A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising
Known to be structured in several patterns at the same time, the prior image of interest is always modeled with the idea of enforcing multiple constraints on unknown signals. For instance, when dealing with a hyperspectral restoration problem, the combination of constraints with piece-wise smoothnes...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-10-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2220-9964/7/10/412 |
| _version_ | 1819102186549805056 |
|---|---|
| author | Le Sun Tianming Zhan Zebin Wu Byeungwoo Jeon |
| author_facet | Le Sun Tianming Zhan Zebin Wu Byeungwoo Jeon |
| author_sort | Le Sun |
| collection | DOAJ |
| description | Known to be structured in several patterns at the same time, the prior image of interest is always modeled with the idea of enforcing multiple constraints on unknown signals. For instance, when dealing with a hyperspectral restoration problem, the combination of constraints with piece-wise smoothness and low rank has yielded promising reconstruction results. In this paper, we propose a novel mixed-noise removal method by employing 3D anisotropic total variation and low rank constraints simultaneously for the problem of hyperspectral image (HSI) restoration. The main idea of the proposed method is based on the assumption that the spectra in an HSI lies in the same low rank subspace and both spatial and spectral domains exhibit the property of piecewise smoothness. The low rankness of an HSI is approximately exploited by the nuclear norm, while the spectral-spatial smoothness is explored using 3D anisotropic total variation (3DATV), which is defined as a combination of 2D spatial TV and 1D spectral TV of the HSI cube. Finally, the proposed restoration model is effectively solved by the alternating direction method of multipliers (ADMM). Experimental results of both simulated and real HSI datasets validate the superior performance of the proposed method in terms of quantitative assessment and visual quality. |
| first_indexed | 2024-12-22T01:30:34Z |
| format | Article |
| id | doaj.art-958cc948f77d4e16845905e1213fceba |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-12-22T01:30:34Z |
| publishDate | 2018-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-958cc948f77d4e16845905e1213fceba2022-12-21T18:43:31ZengMDPI AGISPRS International Journal of Geo-Information2220-99642018-10-0171041210.3390/ijgi7100412ijgi7100412A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed DenoisingLe Sun0Tianming Zhan1Zebin Wu2Byeungwoo Jeon3School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Information and Technology, Nanjing Audit University, Nanjing 211815, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon 440746, KoreaKnown to be structured in several patterns at the same time, the prior image of interest is always modeled with the idea of enforcing multiple constraints on unknown signals. For instance, when dealing with a hyperspectral restoration problem, the combination of constraints with piece-wise smoothness and low rank has yielded promising reconstruction results. In this paper, we propose a novel mixed-noise removal method by employing 3D anisotropic total variation and low rank constraints simultaneously for the problem of hyperspectral image (HSI) restoration. The main idea of the proposed method is based on the assumption that the spectra in an HSI lies in the same low rank subspace and both spatial and spectral domains exhibit the property of piecewise smoothness. The low rankness of an HSI is approximately exploited by the nuclear norm, while the spectral-spatial smoothness is explored using 3D anisotropic total variation (3DATV), which is defined as a combination of 2D spatial TV and 1D spectral TV of the HSI cube. Finally, the proposed restoration model is effectively solved by the alternating direction method of multipliers (ADMM). Experimental results of both simulated and real HSI datasets validate the superior performance of the proposed method in terms of quantitative assessment and visual quality.http://www.mdpi.com/2220-9964/7/10/412hyperspectral restorationmultiple constraintslow rank3D anisotropic total variationADMM |
| spellingShingle | Le Sun Tianming Zhan Zebin Wu Byeungwoo Jeon A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising ISPRS International Journal of Geo-Information hyperspectral restoration multiple constraints low rank 3D anisotropic total variation ADMM |
| title | A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising |
| title_full | A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising |
| title_fullStr | A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising |
| title_full_unstemmed | A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising |
| title_short | A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising |
| title_sort | novel 3d anisotropic total variation regularized low rank method for hyperspectral image mixed denoising |
| topic | hyperspectral restoration multiple constraints low rank 3D anisotropic total variation ADMM |
| url | http://www.mdpi.com/2220-9964/7/10/412 |
| work_keys_str_mv | AT lesun anovel3danisotropictotalvariationregularizedlowrankmethodforhyperspectralimagemixeddenoising AT tianmingzhan anovel3danisotropictotalvariationregularizedlowrankmethodforhyperspectralimagemixeddenoising AT zebinwu anovel3danisotropictotalvariationregularizedlowrankmethodforhyperspectralimagemixeddenoising AT byeungwoojeon anovel3danisotropictotalvariationregularizedlowrankmethodforhyperspectralimagemixeddenoising AT lesun novel3danisotropictotalvariationregularizedlowrankmethodforhyperspectralimagemixeddenoising AT tianmingzhan novel3danisotropictotalvariationregularizedlowrankmethodforhyperspectralimagemixeddenoising AT zebinwu novel3danisotropictotalvariationregularizedlowrankmethodforhyperspectralimagemixeddenoising AT byeungwoojeon novel3danisotropictotalvariationregularizedlowrankmethodforhyperspectralimagemixeddenoising |