Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification
Graph convolutional networks (GCNs) are a promising approach for addressing the necessity for long-range information in hyperspectral image (HSI) classification. Researchers have attempted to develop classification methods that combine strong generalizations with effective classification. However, t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/23/5483 |
| _version_ | 1797399664706715648 |
|---|---|
| author | Jie Liu Renxiang Guan Zihao Li Jiaxuan Zhang Yaowen Hu Xueyong Wang |
| author_facet | Jie Liu Renxiang Guan Zihao Li Jiaxuan Zhang Yaowen Hu Xueyong Wang |
| author_sort | Jie Liu |
| collection | DOAJ |
| description | Graph convolutional networks (GCNs) are a promising approach for addressing the necessity for long-range information in hyperspectral image (HSI) classification. Researchers have attempted to develop classification methods that combine strong generalizations with effective classification. However, the current HSI classification methods based on GCN present two main challenges. First, they overlook the multi-view features inherent in HSIs, whereas multi-view information interacts with each other to facilitate classification tasks. Second, many algorithms perform a rudimentary fusion of extracted features, which can result in information redundancy and conflicts. To address these challenges and exploit the strengths of multiple features, this paper introduces an adaptive multi-feature fusion GCN (AMF-GCN) for HSI classification. Initially, the AMF-GCN algorithm extracts spectral and textural features from the HSIs and combines them to create fusion features. Subsequently, these three features are employed to construct separate images, which are then processed individually using multi-branch GCNs. The AMG-GCN aggregates node information and utilizes an attention-based feature fusion method to selectively incorporate valuable features. We evaluated the model on three widely used HSI datasets, i.e., Pavia University, Salinas, and Houston-2013, and achieved accuracies of 97.45%, 98.03%, and 93.02%, respectively. Extensive experimental results show that the classification performance of the AMF-GCN on benchmark HSI datasets is comparable to those of state-of-the-art methods. |
| first_indexed | 2024-03-09T01:44:23Z |
| format | Article |
| id | doaj.art-c54e09d0908d4d57bd19106d5f747dec |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T01:44:23Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c54e09d0908d4d57bd19106d5f747dec2023-12-08T15:24:46ZengMDPI AGRemote Sensing2072-42922023-11-011523548310.3390/rs15235483Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image ClassificationJie Liu0Renxiang Guan1Zihao Li2Jiaxuan Zhang3Yaowen Hu4Xueyong Wang5College of Management Science, Qufu Normal University, Rizhao 276800, ChinaCollege of Computer, National University of Defense Technology, Changsha 410073, ChinaFaculty of Computer Science, China University of Geosciences, Wuhan 430074, ChinaCollege of Management Science, Qufu Normal University, Rizhao 276800, ChinaCollege of Computer, National University of Defense Technology, Changsha 410073, ChinaCollege of Mathematics and Statistics, Tianshui Normal University, Tianshui 741000, ChinaGraph convolutional networks (GCNs) are a promising approach for addressing the necessity for long-range information in hyperspectral image (HSI) classification. Researchers have attempted to develop classification methods that combine strong generalizations with effective classification. However, the current HSI classification methods based on GCN present two main challenges. First, they overlook the multi-view features inherent in HSIs, whereas multi-view information interacts with each other to facilitate classification tasks. Second, many algorithms perform a rudimentary fusion of extracted features, which can result in information redundancy and conflicts. To address these challenges and exploit the strengths of multiple features, this paper introduces an adaptive multi-feature fusion GCN (AMF-GCN) for HSI classification. Initially, the AMF-GCN algorithm extracts spectral and textural features from the HSIs and combines them to create fusion features. Subsequently, these three features are employed to construct separate images, which are then processed individually using multi-branch GCNs. The AMG-GCN aggregates node information and utilizes an attention-based feature fusion method to selectively incorporate valuable features. We evaluated the model on three widely used HSI datasets, i.e., Pavia University, Salinas, and Houston-2013, and achieved accuracies of 97.45%, 98.03%, and 93.02%, respectively. Extensive experimental results show that the classification performance of the AMF-GCN on benchmark HSI datasets is comparable to those of state-of-the-art methods.https://www.mdpi.com/2072-4292/15/23/5483attention mechanismgraph convolution networkhyperspectral image classificationmulti-view |
| spellingShingle | Jie Liu Renxiang Guan Zihao Li Jiaxuan Zhang Yaowen Hu Xueyong Wang Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification Remote Sensing attention mechanism graph convolution network hyperspectral image classification multi-view |
| title | Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification |
| title_full | Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification |
| title_fullStr | Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification |
| title_full_unstemmed | Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification |
| title_short | Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification |
| title_sort | adaptive multi feature fusion graph convolutional network for hyperspectral image classification |
| topic | attention mechanism graph convolution network hyperspectral image classification multi-view |
| url | https://www.mdpi.com/2072-4292/15/23/5483 |
| work_keys_str_mv | AT jieliu adaptivemultifeaturefusiongraphconvolutionalnetworkforhyperspectralimageclassification AT renxiangguan adaptivemultifeaturefusiongraphconvolutionalnetworkforhyperspectralimageclassification AT zihaoli adaptivemultifeaturefusiongraphconvolutionalnetworkforhyperspectralimageclassification AT jiaxuanzhang adaptivemultifeaturefusiongraphconvolutionalnetworkforhyperspectralimageclassification AT yaowenhu adaptivemultifeaturefusiongraphconvolutionalnetworkforhyperspectralimageclassification AT xueyongwang adaptivemultifeaturefusiongraphconvolutionalnetworkforhyperspectralimageclassification |