Abstract
During the last decades, learning-based deep neural network (DNN) has shown its advantages on hyperspectral image (HSI) denoising. Compared to classical prior-based methods, DNN-based algorithms employ a larger scale of training samples for learning to simulate the complex image generation process with higher accuracy. However, most DNN-based HSI denoising methods are designed by a superposition convolution layer, which cannot fully use the frequency information in the image itself, especially the information containing a strong response to noise in high-frequency domain. Thus, we propose a high-frequency attention network (HFAN) assisted by both spectral and spatial high-frequency information to achieve accurate HSIs denoising in this paper. Our proposed HFAN comprises a high-frequency and denoising branch, and the auxiliary function of high-frequency information is realized by transmitting the characteristic information of the high-frequency component to the denoising branch. Specifically, the spatial-spectral attention (SSA) module is presented to recover more detail in space and spectra. Experiments on synthetic and real HSI data show that our proposed HFAN achieves better denoising results compare to the other advanced methods.
Similar content being viewed by others
Data availibility statement
The data that support the findings of this study are available from the corresponding author, C. W., upon reasonable request.
References
Aggarwal HK, Majumdar A (2015) Mixed gaussian and impulse denoising of hyperspectral images. In: 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE, pp 429–432
Arad B, Ben-Shahar O (2016) Sparse recovery of hyperspectral signal from natural rgb images. In: European Conference on Computer Vision, Springer, pp 19–34
Buades A, Coll B, Morel JM (2005) A non-local algorithm for image denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), IEEE, pp 60–65
Cao X, Yao J, Xu Z et al (2020) Hyperspectral image classification with convolutional neural network and active learning. IEEE Trans Geosci Remote Sens 58(7):4604–4616
Cao X, Fu X, Xu C et al (2021) Deep spatial-spectral global reasoning network for hyperspectral image denoising. IEEE Trans Geosci Remote Sens 60:1–14
Chang Y, Yan L, Zhong S (2017) Hyper-laplacian regularized unidirectional low-rank tensor recovery for multispectral image denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4260–4268
Chang Y, Yan L, Fang H et al (2018) Hsi-denet: Hyperspectral image restoration via convolutional neural network. IEEE Trans Geosci Remote Sens 57(2):667–682
Chen Y, Cao X, Zhao Q et al (2017) Denoising hyperspectral image with non-iid noise structure. IEEE Trans Cybernet 48(3):1054–1066
Chen Y, Guo Y, Wang Y et al (2017) Denoising of hyperspectral images using nonconvex low rank matrix approximation. IEEE Trans Geosci Remote Sens 55(9):5366–5380
Chen Y, Huang TZ, Deng LJ et al (2017) Group sparsity based regularization model for remote sensing image stripe noise removal. Neurocomputing 267:95–106
Chen Y, Huang TZ, Zhao XL et al (2017) Stripe noise removal of remote sensing images by total variation regularization and group sparsity constraint. Remote Sens 9(6):559
Chen Y, He W, Yokoya N et al (2019) Hyperspectral image restoration using weighted group sparsity-regularized low-rank tensor decomposition. IEEE Trans Cybernet 50(8):3556–3570
Chen Y, Li J, Zhou Y (2020) Hyperspectral image denoising by total variation-regularized bilinear factorization. Signal Processing 174(107):645
Deng LJ, Huang TZ, Zhao XL et al (2018) A directional global sparse model for single image rain removal. Appl Math Modell 59:662–679
Deng LJ, Vivone G, Jin C et al (2020) Detail injection-based deep convolutional neural networks for pansharpening. IEEE Trans Geosci Remote Sens 59(8):6995–7010
Dong W, Wang H, Wu F et al (2019) Deep spatial-spectral representation learning for hyperspectral image denoising. IEEE Trans Comput Imag 5(4):635–648
Dou HX, Huang TZ, Deng LJ et al (2018) Directional l0 sparse modeling for image stripe noise removal. Remote Sens 10(3):361
