Bathymetric-Based Band Selection Method for Hyperspectral Underwater Target Detection
Band selection has imposed great impacts on hyperspectral image processing in recent years. Unfortunately, few existing methods are proposed for hyperspectral underwater target detection (HUTD). In this paper, a novel unsupervised band selection method is proposed for HUTD by embedding the bathymetr...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/19/3798 |
| _version_ | 1797515857119674368 |
|---|---|
| author | Jiahao Qi Zhiqiang Gong Aihuan Yao Xingyue Liu Yongqian Li Yichuang Zhang Ping Zhong |
| author_facet | Jiahao Qi Zhiqiang Gong Aihuan Yao Xingyue Liu Yongqian Li Yichuang Zhang Ping Zhong |
| author_sort | Jiahao Qi |
| collection | DOAJ |
| description | Band selection has imposed great impacts on hyperspectral image processing in recent years. Unfortunately, few existing methods are proposed for hyperspectral underwater target detection (HUTD). In this paper, a novel unsupervised band selection method is proposed for HUTD by embedding the bathymetric model into the band selection process. Considering the dependence between targets and background, a bathymetric latent spectral representation learning scheme is designed to investigate a physically meaningful subspace where the desired targets are the most distinguishable from the background. This calculated subspace is exploited as a reference to select out desired bands based on the spectral distance metric. Then, we propose an iteration-based band subset generation strategy for the sake of promoting the diversity of the band selection results and taking full advantage of the ample spectral information. Moreover, a representative band selection approach based on sparse representation is also conducted to eliminate the redundant information among adjacent bands. The band selection result is eventually achievable by connecting the representative bands of all the band subsets. Qualitative and quantitative evaluations demonstrate the effectiveness and efficiency of the proposed method in comparison with state-of-the-art band selection methods. |
| first_indexed | 2024-03-10T06:53:10Z |
| format | Article |
| id | doaj.art-90068df7a3ee481ebf0a463528503cef |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T06:53:10Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-90068df7a3ee481ebf0a463528503cef2023-11-22T16:41:00ZengMDPI AGRemote Sensing2072-42922021-09-011319379810.3390/rs13193798Bathymetric-Based Band Selection Method for Hyperspectral Underwater Target DetectionJiahao Qi0Zhiqiang Gong1Aihuan Yao2Xingyue Liu3Yongqian Li4Yichuang Zhang5Ping Zhong6National Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, ChinaNational Innovation Institute of Defense Technology, Chinese Academy of Military Science, Beijing 110000, ChinaNational Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, ChinaBand selection has imposed great impacts on hyperspectral image processing in recent years. Unfortunately, few existing methods are proposed for hyperspectral underwater target detection (HUTD). In this paper, a novel unsupervised band selection method is proposed for HUTD by embedding the bathymetric model into the band selection process. Considering the dependence between targets and background, a bathymetric latent spectral representation learning scheme is designed to investigate a physically meaningful subspace where the desired targets are the most distinguishable from the background. This calculated subspace is exploited as a reference to select out desired bands based on the spectral distance metric. Then, we propose an iteration-based band subset generation strategy for the sake of promoting the diversity of the band selection results and taking full advantage of the ample spectral information. Moreover, a representative band selection approach based on sparse representation is also conducted to eliminate the redundant information among adjacent bands. The band selection result is eventually achievable by connecting the representative bands of all the band subsets. Qualitative and quantitative evaluations demonstrate the effectiveness and efficiency of the proposed method in comparison with state-of-the-art band selection methods.https://www.mdpi.com/2072-4292/13/19/3798band selectionbathymetric modelsubspacesparse representation |
| spellingShingle | Jiahao Qi Zhiqiang Gong Aihuan Yao Xingyue Liu Yongqian Li Yichuang Zhang Ping Zhong Bathymetric-Based Band Selection Method for Hyperspectral Underwater Target Detection Remote Sensing band selection bathymetric model subspace sparse representation |
| title | Bathymetric-Based Band Selection Method for Hyperspectral Underwater Target Detection |
| title_full | Bathymetric-Based Band Selection Method for Hyperspectral Underwater Target Detection |
| title_fullStr | Bathymetric-Based Band Selection Method for Hyperspectral Underwater Target Detection |
| title_full_unstemmed | Bathymetric-Based Band Selection Method for Hyperspectral Underwater Target Detection |
| title_short | Bathymetric-Based Band Selection Method for Hyperspectral Underwater Target Detection |
| title_sort | bathymetric based band selection method for hyperspectral underwater target detection |
| topic | band selection bathymetric model subspace sparse representation |
| url | https://www.mdpi.com/2072-4292/13/19/3798 |
| work_keys_str_mv | AT jiahaoqi bathymetricbasedbandselectionmethodforhyperspectralunderwatertargetdetection AT zhiqianggong bathymetricbasedbandselectionmethodforhyperspectralunderwatertargetdetection AT aihuanyao bathymetricbasedbandselectionmethodforhyperspectralunderwatertargetdetection AT xingyueliu bathymetricbasedbandselectionmethodforhyperspectralunderwatertargetdetection AT yongqianli bathymetricbasedbandselectionmethodforhyperspectralunderwatertargetdetection AT yichuangzhang bathymetricbasedbandselectionmethodforhyperspectralunderwatertargetdetection AT pingzhong bathymetricbasedbandselectionmethodforhyperspectralunderwatertargetdetection |