L Liang, Y Zhang, S Zhang, J Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) have been widely employed for hyperspectral image (HSI) classification due to their powerful ability to extract local spatial features. However …
In recent years, significant breakthroughs have been achieved in hyperspectral image (HSI) processing using deep learning techniques, including classification, object detection, and …
EC Seyrek, M Uysal - Multimedia Tools and Applications, 2024 - Springer
Hyperspectral imaging has a strong capability respecting distinguishing surface objects due to the ability of collect hundreds of bands along the electromagnetic spectrum. Hyperspectral …
W Cai, M Gao, Y Ding, X Ning, X Bai… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Federated learning is a promising solution in several industries for cotraining models among distributed clients via centralized servers without leaving private user data on the devices …
C Lou, MAA Al-qaness, D AL-Alimi… - Geo-spatial …, 2024 - Taylor & Francis
In the rapidly evolving realm of remote sensing technology, the classification of Hyperspectral Images (HSIs) is a pivotal yet formidable task. Hindered by inherent …
W Cai, P Qian, Y Ding, M Bi, X Ning… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Although convolutional neural networks (CNNs) have shown superior performance to traditional machine learning algorithms for hyperspectral image (HSI) classification tasks …
Abstract Land Use/Land Cover (LULC) classification using hyperspectral images in remote sensing is a leading technology. However, LULC classification using hyperspectral images …
Traditional convolutional neural networks (CNNs) can be applied to obtain the spectral- spatial feature information from hyperspectral images (HSIs). However, they often introduce …
Z Li, Q Meng, F Guo, L Wang, W Huang, Y Hu… - International Journal of …, 2023 - Elsevier
Recently, graph convolutional networks (GCNs) has attracted wide attention on the wetland classification with limited samples. However, traditional approaches of superpixel …