A Probabilistic Hyperspectral Imagery Restoration Method
Source abstract
Abstract
Hyperspectral image (HSI) restoration is an important task of hyperspectral imagery processing, which aims to improve the performance of the subsequent HSI interpretation and applications. Considering HSI is always influenced by multiple factors—such as Gaussian noise, stripes, dead pixels, etc.—we propose an HSI-oriented probabilistic low-rank restoration method to address this problem. Specifically, we treat the expected clean HSI as a low-rank matrix. We assume the distribution of complex noise obeys a mixture of Gaussian distributions. Then, the HSI restoration problem is casted into solving the clean HSI from its counterpart with complex noise. In addition, considering the rank number need to be assigned manually for existing low-rank based HSI restoration method, we propose to automatically determine the rank number of the low-rank matrix by taking advantage of hyperspectral unmixing. Experimental results demonstrate HSI image can be well restored with the proposed method.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote-Sensing Image Classification · Advanced Image Fusion Techniques · Image and Signal Denoising Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China
School of Electronic Engineering, Xidian University, Xi’an 710071, China
Funding
National Natural Science Foundation of China
References (43)
Show source-provided references
1. Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art
2. Self-paced joint sparse representation for the classification of hyperspectral images10.1109/TGRS.2018.2865102 ↗
3. Hyperspectral remote sensing data analysis and future challenges10.1109/MGRS.2013.2244672 ↗
4. Graph-regularized fast and robust principal component analysis for hyperspectral band selection10.1109/TGRS.2018.2794443 ↗
5. Lara, M.Á., Diezma, B., Lleó, L., Roger, J.M., Garrido, Y., Gil, M.I., and Ruiz-Altisent, M. (2016). Hyperspectral Imaging to Evaluate the Effect of Irrigation Water Salinity in Lettuce. Appl. Sci., 6.10.3390/app6120412 ↗
6. A Poisson nonnegative matrix factorization method with parameter subspace clustering constraint for endmember extraction in hyperspectral imagery10.1016/j.isprsjprs.2017.03.004 ↗
7. Djokam, M., Sandasi, M., Chen, W., Viljoen, A., and Vermaak, I. (2017). Hyperspectral Imaging as a Rapid Quality Control Method for Herbal Tea Blends. Appl. Sci., 7.10.3390/app7030268 ↗
8. Local spectral component decomposition for multi-channel image denoising10.1109/TIP.2016.2561320 ↗
9. Denoising Of Hyperspectral Image
10. Structured Sparse Coding based Hyperspectral Imagery Denoising with Intra-cluster Filtering10.1109/TGRS.2017.2735488 ↗
11. Hyperspectral image restoration using low-rank matrix recovery10.1109/TGRS.2013.2284280 ↗
12. Pure endmember extraction using robust kernel archetypoid analysis for hyperspectral imagery10.1016/j.isprsjprs.2017.08.001 ↗
13. Signal-dependent noise modeling and model parameter estimation in hyperspectral images10.1109/TGRS.2011.2110657 ↗
14. Hyperspectral signal subspace identification in the presence of rare vectors and signal-dependence noise10.1109/TGRS.2012.2201488 ↗
15. Caselles, V. (2006, January 22–30). Total Variation Based Image Denoising and Restoration. Proceedings of the International Congress of Mathematicians, Madrid, Spain.
16. Image denoising using trivariate shrinkage filter in the wavelet domain and joint bilateral filter in the spatial domain10.1109/TIP.2009.2026685 ↗
17. Adapting to unknown smoothness via wavelet shrinkage10.1080/01621459.1995.10476626 ↗
18. Zelinski, A.C., and Goyal, V.K. (August, January 31). Denoising Hyperspectral Imagery and Recovering Junk Bands Using Wavelets and Sparse Approximation. Proceedings of the International Conference on Geoscience and Remote Sensing Symposium, Denver, CO, USA.
