ABSTRACT
In recent years, the utilization of both Graph Neural Network (GNN) and Convolutional Neural Network (CNN) in hyperspectral image (HSI) classification has gained significant attention. GNN, in particular, have proven effective in modelling irregular image regions. However, the limitations of single-scale graph structures and the focus on super-pixel nodes instead of pixel nodes within GNN hinder the extraction of pixel-level spectral-spatial features. To address these challenges and leverage the strengths of both CNN and GNN, we propose a novel heterogeneous deep network called CNN-Enhanced Multi-Scale Graph Attention Network (CEMSGAT). In CEMSGAT, we employ semi-supervised Local Fisher Discriminant Analysis (SELF) for dimensionality reduction and spectral-spatial convolution to extract surface features. Furthermore, our utilize super-pixel segmentation to create multi-scale graphs and implementing an improved graph attention algorithm at each scale to process the features obtained from the spectral-spatial convolutions. A spatial transformation operation is designed to enable seamless integration between the different scales of the graphs. Simultaneously, the features obtained from the previous spectral-spatial convolution are fed into a multilayer convolutional network for deep feature extraction and enhance the accuracy of the classification of connected areas between different land cover types calculated by the graph attention algorithm to achieve a clearer classification. Finally, the super-pixel level features derived from the multi-scale graph attention network are fused with the pixel level features obtained from the multilayer convolutional network for precise hyperspectral image classification. Experimental results on three hyperspectral datasets demonstrate the superiority of CEMSGAT over numerous state-of-the-art methods.
- Camps-Valls G. & Bruzzone L.(2005).Kernel-based methods for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing(6).Google ScholarCross Ref
- Wei Li 0032,Saurabh Prasad,James E. Fowler & Lori Mann Bruce.(2012).Locality-Preserving Dimensionality Reduction and Classification for Hyperspectral Image Analysis. IEEE Trans. Geoscience and Remote Sensing(4).Google Scholar
- Wei Li 0032,Jiabin Liu & Qian Du.(2016).Sparse and Low-Rank Graph for Discriminant Analysis of Hyperspectral Imagery.. IEEE Trans. Geoscience and Remote Sensing(7).Google Scholar
- Lu Li,Chengyi Wang,Jingbo Chen... & Prasad S. Thenkabail.(2017).Refinement of Hyperspectral Image Classification with Segment-Tree Filtering. Remote Sensing(1).Google Scholar
- Li, J., Du, Q., Xi, B., & Li, Y. (2018, September). Hyperspectral image classification via sample expansion for convolutional neural network. In 2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) (pp. 1-5). IEEE.Google ScholarCross Ref
- Aydemir, M. S., & Bilgin, G. (2017). Semisupervised hyperspectral image classification using small sample sizes. IEEE Geoscience and Remote Sensing Letters, 14(5), 621-625.Google ScholarCross Ref
- Liu, L., Zuo, D., Wang, Y., & Qu, H. (2022). Feedback-Enhanced Few-Shot Transformer Learning for Small-Sized Hyperspectral Image Classification. IEEE Geoscience and Remote Sensing Letters, 19, 1-5.Google Scholar
- Zheng, C., Wang, N., & Cui, J. (2019). Hyperspectral image classification with small training sample size using superpixel-guided training sample enlargement. IEEE Transactions on Geoscience and Remote Sensing, 57(10), 7307-7316.Google ScholarCross Ref
- Gualtieri, J. A., & Chettri, S. (2000, July). Support vector machines for classification of hyperspectral data. In IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No. 00CH37120) (Vol. 2, pp. 813-815). IEEE.Google Scholar
- Amini, S., Homayouni, S., & Safari, A. (2014, July). Semi-supervised classification of hyperspectral image using random forest algorithm. In 2014 IEEE geoscience and remote sensing symposium (pp. 2866-2869). IEEE.Google Scholar
- Tarabalka, Y., Fauvel, M., Chanussot, J., & Benediktsson, J. A. (2010). SVM-and MRF-based method for accurate classification of hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 7(4), 736-740.Google ScholarCross Ref
