SF-UNet: An Adaptive Cross-Level Residual Cascade for Forest Hyperspectral Image Classification Algorithm by Fusing SpectralFormer and U-Net
Open Access
Abstract
Traditional deep learning algorithms struggle to effectively utilize local spectral info in forest HS images and adequately capture subtle feature differences, often causing model confusion and misclassification. To tackle these issues, we present SF-UNet, a novel pixel-level classification network for forest HS images. It integrates the strengths of SpectralFormer and U-Net. First, the HGSE module generates semicomponent spectral nesting, strengthening local info element connections via spectral embedding. Next, the CAM within SpectralFormer serves as an auxiliary U-Net encoder. This allows cross-level jump connections and cascading through interlayer soft residuals, enhancing feature representation via cross-regional adaptive learning. Finally, the U-Net decoder is used for pixel-level classification. Experiments on forest Sentinel-2 data show that SF-UNet outperforms mainstream frameworks. While Vision Transformer has an 88.29% classification accuracy, SF-UNet achieves 95.28%, a significant 6.99% improvement. Moreover, SF-UNet excels in land cover change analysis using multi-temporal Sentinel-2 images. It can accurately capture subtle land use changes and maintain classification consistency across seasons and years. These results highlight SF-UNet’s effectiveness in forest remote sensing image classification and its potential application value in deep learning-based forest HS remote sensing image classification research.Keywords
Funding Information
- National Natural Science 441 Foundation of China (62161051, 2023AB38108, YNSC23119, 202501AT070452, 2023J0678, 2024D43)
- Guangxi Key Research and Development Program (62161051, 2023AB38108, YNSC23119, 202501AT070452, 2023J0678, 2024D43)
- Foundation of Yunnan Key Laboratory of Service Computing (62161051, 2023AB38108, YNSC23119, 202501AT070452, 2023J0678, 2024D43)
- Yunnan Provincial Basic Research Program (62161051, 2023AB38108, YNSC23119, 202501AT070452, 2023J0678, 2024D43)
- Yunnan Provincial Department of Education Science Research Fund Project (62161051, 2023AB38108, YNSC23119, 202501AT070452, 2023J0678, 2024D43)
- Yunnan University of Finance and Economics Science Research Fund Project (62161051, 2023AB38108, YNSC23119, 202501AT070452, 2023J0678, 2024D43)
This publication has 21 references indexed in Scilit:
- Combining deep learning and ontology reasoning for remote sensing image semantic segmentationKnowledge-Based Systems, 2022
- Review the state-of-the-art technologies of semantic segmentation based on deep learningNeurocomputing, 2022
- Semantic segmentation of high-resolution remote sensing images based on a class feature attention mechanism fused with Deeplabv3+Computers & Geosciences, 2022
- A review of deep learning methods for semantic segmentation of remote sensing imageryExpert Systems with Applications, 2021
- Semantic segmentation for partially occluded apple trees based on deep learningComputers and Electronics in Agriculture, 2021
- Context Union Edge Network for Semantic Segmentation of Small-Scale Objects in Very High Resolution Remote Sensing ImagesIEEE Geoscience and Remote Sensing Letters, 2020
- Remote sensing for agricultural applications: A meta-reviewRemote Sensing of Environment, 2020
- Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learningISPRS Journal of Photogrammetry and Remote Sensing, 2018
- Recent advances in convolutional neural networksPattern Recognition, 2018
- GIS numerical and remote sensing analyses of forest changes in the Toplica region for the period of 1953–2013Applied Geography, 2018