EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection
Hyperspectral band selection (BS) is an effective means to avoid the Hughes phenomenon and heavy computational burden in hyperspectral image processing. However, most of the existing BS methods fail to fully consider the interaction between spectral bands and cannot comprehensively consider the repr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/18/3602 |
| _version_ | 1797517389961625600 |
|---|---|
| author | Yufei Liu Xiaorun Li Ziqiang Hua Liaoying Zhao |
| author_facet | Yufei Liu Xiaorun Li Ziqiang Hua Liaoying Zhao |
| author_sort | Yufei Liu |
| collection | DOAJ |
| description | Hyperspectral band selection (BS) is an effective means to avoid the Hughes phenomenon and heavy computational burden in hyperspectral image processing. However, most of the existing BS methods fail to fully consider the interaction between spectral bands and cannot comprehensively consider the representativeness and redundancy of the selected band subset. To solve these problems, we propose an unsupervised effective band attention reconstruction framework for band selection (EBARec-BS) in this article. The framework utilizes the EBARec network to learn the representativeness of each band to the original band set and measures the redundancy between the bands by calculating the distance of each unselected band to the selected band subset. Subsequently, by designing an adaptive weight to balance the influence of the representativeness metric and redundancy metric on the band evaluation, a final band scoring function is obtained to select a band subset that well represents the original hyperspectral image and has low redundancy. Experiments on three well-known hyperspectral data sets indicate that compared with the existing BS methods, the proposed EBARec-BS is robust to noise bands and can effectively select the band subset with higher classification accuracy and less redundant information. |
| first_indexed | 2024-03-10T07:15:58Z |
| format | Article |
| id | doaj.art-f7c8fd9452f64acfad2fc2f10269d368 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T07:15:58Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f7c8fd9452f64acfad2fc2f10269d3682023-11-22T15:05:30ZengMDPI AGRemote Sensing2072-42922021-09-011318360210.3390/rs13183602EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band SelectionYufei Liu0Xiaorun Li1Ziqiang Hua2Liaoying Zhao3College of Electrical Engineering, Zhejiang University, No.38, Zheda Road, Xihu District, Hangzhou 310027, ChinaCollege of Electrical Engineering, Zhejiang University, No.38, Zheda Road, Xihu District, Hangzhou 310027, ChinaCollege of Electrical Engineering, Zhejiang University, No.38, Zheda Road, Xihu District, Hangzhou 310027, ChinaDepartment of Computer Science, Hangzhou Dianzi University, Hangzhou 310027, ChinaHyperspectral band selection (BS) is an effective means to avoid the Hughes phenomenon and heavy computational burden in hyperspectral image processing. However, most of the existing BS methods fail to fully consider the interaction between spectral bands and cannot comprehensively consider the representativeness and redundancy of the selected band subset. To solve these problems, we propose an unsupervised effective band attention reconstruction framework for band selection (EBARec-BS) in this article. The framework utilizes the EBARec network to learn the representativeness of each band to the original band set and measures the redundancy between the bands by calculating the distance of each unselected band to the selected band subset. Subsequently, by designing an adaptive weight to balance the influence of the representativeness metric and redundancy metric on the band evaluation, a final band scoring function is obtained to select a band subset that well represents the original hyperspectral image and has low redundancy. Experiments on three well-known hyperspectral data sets indicate that compared with the existing BS methods, the proposed EBARec-BS is robust to noise bands and can effectively select the band subset with higher classification accuracy and less redundant information.https://www.mdpi.com/2072-4292/13/18/3602hyperspectral image (HSI)unsupervised band selectionconvolutional autoencoder (CAE)band attention |
| spellingShingle | Yufei Liu Xiaorun Li Ziqiang Hua Liaoying Zhao EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection Remote Sensing hyperspectral image (HSI) unsupervised band selection convolutional autoencoder (CAE) band attention |
| title | EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection |
| title_full | EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection |
| title_fullStr | EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection |
| title_full_unstemmed | EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection |
| title_short | EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection |
| title_sort | ebarec bs effective band attention reconstruction network for hyperspectral imagery band selection |
| topic | hyperspectral image (HSI) unsupervised band selection convolutional autoencoder (CAE) band attention |
| url | https://www.mdpi.com/2072-4292/13/18/3602 |
| work_keys_str_mv | AT yufeiliu ebarecbseffectivebandattentionreconstructionnetworkforhyperspectralimagerybandselection AT xiaorunli ebarecbseffectivebandattentionreconstructionnetworkforhyperspectralimagerybandselection AT ziqianghua ebarecbseffectivebandattentionreconstructionnetworkforhyperspectralimagerybandselection AT liaoyingzhao ebarecbseffectivebandattentionreconstructionnetworkforhyperspectralimagerybandselection |