoT [J]. Concurrency and Computation: Practice and Experience, e6729. https://doi.org/10.1002/cpe.6729,2021.
Wang, Le et al., “A survey of methods incorporating spatial infomation in image classification and special unmixing,” International Journal of Remote Sensing., vol. 37, no.16, pp.3870-3910, 2016.
Feng, Ruyi et al., “Rolling guidance based scale-aware spatial sparse unmixing for hype spectral remote sensing imagery,” Remote Sensing., vol.9, no. 12 , pp.1218-1221, 2017.
Shi, Zhenwei et al., “Collaborative Sparse Hyperspectral Unmixing Using $ l_ {0} $ Norm,” IEEE Transactions on Geoscience and Remote Sensing., vol. 56, no. 9, pp.5495-5508, 2018.
Ertürk, Alp, Marian-Daniel Iordache, and Antonio Plaza, “Sparse unmixing-based change detection for multitemporal hyperspectral images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing., vol. 9, no.2, pp.708-719, 2015
Qi, Lin et al., “Region-Based Multiview Sparse Hyperspectral Unmixing Incorporating Spectral Library,” IEEE Geoscience and Remote Sensing Letters., vol. 7, no.16, pp.1140-1144, 2019.
Palsson, Burkni et al., “Hyperspectral unmixing using a neutral network autoencoder,” IEEE Access., vol.6, pp.25646-25656, 2018.
Dai, Y., Wang, S., Chen, X., Xu, C. and Guo, W..Generative adversarial networks based on Wasserstein distance for knowledge graph embeddings[J]. Knowledge-Based Systems, 190: 105165,2020.
Li, X. Y., Lin, W., Liu, X., Lin, C., Pai, K. and Chang, J. Completely Independent Spanning Trees on BCCC Data Center Networks with an Application to Fault-Tolerant Routing[J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, vol.33, no.8, pp. 1939-1952,2022.
Iordache, Marian-Daniel, José M. Bioucas-Dias, and Antonio Plaza, “Sparse unmixing of hyperspectral data,” IEEE Transactions on Geoscience and Remote Sensing., vol. 49, no.6, pp.2014-2039,2011.
Iordache, Marian-Daniel, José M. Bioucas-Dias, and Antonio Plaza. “Total variation spatial regularization of sparsse hyperspectral unmixing,” IEEE Transactions on Geoscience and Remote Sensing., vol. 50, no.11, pp.4484-4502, 2012.
Zhang, Shaoquan et al. “Spectral-spatial weighted sparse regression for hyperspectral image unmixing,” IEEE Transactions on Geoscience and Remote Sensing., vol.56, no. 6, pp.3265-3276,2018.
Borsoi, Ricardo Augusto et al. “A fast multiscale Spartial Regularization for Sparse Hyperspectral Unmixing,” IEEE Geoscience and Remote Sensing Letters., vol. 4, no.16, pp.598-602, 2018.
Cheng, Y., Jiang, H., Wang, F., Hua, Y., Feng, D., Guo, W. and Wu, Y. Using High-Bandwidth Networks Efficiently for Fast Graph Computation [J]. IEEE Transactions on Parallel and Distributed Systems, vol.30, no.5, pp. 1170-1183,2019.
Wang, S., Wang, Z., Lim, K. L., Xiao, G. and Guo, W. Seeded random walk for multi-view semi-supervised classification [J]. Knowledge-Based Systems, 222:107016, 2021.
Zhang, H., Li, J. L., Liu, X. M. and Chen, D. Multi-dimensional feature fusion and stacking ensemble mechanism for network intrusion detection [J]. Future Generation Computer Systems, 122: 130-143,2021.
Zhang, Y., Lu, Z. and Wang, S. Unsupervised feature selection via transformed auto-encoder[J]. Knowledge-Based Systems, 215: 106748,2021 .