- Cao, J., & Wang, B. (2017). Embedding learning on spectral–spatial graph for semisupervised hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 14(10), 1805-1809.Google ScholarCross Ref
- Kang, X., Li, S., & Benediktsson, J. A. (2013). Spectral–spatial hyperspectral image classification with edge-preserving filtering. IEEE transactions on geoscience and remote sensing, 52(5), 2666-2677.Google Scholar
- Audebert, N., Le Saux, B., & Lefèvre, S. (2019). Deep learning for classification of hyperspectral data: A comparative review. IEEE geoscience and remote sensing magazine, 7(2), 159-173.Google Scholar
- Roy, S. K., Krishna, G., Dubey, S. R., & Chaudhuri, B. B. (2019). HybridSN: Exploring 3-D–2-D CNN feature hierarchy for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 17(2), 277-281.Google ScholarCross Ref
- Hong, D., Gao, L., Yao, J., Zhang, B., Plaza, A., & Chanussot, J. (2020). Graph convolutional networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 59(7), 5966-5978.Google ScholarCross Ref
- Hu, H., Yao, M., He, F., & Zhang, F. (2021). Graph neural network via edge convolution for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 19, 1-5.Google Scholar
- Sha, A., Wang, B., Wu, X., & Zhang, L. (2020). Semisupervised classification for hyperspectral images using graph attention networks. IEEE Geoscience and Remote Sensing Letters, 18(1), 157-161.Google ScholarCross Ref
- Brody, S., Alon, U., & Yahav, E. (2021). How attentive are graph attention networks?. arXiv preprint arXiv:2105.14491.Google Scholar
- Makantasis, K., Karantzalos, K., Doulamis, A., & Doulamis, N. (2015, July). Deep supervised learning for hyperspectral data classification through convolutional neural networks. In 2015 IEEE international geoscience and remote sensing symposium (IGARSS) (pp. 4959-4962). IEEE.Google Scholar
- Li, R., Zheng, S., Duan, C., Yang, Y., & Wang, X. (2020). Classification of hyperspectral image based on double-branch dual-attention mechanism network. Remote Sensing, 12(3), 582.Google ScholarCross Ref
- Zhong, Z., Li, J., Luo, Z., & Chapman, M. (2017). Spectral–spatial residual network for hyperspectral image classification: A 3-D deep learning framework. IEEE Transactions on Geoscience and Remote Sensing, 56(2), 847-858.Google ScholarCross Ref
- Hu, H., Yao, M., He, F., & Zhang, F. (2021). Graph neural network via edge convolution for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 19, 1-5.Google Scholar
- Wang, W., Dou, S., Jiang, Z., & Sun, L. (2018). A fast dense spectral–spatial convolution network framework for hyperspectral images classification. Remote sensing, 10(7), 1068.Google Scholar
Index Terms
- CNN -Enhanced Multi-Scale Graph Attention Network for Hyperspectral Image Classification
Recommendations
Multi-head attention with CNN and wavelet for classification of hyperspectral image
AbstractHyperspectral Image (HSI) is characterized by large number of bands with a high spectral resolution where continuous spectrum is measured for each pixel. This high volume therefore leads to challenges in processing the dataset. Objective of ...
Feature Fusion: Graph Attention Network and CNN Combing for Hyperspectral Image Classification
ICCCV '22: Proceedings of the 5th International Conference on Control and Computer VisionGraph convolutional networks (GCNs) have attracted increasing attention in hyperspectral image classification. However, most of the available GCN-based HSI classification methods treat superpixels as graph nodes, ignoring pixel-level spectral spatial ...
Morphologically dilated convolutional neural network for hyperspectral image classification
AbstractThe use of hyperspectral images is expanding rapidly with the advancement of remote sensing technologies. The precise classification of features for mapping land cover through hyperspectral images is a major research topic and a major ...
Highlights- Mathematical morphological operations are applied to input hyperspectral data to extract spatial feature map as output. This output is concatenated with the ...
Comments