Fang L, Li S, Kang X et al (2015) Spectral-spatial classification of hyperspectral images with a superpixel-based discriminative sparse model. IEEE Trans Geosci Remote Sens 53(8):4186–4201
Goetz AF (2009) Three decades of hyperspectral remote sensing of the earth: A personal view. Remote Sens Environ 113:S5–S16
He T, Zhang Z, Zhang H, et al. (2019a) Bag of tricks for image classification with convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 558–567
He W, Zhang H, Zhang L et al (2015) Total-variation-regularized low-rank matrix factorization for hyperspectral image restoration. IEEE Trans Geosci Remote Sens 54(1):178–188
He W, Yao Q, Li C, et al (2019b) Non-local meets global: An integrated paradigm for hyperspectral denoising. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 6868–6877
Hong D, Gao L, Yokoya N et al (2020) More diverse means better: Multimodal deep learning meets remote-sensing imagery classification. IEEE Trans Geosci Remote Sens 59(5):4340–4354
Ji S, Xu W, Yang M et al (2012) 3d convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Machine Intell 35(1):221–231
Jin C, Deng LJ, Huang TZ et al (2022) Laplacian pyramid networks: A new approach for multispectral pansharpening. Information Fusion 78:158–170
Jin ZR, Zhang TJ, Jiang TX, et al (2022b) Lagconv: Local-context adaptive convolution kernels with global harmonic bias for pansharpening. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)
Lewis SA, Hudak AT, Ottmar RD et al (2011) Using hyperspectral imagery to estimate forest floor consumption from wildfire in boreal forests of alaska, usa. Int J Wildland Fire 20(2):255–271
Lillesand T, Kiefer RW, Chipman J (2015) Remote sensing and image interpretation. John Wiley & Sons, USA
Liu W, Lee J (2019) A 3-d atrous convolution neural network for hyperspectral image denoising. IEEE Trans Geosci Remote Sens 57(8):5701–5715
Lu T, Li S, Fang L et al (2015) Spectral-spatial adaptive sparse representation for hyperspectral image denoising. IEEE Trans Geosci Remote Sens 54(1):373–385
Lu X, Wang Y, Yuan Y (2013) Graph-regularized low-rank representation for destriping of hyperspectral images. IEEE Trans Geosci Remote Sens 51(7):4009–4018
Luo YS, Zhao XL, Jiang TX et al (2021) Hyperspectral mixed noise removal via spatial-spectral constrained unsupervised deep image prior. IEEE J Sel Top Appl Earth Obs Remote Sens 14:9435–9449
Maggioni M, Katkovnik V, Egiazarian K et al (2012) Nonlocal transform-domain filter for volumetric data denoising and reconstruction. IEEE Trans Image Process 22(1):119–133
Marion F. Baumgardner LLB, Landgrebe DA (2015) 220 band aviris hyperspectral image data set: June 12, 1992 indian pine test site 3. https://doi.org/10.4231/R7RX991C, https://purr.purdue.edu/publications/1947/1
Pande-Chhetri R, Abd-Elrahman A (2011) De-striping hyperspectral imagery using wavelet transform and adaptive frequency domain filtering. ISPRS J Photogramm Remote Sens 66(5):620–636
Pang L, Gu W, Cao X (2022) Trq3dnet: A 3d quasi-recurrent and transformer based network for hyperspectral image denoising. Remote Sens 14(18):4598
Peng Y, Meng D, Xu Z, et al (2014) Decomposable nonlocal tensor dictionary learning for multispectral image denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2949–2956
Plaza A, Benediktsson JA, Boardman JW et al (2009) Recent advances in techniques for hyperspectral image processing. Remote Sens Environ 113:S110–S122
Qian Y, Ye M (2012) Hyperspectral imagery restoration using nonlocal spectral-spatial structured sparse representation with noise estimation. IEEE J Sel Top Appl Earth Obs Remote Sens 6(2):499–515
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, Springer, pp 234–241
Shi Q, Tang X, Yang T et al (2021) Hyperspectral image denoising using a 3-d attention denoising network. IEEE Trans Geosci Remote Sens 59(12):10,348-10,363
Su H, Du Q, Chen G et al (2014) Optimized hyperspectral band selection using particle swarm optimization. IEEE J Sel Top Appl Earth Obs Remote Sens 7(6):2659–2670
Tiwari K, Arora MK, Singh D (2011) An assessment of independent component analysis for detection of military targets from hyperspectral images. Int J Appl Earth Obs Geoinf 13(5):730–740
