Missing Data Reconstruction for Remote Sensing Images With Weighted Low-Rank Tensor Model
Missing data reconstruction for remote sensing images, such as dead-pixel recovery and cloud removal, is important for remote sensing data applications. Missing information reconstruction is well known as being an ill-posed inverse problem. In this paper, a weighted low-rank tensor regularization mo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8852746/ |
| _version_ | 1818412676292804608 |
|---|---|
| author | Qing Cheng Qiangqiang Yuan Michael Kwok-Po Ng Huanfeng Shen Liangpei Zhang |
| author_facet | Qing Cheng Qiangqiang Yuan Michael Kwok-Po Ng Huanfeng Shen Liangpei Zhang |
| author_sort | Qing Cheng |
| collection | DOAJ |
| description | Missing data reconstruction for remote sensing images, such as dead-pixel recovery and cloud removal, is important for remote sensing data applications. Missing information reconstruction is well known as being an ill-posed inverse problem. In this paper, a weighted low-rank tensor regularization model is proposed to handle the problem. The proposed model fully utilizes the correlations in the spatial, spectral, and temporal components of the remote sensing images to adaptively deal with the varied missing data problems, including the Aqua Moderate Resolution Imaging Spectroradiometer (MODIS) band 6 dead line problem, the Landsat scan-line corrector failure (SLC-off) problem, and cloud contamination. A double-weighted treatment is developed to balance the contributions from the different dimensions and preserve the different structures and textures in remote sensing images. The experiments undertaken confirmed the good performance of the proposed method, and the reconstruction results of the proposed method, in both visual effect and quantitative evaluation, were superior to those of the other methods. |
| first_indexed | 2024-12-14T10:51:05Z |
| format | Article |
| id | doaj.art-79adba9c7fce446e836e0d08a190c3ae |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T10:51:05Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-79adba9c7fce446e836e0d08a190c3ae2022-12-21T23:05:14ZengIEEEIEEE Access2169-35362019-01-01714233914235210.1109/ACCESS.2019.29445778852746Missing Data Reconstruction for Remote Sensing Images With Weighted Low-Rank Tensor ModelQing Cheng0Qiangqiang Yuan1https://orcid.org/0000-0002-0571-4083Michael Kwok-Po Ng2Huanfeng Shen3Liangpei Zhang4School of Urban Design, Wuhan University, Wuhan, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan, ChinaDepartment of Mathematics, Hong Kong Baptist University, Hong KongSchool of Resource and Environmental Science, Wuhan University, Wuhan, ChinaState Key Laboratory of Information Engineering, Survey Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaMissing data reconstruction for remote sensing images, such as dead-pixel recovery and cloud removal, is important for remote sensing data applications. Missing information reconstruction is well known as being an ill-posed inverse problem. In this paper, a weighted low-rank tensor regularization model is proposed to handle the problem. The proposed model fully utilizes the correlations in the spatial, spectral, and temporal components of the remote sensing images to adaptively deal with the varied missing data problems, including the Aqua Moderate Resolution Imaging Spectroradiometer (MODIS) band 6 dead line problem, the Landsat scan-line corrector failure (SLC-off) problem, and cloud contamination. A double-weighted treatment is developed to balance the contributions from the different dimensions and preserve the different structures and textures in remote sensing images. The experiments undertaken confirmed the good performance of the proposed method, and the reconstruction results of the proposed method, in both visual effect and quantitative evaluation, were superior to those of the other methods.https://ieeexplore.ieee.org/document/8852746/Missing information reconstructiontensor completionlow-rank modelremote sensing |
| spellingShingle | Qing Cheng Qiangqiang Yuan Michael Kwok-Po Ng Huanfeng Shen Liangpei Zhang Missing Data Reconstruction for Remote Sensing Images With Weighted Low-Rank Tensor Model IEEE Access Missing information reconstruction tensor completion low-rank model remote sensing |
| title | Missing Data Reconstruction for Remote Sensing Images With Weighted Low-Rank Tensor Model |
| title_full | Missing Data Reconstruction for Remote Sensing Images With Weighted Low-Rank Tensor Model |
| title_fullStr | Missing Data Reconstruction for Remote Sensing Images With Weighted Low-Rank Tensor Model |
| title_full_unstemmed | Missing Data Reconstruction for Remote Sensing Images With Weighted Low-Rank Tensor Model |
| title_short | Missing Data Reconstruction for Remote Sensing Images With Weighted Low-Rank Tensor Model |
| title_sort | missing data reconstruction for remote sensing images with weighted low rank tensor model |
| topic | Missing information reconstruction tensor completion low-rank model remote sensing |
| url | https://ieeexplore.ieee.org/document/8852746/ |
| work_keys_str_mv | AT qingcheng missingdatareconstructionforremotesensingimageswithweightedlowranktensormodel AT qiangqiangyuan missingdatareconstructionforremotesensingimageswithweightedlowranktensormodel AT michaelkwokpong missingdatareconstructionforremotesensingimageswithweightedlowranktensormodel AT huanfengshen missingdatareconstructionforremotesensingimageswithweightedlowranktensormodel AT liangpeizhang missingdatareconstructionforremotesensingimageswithweightedlowranktensormodel |