Fu, Y. G., Ye, J. F., Yin, Z. F., Chen, L., Wang, Y. and Liu, G. Construction of EBRB classifier for imbalanced data based on Fuzzy C-Means clustering[J]. Knowledge-Based Systems, 234: 107590,2021.
Arridge, Simon et al. “Solving inverse problems using data-driven models,” Acta Numerica., vol. 28, pp. 1-174, 2019.
Ren, Dongwei et al. “Simultaneous Fidelity and Regulariization Learning for Image Restoration”., arXiv preprint arXiv:1804.04522 , 2018.
Cao, Chunhong et al. “Hyperspectral Image Denoising via Subspace-Based Nonlocal Low-Rank and Sparse Factorization,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing., vol.3, no.12, pp. 973-988,2019.
Fu, Y. G., Zhuang, J. H., Chen, Y. P., Guo, L. and Wang, Y. A framework for optimizing extended belief rule base systems with improved Ball trees [J]. Knowledge-Based Systems, 210: 106484,2020.
Liu, G., Chen, Z., Zhuang, Z., Guo, W. and Chen, G. A unified algorithm based on HTS and self-adapting PSO for the construction of octagonal and rectilinear SMT[J]. Soft Computing, vol.24, no.6, pp.3943-3961,2020.
Liu, N., Pan, J. Sun, C., Ch, Su. An efficient surrogate-assisted quasi-affine transformation evolutionary algorithm for expensive optimization problems [J]. Knowledge-Based Systems, 209: 106418,2020.
Huang, Zhen et al. “ Maximum a posteriori adaptation of network parameters in deep models,” Conference of the International Speech Communication Association, ISCA, September 6-10, 2015, Dresden, Germany, pp. 1076-1080,2015.
Pereyra, M. . "Revisiting Maximum-A-Posteriori Estimation in Log-Concave Models." SIAM Journal on Imaging Sciences., vol. 12, no.1, pp.650-670,2019.
Feng, Ruyi, Yanfei Zhong, and Liangpei Zhang. “Adaptive spatial regularization sparse unmixing strategy based on joint MAP for hyperspectral remote sensing imagery,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing., vol.9, no.12, pp. 5791-5805,2016.
Chen, N. N., Gong, X. T., Wang, Y. M., Zhang, C. Y. and Fu, Y. G. Random clustering forest for extended belief rule-based system [J]. Soft Computing, vol.25, no.6, pp.4609-4619,2021.
Fu, Y. G., Huang, H. Y., Guan. Y., Wang, Y., Liu, W. and Fang, W. EBRB cascade classifier for imbalanced data via rule weight updating [J]. Knowledge-Based Systems, 223: 107010,2021..
Guo, L., Li, M. and Xu, D. Efficient Approximation Algorithms for Maximum Coverage with Group Budget Constraints [J]. Theoretical Computer Science, 788:53-65,2019.
Li H. , Lin Z. . “Accelerated Alternating Direction method of multipliers: an Optimal O(1/K) Nonergodic Analysis”, Journal of Scientific Computing, vol.79, no.2, pp. 671-699,2019.
Babacan, S. Derin, Rafael Molina, and Aggelos K. Katsaggelos. “Bayesian compressive sensing using Laplace priors,” IEEE Transactions on image processing., vol.19, no.1, pp.53-63,2009.
Bioucas-Dias J M, Nascimen J P. “Hyperspectral subspace identification,” IEEE Transactions on Geoscience and Remote Sensing. vol. 46, no.8, pp.2435-2445,2008.
Miguel A et al. “Hyperspectral image segmentation using a new spectral unmixing-based binary partition tree representation,” IEEE Transactions on image Processing., vol. 23, no.8, pp.3574-3589,2014.
R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Süsstrunk, “SLIC superpixels compared to state-of-the-a superpixel me thods,” IEEE Transactions on pattern analysis and machine intelligence. vol. 34, no.11, pp.2274-2282,2012.
