Supervised Hyperspectral Remote Sensing Image Classification Using Graph Attention Networks with Hybrid Pooling
Abstract
Traditional remote sensing image surveys rely on field observations, which have shortcomings such as low efficiency and limited coverage, making it difficult to meet the needs of urban planning and management. In response to this, this article conducts in-depth research on remote sensing image classification methods based on graph neural networks (GNN). This study adopts a joint framework of GAT (Graph Attention Network)+SLC (Simple Linear Iterative Clustering)+Hybrid Pooling. Use SLIC algorithm to perform superpixel segmentation on hyperspectral data and construct a graph structure that integrates spectral spatial features. Utilizing GAT's attention mechanism to enhance feature interaction among neighboring nodes, combined with a hybrid pooling strategy to balance feature dimensionality reduction and key information preservation. The experiment was conducted on the public datasets WHU-RS19 and UC Merced, using traditional CNN, random forest, and minimum distance methods as baseline models. The significance of the differences was verified through independent sample t-test. By expanding the sample coverage, optimizing the model regularization strategy, and continuously iterating training, the generalization performance of the model has been significantly improved. Therefore, from the comparison of classification performance, graph NN classification is superior to minimum distance classification. This method utilizes perspective remote sensing data to achieve accurate ground target classification and dynamic change information extraction, providing reliable data support for urban land survey and management.References
Yan M, Zhao H, Li Y, et al. Multi-classification and recognition of hyperspectral remote sensing objects based on convolutional neural network. Laser & Optoelectronics Progress, 2019, 85(17):11-27.
Li Y, Lin H. Multi-spectral remote sensing image classification of ground coverage based on CNN. Microprocessors, 2019, 78(11):28-63.
Niruban, R., & Deepa, R. (2023). Graph neural network-based remote target classification in hyperspectral imaging. International Journal of Remote Sensing, 44(14), 4465-4485.
Wang X, Xie H. A review on applications of remote sensing and geographic information systems (GIS) in water resources and flood risk management. Water, 2018, 10(5): 608.
Cheng G, Han J, Lu X. Remote sensing image scene classification: benchmark and state of the art. arXiv e-prints, 2017, 67(27):38-49.
Sebastianelli A, Zaidenberg D A, Spiller D. On circuit-based hybrid quantum neural networks for remote sensing imagery classification. arXiv e-prints, 2021, 67(11):47-85.
Xie F, Gai H, Yang J. Hyperspectral remote sensing image classification based on ISSMFA and LMPNN. Journal of Chinese Computer Systems, 2018, 39(4):58-61.
Lu G, Chen L. Remote sensing image classification based on deep convolution neural network. Journal of Taiyuan Normal University (Natural Science Edition), 2019, 67(14):28-77.
Ding J, Chen S. Hyper-spectral remote sensing image classification based on residual 3D convolutional neural network. Laser Journal, 2019, 69(12):28-85.
Wang A, Zhang X, Han C et al. Remote sensing image super-resolution reconstruction based on deep convolution neural network. Journal of Natural Science of Heilongjiang University, 2018, 39(18):58-87.
Zhou H, Diao L, Zheng S, et al. Remote sensing monitoring of paddy field expansion in Fuyuan during 1990-2013. Chinese Agricultural Science Bulletin, 2018, 67(17):24-55.
Zhang L. Dynamic monitoring method of large-scale terrain change based on UAV remote sensing image. Journal of Heilongjiang University of Technology (Comprehensive Edition), 2019, 39(7):28-54.
Xiao Z. Feature extraction based on remote sensing image fusion. Electronic Science and Technology, 2017, 31(4):17-44.
Jia H, Dai H. Remote sensing image classification based on local partial classifier and deep neural network. Machine Tool & Hydraulics, 2017, 37(5):24-57.
Zhu J, Hu H, Fan W. Research on hyperspectral remote sensing image classification based on deep neural networks. Journal of Equipment Academy, 2017, 66(30):27-69.
Hua Y, Mou L, Zhu X. Recurrently exploring class-wise attention in a hybrid convolutional and bidirectional LSTM network for multi-label aerial image classification. ISPRS Journal of Photogrammetry and Remote Sensing: Official Publication of the International Society for Photogrammetry and Remote Sensing (ISPRS), 2019, 38(17):22-35.
Lu J, Cheng Y. Application of Bs-Gep algorithm in water conservancy remote sensing image classification. Computers, Materials and Continuum, 2022, 32(11):17-42.
Ye M, Ji L, Luo T et al. A lightweight model of VGG-U-Net for remote sensing image classification. Computers, Materials and Continuum, 2022, 33(2):34-62.
Yang Q Y, Wang W A, Ma X D. Remote sensing image building extraction based on deep convolutional neural network. Journal of Physics: Conference Series, 2019, 36(12):14-31.
Lu F, Zhang X, Wang L et al. Research on information extraction of urban impermeable surface based on remote sensing image. Journal of Heilongjiang Institute of Technology, 2018, 35(11):10-25.
Gaafar, A. S., Dahr, J. M., & Hamoud, A. K. (2022). Comparative analysis of performance of deep learning classification approach based on LSTM-RNN for textual and image datasets. Informatica, 46(5).
Ezhilarasan, M. (2025). A Review of Deep Learning-Based Feature Extraction Techniques for Iris Image Analysis. Informatica, 49(21).
DOI:
https://doi.org/10.31449/inf.v49i20.9769Downloads
Published
How to Cite
Issue
Section
License
I assign to Informatica, An International Journal of Computing and Informatics ("Journal") the copyright in the manuscript identified above and any additional material (figures, tables, illustrations, software or other information intended for publication) submitted as part of or as a supplement to the manuscript ("Paper") in all forms and media throughout the world, in all languages, for the full term of copyright, effective when and if the article is accepted for publication. This transfer includes the right to reproduce and/or to distribute the Paper to other journals or digital libraries in electronic and online forms and systems.
I understand that I retain the rights to use the pre-prints, off-prints, accepted manuscript and published journal Paper for personal use, scholarly purposes and internal institutional use.
In certain cases, I can ask for retaining the publishing rights of the Paper. The Journal can permit or deny the request for publishing rights, to which I fully agree.
I declare that the submitted Paper is original, has been written by the stated authors and has not been published elsewhere nor is currently being considered for publication by any other journal and will not be submitted for such review while under review by this Journal. The Paper contains no material that violates proprietary rights of any other person or entity. I have obtained written permission from copyright owners for any excerpts from copyrighted works that are included and have credited the sources in my article. I have informed the co-author(s) of the terms of this publishing agreement.
Copyright © Slovenian Society Informatika
