低秩张量嵌入的高光谱图像去噪神经网络
Low-rank tensor embedded deep neural network for hyperspectral image denoising
- 2024年28卷第1期 页码:121-131
纸质出版日期: 2024-01-07
DOI: 10.11834/jrs.20243119
扫 描 看 全 文
浏览全部资源
扫码关注微信
纸质出版日期: 2024-01-07 ,
扫 描 看 全 文
涂坤,熊凤超,侯雪强.2024.低秩张量嵌入的高光谱图像去噪神经网络.遥感学报,28(1): 121-131
Tu K,Xiong F C and Hou X Q. 2024. Low-rank tensor embedded deep neural network for hyperspectral image denoising. National Remote Sensing Bulletin, 28(1):121-131
随着遥感卫星技术的快速发展,高光谱图像在环境检测、资源管理、农业预警等领域得到了广泛应用。然而,由于设备误差和大气因素等原因,采集的高光谱图像中常常存在噪声,这会影响后续任务的准确性。因此,高光谱图像去噪成为了一个重要的研究方向。高光谱图像的空间关联、光谱关联和空间—光谱联合关联导致干净的高光谱图像存在低维子空间中。低秩先验是高光谱图像普遍的物理性质,然而基于低秩表示的方法通常需要复杂的参数设置和计算。基于深度学习方法直接从数据中学习到干净图像的先验信息,具有较强的表达能力,但依赖大量数据且缺乏对高光谱图像物理知识如低秩性的有效利用。为了解决这些问题,本文利用高光谱图像的空间—光谱低秩特性,提出一种低秩张量嵌入深度神经网络方法,可以有效去除高光谱图像中的噪声。该方法采用低秩张量分解模块对高光谱图像的特征图进行低秩表示,通过全局池化和卷积等操作完成秩一向量的生成和低秩张量的重构。同时,将低秩张量分解模块与Unet相结合,对浅层特征进行低秩张量表示,以捕捉高光谱图像的空间—光谱低秩特性,提高了模型的去噪能力。当噪声标准差在[0—95]时,算法可以取得41.02 dB的PSNR和0.9888的SSIM。仿真数据和真实数据实验结果表明,所提出的低秩深度神经网络方法去噪效果优于其他方法。
Spectral imagery has emerged as a powerful tool with widespread applications across various fields. This tool’s unique ability to identify materials continuous narrow bands has made it invaluable for tasks such as environmental monitoring
resource management
and agricultural early warning. However
the hyperspectral imagery utility is often compromised by the presence of noise from factors such as equipment errors and atmospheric conditions. This noise poses a significant challenge to the accuracy of subsequent analytical tasks
requiring the development of effective hyperspectral image denoising techniques. The spatial
spectral
and spatial-spectral joint correlations observed in hyperspectral images indicate that clean hyperspectral images occupy a low-dimensional subspace. This characteristic can be effectively characterized by low-rank and sparse representations. Consequently
a considerable body of research has been dedicated to exploring denoising methods based on such representations to enhance hyperspectral image quality. On the one hand
while deep learning methods offer the advantage of directly extracting prior information from data
they often exhibit low efficiency in the utilization of physical knowledge specific to hyperspectral images
such as their inherent low-rank nature. On the other hand
model-based techniques require the manual setting of priors and intricate parameter tuning
presenting a challenge in terms of practicality and adaptability. The objective of this study is to address the existing challenges in hyperspectral image denoising by proposing a novel approach that combines the strengths of deep learning- and model-based methods. The proposed methodology leverages the spatial-spectral low-rank characteristics inherent in hyperspectral images and embeds the low-rank tensor decomposition module into the U-Net for enhanced denoising. The low-rank tensor decomposition module is based on CP decomposition
generates rank-one vectors
and reconstructs low-rank tensors through operations like global pooling and convolution. The low-rank tensor decomposition module is integrated with the U-net architecture to represent shallow features as low-rank tensors. This strategy enables the model to capture spatial-spectral low-rank characteristics comprehensively
thereby significantly enhancing its denoising capabilities. Experimental evaluations
encompassing both simulated and real data
validate the efficacy of the proposed low-rank deep neural network method. Across a noise standard deviation range of [0—95]
the algorithm achieves a peak signal-to-noise ratio of 41.02 dB and a structural similarity index of 0.9888. Empirical results underscore the superiority of the proposed low-rank deep neural network method over alternative approaches in terms of denoising performance for hyperspectral images. By effectively leveraging the spatial-spectral low-rank characteristics intrinsic to hyperspectral images
this methodology presents a robust solution for enhancing the accuracy of hyperspectral imagery in diverse applications. The amalgamation of low-rank tensor decomposition with deep learning techniques not only addresses existing challenges but also opens up promising avenues for future research in hyperspectral image processing
paving the way for improved methodologies and innovative solutions. The comprehensive exploration of this combined approach provides valuable insights and contributes to the evolving landscape of hyperspectral image analysis and enhancement.
