Hyperspectral image classification by integrating attention-based LSTM and hybrid spectral networks
Though hyperspectral remote sensing images contain rich spatial and spectral information, they pose challenges in terms of feature extraction and mining. This paper describes the integration of a dimensionality reduction technique that employs spectral attention and Hybrid Spectral Networks (HybridS...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Taylor & Francis
2022
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/101758/ |
| _version_ | 1848863625138143232 |
|---|---|
| author | Ahmed AL-Kubaisi, Mohammed Shafri, Helmi Zulhaidi Mohd Ismail, Mohd Hasmadi Yusof, Mohd Johari Mohd Hashim, Shaiful Jahari |
| author_facet | Ahmed AL-Kubaisi, Mohammed Shafri, Helmi Zulhaidi Mohd Ismail, Mohd Hasmadi Yusof, Mohd Johari Mohd Hashim, Shaiful Jahari |
| author_sort | Ahmed AL-Kubaisi, Mohammed |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Though hyperspectral remote sensing images contain rich spatial and spectral information, they pose challenges in terms of feature extraction and mining. This paper describes the integration of a dimensionality reduction technique that employs spectral attention and Hybrid Spectral Networks (HybridSN) with spatial attention for hyperspectral image classification. The goal of this approach is to improve the ability to classify hyperspectral images by increasing the capabilities of spectral-spatial feature fusion. Experiments on three hyperspectral datasets (Indian Pines, University of Pavia, and Houston University) demonstrate that our method’s overall accuracy is 99.66%, 99.97%, and 99.17% under 20% of the training samples, respectively, which is superior to several well-known approaches. |
| first_indexed | 2025-11-15T13:35:53Z |
| format | Article |
| id | upm-101758 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T13:35:53Z |
| publishDate | 2022 |
| publisher | Taylor & Francis |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1017582024-08-05T07:32:30Z http://psasir.upm.edu.my/id/eprint/101758/ Hyperspectral image classification by integrating attention-based LSTM and hybrid spectral networks Ahmed AL-Kubaisi, Mohammed Shafri, Helmi Zulhaidi Mohd Ismail, Mohd Hasmadi Yusof, Mohd Johari Mohd Hashim, Shaiful Jahari Though hyperspectral remote sensing images contain rich spatial and spectral information, they pose challenges in terms of feature extraction and mining. This paper describes the integration of a dimensionality reduction technique that employs spectral attention and Hybrid Spectral Networks (HybridSN) with spatial attention for hyperspectral image classification. The goal of this approach is to improve the ability to classify hyperspectral images by increasing the capabilities of spectral-spatial feature fusion. Experiments on three hyperspectral datasets (Indian Pines, University of Pavia, and Houston University) demonstrate that our method’s overall accuracy is 99.66%, 99.97%, and 99.17% under 20% of the training samples, respectively, which is superior to several well-known approaches. Taylor & Francis 2022 Article PeerReviewed Ahmed AL-Kubaisi, Mohammed and Shafri, Helmi Zulhaidi Mohd and Ismail, Mohd Hasmadi and Yusof, Mohd Johari Mohd and Hashim, Shaiful Jahari (2022) Hyperspectral image classification by integrating attention-based LSTM and hybrid spectral networks. International Journal of Remote Sensing, 43 (1). 3450 - 3469. ISSN 0143-1161; ESSN: 1366-5901 https://www.tandfonline.com/doi/abs/10.1080/01431161.2022.2093621 10.1080/01431161.2022.2093621 |
| spellingShingle | Ahmed AL-Kubaisi, Mohammed Shafri, Helmi Zulhaidi Mohd Ismail, Mohd Hasmadi Yusof, Mohd Johari Mohd Hashim, Shaiful Jahari Hyperspectral image classification by integrating attention-based LSTM and hybrid spectral networks |
| title | Hyperspectral image classification by integrating attention-based LSTM and hybrid spectral networks |
| title_full | Hyperspectral image classification by integrating attention-based LSTM and hybrid spectral networks |
| title_fullStr | Hyperspectral image classification by integrating attention-based LSTM and hybrid spectral networks |
| title_full_unstemmed | Hyperspectral image classification by integrating attention-based LSTM and hybrid spectral networks |
| title_short | Hyperspectral image classification by integrating attention-based LSTM and hybrid spectral networks |
| title_sort | hyperspectral image classification by integrating attention-based lstm and hybrid spectral networks |
| url | http://psasir.upm.edu.my/id/eprint/101758/ http://psasir.upm.edu.my/id/eprint/101758/ http://psasir.upm.edu.my/id/eprint/101758/ |