SE-ResUNet Using Feature Combinations: A Deep Learning Framework for Accurate Mountainous Cropland Extraction Using Multi-Source Remote Sensing Data
Land · 25.04.2025 · 14 (5) · 937
DOI: 10.3390/land14050937 ↗Kurz gefasst
Fachartikel in der Zeitschrift Land, online erschienen am 25.04.2025. Verfasst von Ling Xiao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China, the Yunnan Province high-level Talent Training Support Program.
Abstract (Originalsprache)
The accurate extraction of mountainous cropland from remote sensing images remains challenging due to its fragmented plots, irregular shapes, and the terrain-induced shadows. To address this, we propose a deep learning framework, SE-ResUNet, that integrates Squeeze-and-Excitation (SE) modules into ResUNet to enhance feature representation. Leveraging Sentinel-1/2 imagery and DEM data, we fuse vegetation indices (NDVI/EVI), terrain features (Slope/TRI), and SAR polarization characteristics into 3-channel inputs, optimizing the network’s discriminative capacity. Comparative experiments on network architectures, feature combinations, and terrain conditions demonstrated the superiority of our approach. The results showed the following: (1) feature fusion (NDVI + TerrainIndex + SAR) had the best performance (OA: 97.11%; F1-score: 96.41%; IoU: 93.06%), significantly reducing shadow/cloud interference. (2) SE-ResUNet outperformed ResUNet by 3.53% for OA and 8.09% for IoU, emphasizing its ability to recalibrate channel-wise features and refine edge details. (3) The model exhibited robustness across diverse slopes/aspects (OA > 93.5%), mitigating terrain-induced misclassifications. This study provides a scalable solution for mountainous cropland mapping, supporting precision agriculture and sustainable land management.
Förderung
- the National Natural Science Foundation of China
- the Yunnan Province high-level Talent Training Support Program
Zitieren
APA
Xiao, L., Wang, J., Yang, K., Zhou, H., Meng, Q., He, Y., & Shen, S. (2025). SE-ResUNet Using Feature Combinations: A Deep Learning Framework for Accurate Mountainous Cropland Extraction Using Multi-Source Remote Sensing Data. Land, 14(5), 937. https://doi.org/10.3390/land14050937
Vancouver
Xiao L, Wang J, Yang K, Zhou H, Meng Q, He Y, et al. SE-ResUNet Using Feature Combinations: A Deep Learning Framework for Accurate Mountainous Cropland Extraction Using Multi-Source Remote Sensing Data. Land. 2025;14(5):937. doi:10.3390/land14050937
BibTeX
@article{Xiao2025,
author = {Xiao, Ling and Wang, Jiasheng and Yang, Kun and Zhou, Hui and Meng, Qianwen and He, Yue and Shen, Siyi},
title = {SE-ResUNet Using Feature Combinations: A Deep Learning Framework for Accurate Mountainous Cropland Extraction Using Multi-Source Remote Sensing Data},
journal = {Land},
year = {2025},
volume = {14},
number = {5},
pages = {937},
doi = {10.3390/land14050937}
}
EUVIMED