EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semi-supervised segmentation of forest fires from UAV remote sensing images via panoramic feature fusion and pixel contrastive learning

Yuchen Ma, Haifeng Lin

Frontiers in Forests and Global Change · 17.11.2025 · 8

DOI: 10.3389/ffgc.2025.1669707 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Forests and Global Change, online erschienen am 17.11.2025. Verfasst von Yuchen Ma und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Wildfire detection and segmentation play a critical role in environmental monitoring and disaster prevention. However, existing deep learning-based segmentation models often struggle to identify wildfire boundaries accurately due to complex image features and limited annotated data.

Methods

We propose a novel segmentation network called PPCNet, which integrates three key modules: a Panoramic Feature Fusion (PFF) module for multi-scale feature extraction, a Dense Feature Fusion Encoder (DFFE) to capture contextual details, and a Local Detail Compensation (LDC) loss function to enhance boundary accuracy. Additionally, we design a pseudo-label optimization framework to leverage unlabeled data effectively.

Results

Experiments were conducted on multiple wildfire datasets, and the results show that PPCNet achieves superior performance compared to state-of-the-art methods. Our model demonstrates significant improvements in segmentation accuracy and boundary localization, validated through quantitative metrics and visual comparisons.

Discussion

The integration of PFF, DFFE, and LDC components enables PPCNet to generalize well across different wildfire scenarios. The use of pseudo-labeling further enhances performance without requiring additional labeled data, making it suitable for real-world deployment in wildfire monitoring systems.

Zitieren

APA

Ma, Y., & Lin, H. (2025). Semi-supervised segmentation of forest fires from UAV remote sensing images via panoramic feature fusion and pixel contrastive learning. Frontiers in Forests and Global Change, 8. https://doi.org/10.3389/ffgc.2025.1669707

Vancouver

Ma Y, Lin H. Semi-supervised segmentation of forest fires from UAV remote sensing images via panoramic feature fusion and pixel contrastive learning. Frontiers in Forests and Global Change. 2025;8. doi:10.3389/ffgc.2025.1669707

BibTeX
@article{Ma2025,
  author = {Ma, Yuchen and Lin, Haifeng},
  title = {Semi-supervised segmentation of forest fires from UAV remote sensing images via panoramic feature fusion and pixel contrastive learning},
  journal = {Frontiers in Forests and Global Change},
  year = {2025},
  volume = {8},
  doi = {10.3389/ffgc.2025.1669707}
}
Kostenlos starten →