浏览全部资源
扫码关注微信
Published： 07 January 2024 ，
扫 描 看 全 文
谢金凤，陈涛.2024.考虑光谱信息和超像素分割的高光谱解混网络.遥感学报，28（1）： 142-153
Xie J F and Chen T. 2024. Hyperspectral unmixing network considering spectral information and superpixel segmentation. National Remote Sensing Bulletin， 28（1）：142-153
在高光谱解混的过程中考虑影像的空间信息，能够有效提高解混精度。而超像素分割能够划分空间同质区域，为此本文提出一种考虑光谱信息和超像素分割的解混网络（SSUNet）。首先需对原始影像进行超像素分割处理，获得具有空间特征的超像素分割数据，然后采用SSUNet对原始高光谱数据和超像素分割数据进行训练和解混。在线性和非线性混合模型生成的模拟数据集和两个真实数据集上的实验表明，与SUnSAL、SUnSAL-TV、SCLRSU、MTAEU、EGU-Net-pw和1DCNN的解混结果相比，所提网络具有更高的解混精度和较好的鲁棒性。
The pixel is the basic unit of remote sensing images. If a single pixel contains multiple types of covering ground objects
then it is called a mixed pixel. Hyperspectral unmixing aims to decompose the mixed pixels into several basic component units (endmembers) and obtain the proportion (abundance) of each endmember
which can improve the accuracy of remote sensing image classification and subpixel level target detection. Thus
research on this method promotes the development of hyperspectral remote sensing technology. Studies show that considering the spatial information in the process of hyperspectral unmixing can effectively improve the unmixing accuracy. However
most of the nonlinear unmixing networks based on deep learning only use the spectral information of images.
A hyperspectral unmixing network considering spectral information and superpixel segmentation (SSUNet) is proposed on the basis of the supervised unmixing idea and one-dimensional convolutional neural network to maximize the spectral and spatial information of images. First
the original hyperspectral data should be processed using superpixel segmentation to obtain the superpixel segmentation data with spatial characteristics. Then
SSUNet is used to train and unmix the original hyperspectral and superpixel segmentation data. The loss function adds regularization constraint term based on the root mean square error to promote the sparsity of the unmixing abundance and generate closer unmixing results to the real value. The activation function of the network output layer is softmax
which yields output values of each output node within the range of [0
1] and constrains their sum to 1
thus satisfying the two constraints of unmixing: the abundance nonnegative constraint and abundance sum-to-one constraint.
Experiments on simulated datasets generated by the linear and nonlinear mixed models and the two real datasets show that the proposed network has higher unmixing accuracy and better robustness than the unmixing results of SUnSAL
SUnSAL-TV
SCLRSU
MTAEU
EGU-Net-pw
and 1DCNN. Three Gaussian noises with different SNR levels (20
30
and 40 dB) are added to the simulated dataset. The proposed network can achieve the best unmixing results at all SNR levels
and the network also achieves high unmixing accuracy with the increase in SNR. In addition
the influence of the change of w value on the unmixing result of the simulated datasets under different SNR is verified. The experimental results show that when the value range of w is [3
13]
the RMSE value does not change substantially
and the best value of w is 5. Experiments on real datasets show that SSUNet can still achieve the best unmixing results in complex real scenes.
The SSUNet network uses the dual-branch structure to mine the features of the original image data and the superpixel segmentation data with spatial features. This network also utilizes the fusion layer to fuse the features and improve the unmixing accuracy of the model. Experiments on simulated and real hyperspectral datasets show that the proposed network has high accuracy.
高光谱图像高光谱解混光谱和空间信息超像素分割深度学习卷积神经网络
hyperspectral imageshyperspectral unmixingspectral and spatial informationsuperpixel segmentationdeep learningconvolutional neural network
Achanta R, Shaji A, Smith K, Lucchi A, Fua P and Süsstrunk S. 2012. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11): 2274-2282 [DOI: 10.1109/TPAMI.2012.120http://dx.doi.org/10.1109/TPAMI.2012.120]
Afonso M V, Bioucas-Dias J M and Figueiredo M A T. 2011. An augmented lagrangian approach to the constrained optimization formulation of imaging inverse problems. IEEE Transactions on Image Processing, 20(3): 681-695 [DOI: 10.1109/TIP.2010.2076294http://dx.doi.org/10.1109/TIP.2010.2076294]
Altmann Y, Dobigeon N and Tourneret J Y. 2011. Bilinear models for nonlinear unmixing of hyperspectral images//2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). Lisbon: IEEE: 1-4 [DOI: 10.1109/WHISPERS.2011.6080928http://dx.doi.org/10.1109/WHISPERS.2011.6080928]
Bioucas-Dias J. M., and M. A. T. Figueiredo. 2010. Alternating direction algorithms for constrained sparse regression: Application to hyperspectral unmixing. Paper presented at the 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 14-16 June 2010.