高光谱图像去噪深度神经网络低秩张量表示知识驱动深度学习CP分解U-Net
hyperspectral image denoisingdeep neural networklow-rank tensor representationknowledge-driven deep learningCP decompositionU-Net
Chang Y, L Yan and S Zhong. 2017. Hyper-Laplacian Regularized Unidirectional Low-Rank Tensor Recovery for Multispectral Image Denoising. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [10.1109/CVPR.2017.625http://dx.doi.org/10.1109/CVPR.2017.625]
Çiçek Ö, A Abdulkadir, S S Lienkamp, T Brox and O Ronneberger. 2016. 3D U-Net: learning dense volumetric segmentation from sparse annotation. International conference on medical image computing and computer-assisted intervention, Springer
Dong W, H Wang, F Wu, G Shi and X J I T o C I Li. 2019. Deep spatial-spectral representation learning for hyperspectral image denoising. 5(4): 635-648. [10.1109/TCI.2019.2911881]
Fu Y, A Lam, I Sato and Y Sato 2015. Adaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image Denoising. 2015 IEEE International Conference on Computer Vision (ICCV): 343-351. [10.1109/iccv.2015.47]
Guo X, X Huang, L Zhang and L Zhang. 2013. Hyperspectral image noise reduction based on rank-1 tensor decomposition. ISPRS Journal of Photogrammetry and Remote Sensing 83: 50-63. [10.1016/j.isprsjprs.2013.06.001]
Liu X, S Bourennane and C Fossati. 2012. Denoising of Hyperspectral Images Using the PARAFAC Model and Statistical Performance Analysis. IEEE Trans. Geosci. Remote. Sens. 50(10): 3717-3724. [10.1109/TGRS.2012.2187063]
Lone Z A and A R Pais. 2022. Object detection in hyperspectral images. Digit. Signal Process. 131: 103752. [10.1016/j.dsp.2022.103752http://dx.doi.org/10.1016/j.dsp.2022.103752]
Maggioni M, V Katkovnik, K O Egiazarian and A J I T o I P Foi. 2013. Nonlocal Transform-Domain Filter for Volumetric Data Denoising and Reconstruction.