Vaswani A, Shazeer N, Parmar N, et al (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998–6008
Wang C, Shen HZ, Fan F, et al (2021a) Eaa-net: A novel edge assisted attention network for single image dehazing. Knowledge-Based Systems p. 107279
Wang Y, Deng LJ, Zhang TJ, et al. (2021b) Ssconv: Explicit spectral-to-spatial convolution for pansharpening. In: Proceedings of the 29th ACM International Conference on Multimedia, pp 4472–4480
Wang Z, Bovik AC, Sheikh HR et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Wei K, Fu Y, Huang H (2020) 3-d quasi-recurrent neural network for hyperspectral image denoising. IEEE Trans Neural Netw Learn Syst 32(1):363–375
Wu X, Huang TZ, Deng LJ, et al (2021) Dynamic cross feature fusion for remote sensing pansharpening. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 14,687–14,696
Xiao JL, Huang TZ, Deng LJ, et al (2022) A new context-aware details injection fidelity with adaptive coefficients estimation for variational pansharpening. IEEE Trans Geosci Remote Sens
Xie Q, Zhao Q, Meng D et al (2017) Kronecker-basis-representation based tensor sparsity and its applications to tensor recovery. IEEE Trans Pattern Anal Mach Intell 40(8):1888–1902
Xue J, Zhao Y, Liao W et al (2017) Joint spatial and spectral low-rank regularization for hyperspectral image denoising. IEEE Trans Geosci Remote Sens 56(4):1940–1958
Yuan Q, Zhang L, Shen H (2012) Hyperspectral image denoising employing a spectral-spatial adaptive total variation model. IEEE Trans Geosci Remote Sens 50(10):3660–3677
Yuan Q, Zhang Q, Li J et al (2018) Hyperspectral image denoising employing a spatial-spectral deep residual convolutional neural network. IEEE Trans Geosci Remote Sens 57(2):1205–1218
Zhang H, He W, Zhang L et al (2013) Hyperspectral image restoration using low-rank matrix recovery. IEEE Trans Geosci Remote Sens 52(8):4729–4743
Zhang J, Cai Z, Chen F et al (2022) Hyperspectral image denoising via adversarial learning. Remote Sens 14(8):1790
Zhang L, Zhang L, Tao D et al (2013) Hyperspectral remote sensing image subpixel target detection based on supervised metric learning. IEEE Trans Geosci Remote Sens 52(8):4955–4965
Zhang Q, Yuan Q, Li J et al (2019) Hybrid noise removal in hyperspectral imagery with a spatial-spectral gradient network. IEEE Trans Geosci Remote Sens 57(10):7317–7329
Zhang Q, Yuan Q, Li J et al (2020) Deep spatio-spectral bayesian posterior for hyperspectral image non-iid noise removal. ISPRS J Photogramm Remote Sens 164:125–137
Zhang T, Fu Y, Li C (2021) Hyperspectral image denoising with realistic data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 2248–2257
Zhang TJ, Deng LJ, Huang TZ, et al (2022b) A triple-double convolutional neural network for panchromatic sharpening. IEEE Trans Neural Netw Learn Syst
Zhao YQ, Yang J (2014) Hyperspectral image denoising via sparse representation and low-rank constraint. IEEE Trans Geosci Remote Sens 53(1):296–308
Zhao YQ, Gong P, Pan Q (2008) Object detection by spectropolarimeteric imagery fusion. IEEE Trans Geosci Remote Sens 46(10):3337–3345
Zhou Y, Peng J, Chen CP (2014) Dimension reduction using spatial and spectral regularized local discriminant embedding for hyperspectral image classification. IEEE Trans Geosci Remote Sens 53(2):1082–1095
Zhuang JH, Luo Y, Zhao XL et al (2021) Reconciling hand-crafted and self-supervised deep priors for video directional rain streaks removal. IEEE Signal Process Lett 28:2147–2151
Acknowledgements
This work is supported by the Basic Public Welfare Research Program of Zhejiang Province (LGG22F020036), Natural Science Research Project of Anhui Universities (KJ2019A0032), Natural Science Foundation of Anhui Province (2008085QF286), National key research and development program of China (2021YFF0700203).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yang, C., Zhang, C., Shen, H. et al. HFAN: High-Frequency Attention Network for hyperspectral image denoising. Int. J. Mach. Learn. & Cyber. 15, 837–851 (2024). https://doi.org/10.1007/s13042-023-01942-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-023-01942-2