19. Rasti, B., Sveinsson, J.R., Ulfarsson, M.O., and Benediktsson, J.A. (2012, January 22–27). Hyperspectral Image Denoising Using 3D Wavelets. Proceedings of the International Conference on Geoscience and Remote Sensing Symposium, Munich, Germany.10.1109/IGARSS.2012.6351286 ↗
20. The curvelet transform for image denoising10.1109/TIP.2002.1014998 ↗
21. Analysis and denoising of hyperspectral remote sensing image in the curvelet domain
22. Total variation, adaptive total variation and nonconvex smoothly clipped absolute deviation penalty for denoising blocky images10.1016/j.patcog.2010.03.022 ↗
23. Yanovsky, I., and Dragomiretskiy, K. (2018). Variational destriping in remote sensing imagery: Total variation with L1 fidelity. Remote Sens., 10.10.3390/rs10020300 ↗
24. Hyperspectral image denoising employing a spectral–spatial adaptive total variation model10.1109/TGRS.2012.2185054 ↗
25. Maboudi, M., Amini, J., Hahn, M., and Saati, M. (2016). Road Network Extraction from VHR Satellite Images Using Context Aware Object Feature Integration and Tensor Voting. Remote Sens., 8.10.3390/rs8080637 ↗
26. Survey of hyperspectral image denoising methods based on tensor decompositions10.1186/1687-6180-2013-186 ↗
27. PLTD: Patch-Based Low-Rank Tensor Decomposition for Hyperspectral Images10.1109/TMM.2016.2608780 ↗
28. Dabov, K., Foi, A., and Egiazarian, K. (2007, January 3–7). Video Denoising by Sparse 3D Transform-Domain Collaborative Filtering. Proceedings of the European Signal Processing Conference, Poznan, Poland.10.1117/12.766355 ↗
29. Hyperspectral image denoising via sparse representation and low-rank constraint10.1109/TGRS.2014.2321557 ↗
30. BM3D Frames and Variational Image Deblurring10.1109/TIP.2011.2176954 ↗
31. Exploring structured sparsity by a reweighted laplace prior for hyperspectral compressive sensing10.1109/TIP.2016.2598652 ↗
32. Total-variation-regularized low-rank matrix factorization for hyperspectral image restoration10.1109/TGRS.2015.2452812 ↗
33. Denoising of hyperspectral images using group low-rank representation10.1109/JSTARS.2016.2531178 ↗
34. Hyperspectral image denoising with superpixel segmentation and low-rank representation10.1016/j.ins.2017.02.044 ↗
35. Intracluster structured low-rank matrix analysis method for hyperspectral denoising10.1109/TGRS.2018.2862384 ↗
36. Robust Collaborative Nonnegative Matrix Factorization for Hyperspectral Unmixing10.1109/TGRS.2016.2580702 ↗
37. Hyperspectral subspace identification10.1109/TGRS.2008.918089 ↗
38. Hyperspectral Data Geometry-Based Estimation of Number of Endmembers Using p-Norm-Based Pure Pixel Identification Algorithm10.1109/TGRS.2012.2213261 ↗
39. Robust principal component analysis?10.1145/1970392.1970395 ↗
40. Wright, J., Ganesh, A., Rao, S., Peng, Y., and Ma, Y. (2009, January 7–10). Robust Principal Component Analysis: Exact Recovery of Corrupted low-Rank Matrices Via Convex Optimization. Proceedings of the Neural Information Processing Systems, Vancouver, BC, Canada.
41. Zhou, T., and Tao, D. (July, January 28). Godec: Randomized Low-Rank & Sparse Matrix Decomposition in Noisy Case. Proceedings of the International Conference on Machine Learning, Bellevue, Washington, DC, USA.
42. Zhao, Q., Meng, D., Xu, Z., Zuo, W., and Zhang, L. (2014, January 22–24). Robust Principal Component Analysis with Complex Noise. Proceedings of the International Conference on Machine Learning, Beijing, China.
43. Sparse bayesian methods for low-rank matrix estimation10.1109/TSP.2012.2197748 ↗