SSATNet: Spectral-spatial attention transformer for hyperspectral corn image classification
Hyperspectral images are rich in spectral and spatial information, providing a detailed and comprehensive description of objects, which makes hyperspectral image analysis technology essential in intelligent agriculture. With various corn seed varieties exhibiting significant internal structural diff...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2024.1458978/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526595073867776 |
|---|---|
| author | Bin Wang Gongchao Chen Juan Wen Linfang Li Songlin Jin Yan Li Ling Zhou Weidong Zhang |
| author_facet | Bin Wang Gongchao Chen Juan Wen Linfang Li Songlin Jin Yan Li Ling Zhou Weidong Zhang |
| author_sort | Bin Wang |
| collection | DOAJ |
| description | Hyperspectral images are rich in spectral and spatial information, providing a detailed and comprehensive description of objects, which makes hyperspectral image analysis technology essential in intelligent agriculture. With various corn seed varieties exhibiting significant internal structural differences, accurate classification is crucial for planting, monitoring, and consumption. However, due to the large volume and complex features of hyperspectral corn image data, existing methods often fall short in feature extraction and utilization, leading to low classification accuracy. To address these issues, this paper proposes a spectral-spatial attention transformer network (SSATNet) for hyperspectral corn image classification. Specifically, SSATNet utilizes 3D and 2D convolutions to effectively extract local spatial, spectral, and textural features from the data while incorporating spectral and spatial morphological structures to understand the internal structure of the data better. Additionally, a transformer encoder with cross-attention extracts and refines feature information from a global perspective. Finally, a classifier generates the prediction results. Compared to existing state-of-the-art classification methods, our model performs better on the hyperspectral corn image dataset, demonstrating its effectiveness. |
| format | Article |
| id | doaj-art-b75e3aa1ce8949eba3486118de1b8a50 |
| institution | Kabale University |
| issn | 1664-462X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-b75e3aa1ce8949eba3486118de1b8a502025-01-16T16:15:59ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-01-011510.3389/fpls.2024.14589781458978SSATNet: Spectral-spatial attention transformer for hyperspectral corn image classificationBin Wang0Gongchao Chen1Juan Wen2Linfang Li3Songlin Jin4Yan Li5Ling Zhou6Weidong Zhang7School of Life Sciences, Henan Institute of Science and Technology, Xinxiang, ChinaSchool of Information Engineering, Henan Institute of Science and Technology, Xinxiang, ChinaSchool of Art, Henan University of Economics and Law, Zhengzhou, ChinaSchool of Information Engineering, Henan Institute of Science and Technology, Xinxiang, ChinaSchool of Information Engineering, Henan Institute of Science and Technology, Xinxiang, ChinaSchool of Software, Henan Institute of Science and Technology, Xinxiang, ChinaSchool of Information Engineering, Henan Institute of Science and Technology, Xinxiang, ChinaSchool of Information Engineering, Henan Institute of Science and Technology, Xinxiang, ChinaHyperspectral images are rich in spectral and spatial information, providing a detailed and comprehensive description of objects, which makes hyperspectral image analysis technology essential in intelligent agriculture. With various corn seed varieties exhibiting significant internal structural differences, accurate classification is crucial for planting, monitoring, and consumption. However, due to the large volume and complex features of hyperspectral corn image data, existing methods often fall short in feature extraction and utilization, leading to low classification accuracy. To address these issues, this paper proposes a spectral-spatial attention transformer network (SSATNet) for hyperspectral corn image classification. Specifically, SSATNet utilizes 3D and 2D convolutions to effectively extract local spatial, spectral, and textural features from the data while incorporating spectral and spatial morphological structures to understand the internal structure of the data better. Additionally, a transformer encoder with cross-attention extracts and refines feature information from a global perspective. Finally, a classifier generates the prediction results. Compared to existing state-of-the-art classification methods, our model performs better on the hyperspectral corn image dataset, demonstrating its effectiveness.https://www.frontiersin.org/articles/10.3389/fpls.2024.1458978/fullcorn identificationhyperspectral image classificationdeep learningmorphologyimage classification |
| spellingShingle | Bin Wang Gongchao Chen Juan Wen Linfang Li Songlin Jin Yan Li Ling Zhou Weidong Zhang SSATNet: Spectral-spatial attention transformer for hyperspectral corn image classification Frontiers in Plant Science corn identification hyperspectral image classification deep learning morphology image classification |
| title | SSATNet: Spectral-spatial attention transformer for hyperspectral corn image classification |
| title_full | SSATNet: Spectral-spatial attention transformer for hyperspectral corn image classification |
| title_fullStr | SSATNet: Spectral-spatial attention transformer for hyperspectral corn image classification |
| title_full_unstemmed | SSATNet: Spectral-spatial attention transformer for hyperspectral corn image classification |
| title_short | SSATNet: Spectral-spatial attention transformer for hyperspectral corn image classification |
| title_sort | ssatnet spectral spatial attention transformer for hyperspectral corn image classification |
| topic | corn identification hyperspectral image classification deep learning morphology image classification |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2024.1458978/full |
| work_keys_str_mv | AT binwang ssatnetspectralspatialattentiontransformerforhyperspectralcornimageclassification AT gongchaochen ssatnetspectralspatialattentiontransformerforhyperspectralcornimageclassification AT juanwen ssatnetspectralspatialattentiontransformerforhyperspectralcornimageclassification AT linfangli ssatnetspectralspatialattentiontransformerforhyperspectralcornimageclassification AT songlinjin ssatnetspectralspatialattentiontransformerforhyperspectralcornimageclassification AT yanli ssatnetspectralspatialattentiontransformerforhyperspectralcornimageclassification AT lingzhou ssatnetspectralspatialattentiontransformerforhyperspectralcornimageclassification AT weidongzhang ssatnetspectralspatialattentiontransformerforhyperspectralcornimageclassification |