Robust and Transferable Elevation-Aware Multi-Resolution Network for Semantic Segmentation of LiDAR Point Clouds in Powerline Corridors
Remote Sensing · 27.09.2025 · 17 (19) · 3318
DOI: 10.3390/rs17193318 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 27.09.2025. Verfasst von Yifan Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research on Wide Area Identification Technology of Potential External Force Damage Hazards in Transmission Lines by Satellite Earth Alliance.
Abstract (Originalsprache)
Semantic segmentation of LiDAR point clouds in powerline corridor environments is crucial for the intelligent inspection and maintenance of power infrastructure. However, existing deep learning methods often underperform in such scenarios due to severe class imbalance, sparse and long-range structures, and complex elevation variations. We propose EMPower-Net, an Elevation-Aware Multi-Resolution Network, which integrates an Elevation Distribution (ED) module to enhance vertical geometric awareness and a Multi-Resolution (MR) module to enhance segmentation accuracy for corridor structures with varying object scales. Experiments on real-world datasets from Yunnan and Guangdong show that EMPower-Net outperforms state-of-the-art baselines, especially in recognizing power lines and towers with high structural fidelity under occlusion and dense vegetation. Ablation studies confirm the complementary effects of the MR and ED modules, while transfer learning results reveal strong generalization with minimal performance degradation across different powerline regions. Additional tests on urban datasets indicate that the proposed elevation features are also effective for vertical structure recognition beyond powerline scenarios.
Förderung
- Research on Wide Area Identification Technology of Potential External Force Damage Hazards in Transmission Lines by Satellite Earth Alliance
Zitieren
APA
Wang, Y., Li, S., Wang, G., Jiang, W., Yan, Y., & Sun, J. (2025). Robust and Transferable Elevation-Aware Multi-Resolution Network for Semantic Segmentation of LiDAR Point Clouds in Powerline Corridors. Remote Sensing, 17(19), 3318. https://doi.org/10.3390/rs17193318
Vancouver
Wang Y, Li S, Wang G, Jiang W, Yan Y, Sun J. Robust and Transferable Elevation-Aware Multi-Resolution Network for Semantic Segmentation of LiDAR Point Clouds in Powerline Corridors. Remote Sensing. 2025;17(19):3318. doi:10.3390/rs17193318
BibTeX
@article{Wang2025,
author = {Wang, Yifan and Li, Shenhong and Wang, Guofang and Jiang, Wanshou and Yan, Yijun and Sun, Jianwen},
title = {Robust and Transferable Elevation-Aware Multi-Resolution Network for Semantic Segmentation of LiDAR Point Clouds in Powerline Corridors},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {19},
pages = {3318},
doi = {10.3390/rs17193318}
}
EUVIMED