Peng J, W Sun, H-C Li, W Li, X Meng, C Ge and Q Du. 2022. Low-Rank and Sparse Representation for Hyperspectral Image Processing: A review. IEEE Geoscience and Remote Sensing Magazine 10(1): 10-43. [10.1109/mgrs.2021.3075491]
Peng Y, D Meng, Z Xu, C Gao, Y Yang and B Zhang. 2014. Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising. 2014 IEEE Conference on Computer Vision and Pattern Recognition. [10.1109/CVPR.2014.377http://dx.doi.org/10.1109/CVPR.2014.377]
Ronneberger O, P Fischer and T Brox 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation: 234-241. [10.1007/978-3-319-24574-4_28http://dx.doi.org/10.1007/978-3-319-24574-4_28]
Wu C Z,Chen X and Zhan S. 2020. Remote sensing image denoising using residual encoder-decoder networks with edge enhancement. Journal of Remote Sensing (Chinese),24(1):27-36
吴从中, 陈曦和詹曙. 2020. 结合残差编解码网络和边缘增强的遥感图像去噪. 遥感学报. 24(01): 27-36 [DOI:10.11834/jrs.20208169http://dx.doi.org/10.11834/jrs.20208169]
Wang L, L Wang, Q Wang and L Bruzzone. 2022. RSCNet: A Residual Self-Calibrated Network for Hyperspectral Image Change Detection. IEEE Transactions on Geoscience and Remote Sensing 60: 1-17. [10.1109/TGRS.2022.3177478]
Wang M, J Yu, J-H Xue and W Sun. 2016. Denoising of Hyperspectral Images Using Group Low-Rank Representation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 9(9): 4420-4427. [10.1109/jstars.2016.2531178]
Wei K, Y Fu and H Huang. 2021. 3-D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising. IEEE Trans. Neural Networks Learn. Syst. 32(1): 363-375. [10.1109/TNNLS.2020.2978756]
Xiong F, J Zhou, S Tao, J Lu, J Zhou and Y Qian. 2022. SMDS-Net: Model Guided Spectral-Spatial Network for Hyperspectral Image Denoising. IEEE Transactions on Image Processing 31: 5469-5483. [10.1109/tip.2022.3196826]
Xiong F, J Zhou, Q Zhao, J Lu and Y Qian. 2022. MAC-Net: Model-Aided Nonlocal Neural Network for Hyperspectral Image Denoising. IEEE Transactions on Geoscience and Remote Sensing 60: 1-14. [10.1109/TGRS.2021.3131878]
Xue J, Y Zhao, W Liao and J C-W Chan. 2019. Nonlocal Low-Rank Regularized Tensor Decomposition for Hyperspectral Image Denoising. IEEE Trans. Geosci. Remote. Sens. 57(7): 5174-5189. [10.1109/TGRS.2019.2897316]
Ye M, Y Qian and J Zhou. 2015. Multitask Sparse Nonnegative Matrix Factorization for Joint Spectral–Spatial Hyperspectral Imagery Denoising. IEEE Transactions on Geoscience and Remote Sensing 53(5): 2621-2639. [10.1109/tgrs.2014.2363101]
Zhang H, W He, L Zhang, H Shen and Q Yuan. 2014. Hyperspectral Image Restoration Using Low-Rank Matrix Recovery. IEEE Trans. Geosci. Remote. Sens. 52(8): 4729-4743. [10.1109/TGRS.2013.2284280]
Zhang K, W Zuo, Y Chen, D Meng and L Zhang. 2017. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Trans Image Process 26(7): 3142-3155. [10.1109/TIP.2017.2662206]
Zhang S, L Wang, L Zhang and H Huang. 2021. Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [10.1109/CVPR46437.2021.01183http://dx.doi.org/10.1109/CVPR46437.2021.01183]
Zheng Y-B, T-Z Huang, X-L Zhao, T-X Jiang, T-H Ma and T-Y Ji. 2020. Mixed Noise Removal in Hyperspectral Image via Low-Fibered-Rank Regularization. IEEE Trans. Geosci. Remote. Sens. 58(1): 734-749. [10.1109/TGRS.2019.2940534]
Zhu Q, W Deng, Z Zheng, Y Zhong, Q Guan, W Lin, L Zhang and D Li. 2022. A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification. IEEE Transactions on Cybernetics 52(11): 11709-11723. [10.1109/TCYB.2021.3070577]
Zhuang L and J M Bioucas-Dias. 2018. Fast Hyperspectral Image Denoising and Inpainting Based on Low-Rank and Sparse Representations. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 11(3): 730-742. [10.1109/jstars.2018.2796570]
相关作者
相关机构