Academic Journal of Computing & Information Science, 2025, 8(8); doi: 10.25236/AJCIS.2025.080808.
Junhua Ku1,2, Jie Zhao3
1School of Information Science and Technology, Qiongtai Normal University, Haikou, Hainan, 571127, China
2Institute of Educational Big Data and Artificial Intelligence, Qiongtai Normal University, Haikou, Hainan, China
3School of Science, Qiongtai Normal University, Haikou, Hainan, 571127, China
In this paper, we present a novel Multi–Scale Graph Wavelet Convolutional Network for Hyperspectral and LiDAR Data Classification. The proposed MS-GWCN enables more effective learning of spatial–spectral relationships for pixel-wise classification. We conduct extensive experiments on the Houston 2013 dataset, which comprises 15 diverse land-cover classes. The results demonstrate that our method achieves significant improvements over baseline approaches, attaining an overall accuracy (OA) of 85.98%, an average accuracy (AA) of 88.39%, and a Kappa coefficient of 84.79%.
Multi-Scale Graph Convolutional Network, Deep Learning, Hyperspectral and Lidar Data Classification
Junhua Ku, Jie Zhao. Multi–Scale Graph Wavelet Convolutional Network for Hyperspectral and LiDAR Data Classification. Academic Journal of Computing & Information Science (2025), Vol. 8, Issue 8: 51-58. https://doi.org/10.25236/AJCIS.2025.080808.
[1] Li, H., Wang, F., & Zhang, X. (2020). A comprehensive review of hyperspectral and LiDAR data fusion techniques for remote sensing applications. Remote Sensing, 12(5), 1053.
[2] Yang, J., Wang, J., Sui, C. H., Long, Z., & Zhou, J. (2024). HSLiNets: Hyperspectral Image and LiDAR Data Fusion Using Efficient Dual Non-Linear Feature Learning Networks. arXiv Preprint.
[3] Zhao, B., & Wu, T. (2019). Early and late fusion methods for hyperspectral and LiDAR data classification: A comparative study. Remote Sensing of Environment, 231, 111305.
[4] Wang, F., Du, X., Zhang, W., Nie, L., Wang, H., Zhou, S., & Ma, J. (2024). Remote Sensing LiDAR and Hyperspectral Classification with Multi-Scale Graph Encoder–Decoder Network. Remote Sensing, 16(20), 3912.
[5] Chang, Y., & Liu, Y. (2018). Dimensionality reduction and feature fusion for hyperspectral and LiDAR data classification. International Journal of Applied Earth Observation and Geoinformation, 70, 111-121.
[6] Yang, J., Zhou, J., Wang, J., Tian, H., & Liew, A. W.-C. (2024). LiDAR-Guided Cross-Attention Fusion for Hyperspectral Band Selection and Image Classification. arXiv Preprint.
[7] Zhang, L., & Shi, W. (2021). Graph convolutional networks for remote sensing image classification: A survey. Remote Sensing, 13(4), 1-21.
[8] Wang, L., & Li, J. (2022). Dynamic graph convolutional network for hyperspectral and LiDAR data fusion. Sensors, 22(9), 3245.
[9] Zhao, B., & Wu, T. (2024). Classification of Hyperspectral and LiDAR Data by Transformer-Based Cross-Modal Self-Attentive Feature Fusion. Remote Sensing, 16(1), 94.
[10] Zhang, Z., Cai, Y., Liu, X., Zhang, M., & Meng, Y. (2024). An Efficient Graph Convolutional RVFL Network for Hyperspectral Image Classification. Remote Sensing, 16(1), 37.