Boardman J W, Kruscl F A and Grccn R O. 1995. Mapping target signatures via partial unmixing of AVIRIS data//Summaries of the Fifth Annual JPL Airborne Earth Science Workshop. Washington: JPL Publi Cation: 23-26
Borsoi R A, Imbiriba T, Bermudez J C M and Richard C. 2020. A blind multiscale spatial regularization framework for kernel-based spectral unmixing. IEEE Transactions on Image Processing, 29: 4965-4979 [DOI: 10.1109/TIP.2020.2978342http://dx.doi.org/10.1109/TIP.2020.2978342]
Chen T, Liu Y, Zhang Y X, Du B and Plaza A. 2022. Superpixel-based collaborative and low-rank regularization for sparse hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 60: 5529216 [DOI: 10.1109/tgrs.2022.3177636http://dx.doi.org/10.1109/tgrs.2022.3177636]
Ding L, Tang P and Li H Y. 2013. Analysis on spectral unmixing based on manifold learning. Infrared and Laser Engineering, 42(9): 2421-2425
丁玲, 唐娉, 李宏益. 2013. 基于流形学习的混合光谱解混分析. 红外与激光工程, 42(9): 2421-2425
Hong D F, Gao L R, Yao J, Yokoya N, Chanussot J, Heiden U and Zhang B. 2022. Endmember-guided unmixing network (EGU-Net): a general deep learning framework for self-supervised hyperspectral unmixing. IEEE Transactions on Neural Networks and Learning Systems, 33(11): 6518-6531 [DOI: 10.1109/tnnls.2021.3082289http://dx.doi.org/10.1109/tnnls.2021.3082289]
Huang Y F, Li J, Qi L, Wang Y and Gao X B. 2020. Spatial-spectral autoencoder networks for hyperspectral unmixing//IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium. Waikoloa: IEEE: 2396-2399
Iordache M D, Bioucas-Dias J M and Plaza A. 2012. Total variation spatial regularization for sparse hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 50(11): 4484-4502 [DOI: 10.1109/tgrs.2012.2191590http://dx.doi.org/10.1109/tgrs.2012.2191590]
Iordache M D, Bioucas-Dias J M and Plaza A. 2014. Collaborative sparse regression for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 52(1): 341-354 [DOI: 10.1109/tgrs.2013.2240001http://dx.doi.org/10.1109/tgrs.2013.2240001]
Kong F Q, Chen M Y, Li Y S and Li D. 2022. A global spectral–spatial feature learning network for semisupervised hyperspectral unmixing. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15: 3190-3203 [DOI: 10.1109/jstars.2022.3168333http://dx.doi.org/10.1109/jstars.2022.3168333]
Nascimento J M P and Dias J M B. 2005. Vertex component analysis: a fast algorithm to unmix hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 43(4): 898-910 [DOI: 10.1109/tgrs.2005.844293http://dx.doi.org/10.1109/tgrs.2005.844293]
Palsson B, Sigurdsson J, Sveinsson J R and Ulfarsson M O. 2018. Hyperspectral unmixing using a neural network autoencoder. IEEE Access, 6: 25646-25656 [DOI: 10.1109/access.2018.2818280http://dx.doi.org/10.1109/access.2018.2818280]
Palsson B, Sveinsson J R and Ulfarsson M O. 2019. Spectral-spatial hyperspectral unmixing using multitask learning. IEEE Access, 7: 148861-148872 [DOI: 10.1109/access.2019.2944072http://dx.doi.org/10.1109/access.2019.2944072]
Qi L, Gao F, Dong J Y, Gao X B and Du Q. 2022. SSCU-Net: spatial-spectral collaborative unmixing network for hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 60: 5407515 [DOI: 10.1109/tgrs.2022.3150970http://dx.doi.org/10.1109/tgrs.2022.3150970]
Wan L L, Chen T, Plaza A and Cai H J. 2021. Hyperspectral unmixing based on spectral and sparse deep convolutional neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 11669-11682 [DOI: 10.1109/jstars.2021.3126755http://dx.doi.org/10.1109/jstars.2021.3126755]
Wang X Y, Zhong Y F, Zhang L P and Xu Y Y. 2017. Spatial group sparsity regularized nonnegative matrix factorization for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 55(11): 6287-6304 [DOI: 10.1109/tgrs.2017.2724944http://dx.doi.org/10.1109/tgrs.2017.2724944]
Weng X H, Lei W H and Ren X D. 2020. Kernel sparse representation for hyperspectral unmixing based on high mutual coherence spectral library. International Journal of Remote Sensing, 41(4): 1286-1301 [DOI: 10.1080/01431161.2019.1666215http://dx.doi.org/10.1080/01431161.2019.1666215]
Winter M E. 1999. N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data//Proceedings Volume 3753, Imaging Spectrometry V. Denver: SPIE: 266-275
Xu X, Song X Y, Li T, Shi Z W and Pan B. 2022. Deep autoencoder for hyperspectral unmixing via global-local smoothing. IEEE Transactions on Geoscience and Remote Sensing, 60: 5524216 [DOI: 10.1109/tgrs.2022.3152782http://dx.doi.org/10.1109/tgrs.2022.3152782]
Zhang X R, Sun Y J, Zhang J Y, Wu P and Jiao L C. 2018. Hyperspectral unmixing via deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 15(11): 1755-1759 [DOI: 10.1109/lgrs.2018.2857804http://dx.doi.org/10.1109/lgrs.2018.2857804]
Zhao M, Yan L B and Chen J. 2021. LSTM-DNN based autoencoder network for nonlinear hyperspectral image unmixing. IEEE Journal of Selected Topics in Signal Processing, 15(2): 295-309 [DOI: 10.1109/jstsp.2021.3052361http://dx.doi.org/10.1109/jstsp.2021.3052361]
Zhu F Y. 2017. Hyperspectral unmixing: ground truth labeling, datasets, benchmark performances and survey. arXiv: 1708.05125
Zhu Q Q, Wang L L, Chen J L, Zeng W, Zhong Y F, Guan Q G and Yang Z J. 2022. S3TRM: spectral-spatial unmixing of hyperspectral imagery based on sparse topic relaxation-clustering model. IEEE Transactions on Geoscience and Remote Sensing, 60: 5515613 [DOI: 10.1109/tgrs.2021.3117250http://dx.doi.org/10.1109/tgrs.2021.3117250]
相关文章
相关作者
相关机构
京公网安备11010802024621