EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Weakly Supervised Forest Fire Segmentation in UAV Imagery Based on Foreground-Aware Pooling and Context-Aware Loss

Junling Wang, Yupeng Wang, Liping Liu, Hengfu Yin, Ning Ye, Can Xu

Remote Sensing · 19.07.2023 · 15 (14) · 3606

DOI: 10.3390/rs15143606 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.07.2023. Verfasst von Junling Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chinese Academy of Forestry, Zhejiang Science and Technology Major Program on Agricultural New Variety Breeding, Postgraduate Research & Practice Innovation Program of Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, tragedies caused by forest fires have been frequently reported. Forest fires not only result in significant economic losses but also cause environmental damage. The utilization of computer vision techniques and unmanned aerial vehicles (UAVs) for forest fire monitoring has become a primary approach to accurately locate and extinguish fires during their early stages. However, traditional computer-based methods for UAV forest fire image segmentation require a large amount of pixel-level labeled data to train the networks, which can be time-consuming and costly to acquire. To address this challenge, we propose a novel weakly supervised approach for semantic segmentation of fire images in this study. Our method utilizes self-supervised attention foreground-aware pooling (SAP) and context-aware loss (CAL) to generate high-quality pseudo-labels, serving as substitutes for manual annotation. SAP collaborates with bounding box and class activation mapping (CAM) to generate a background attention map, which aids in the generation of accurate pseudo-labels. CAL further improves the quality of the pseudo-labels by incorporating contextual information related to the target objects, effectively reducing environmental noise. We conducted experiments on two publicly available UAV forest fire datasets: the Corsican dataset and the Flame dataset. Our proposed method achieved impressive results, with IoU values of 81.23% and 76.43% for the Corsican dataset and the Flame dataset, respectively. These results significantly outperform the latest weakly supervised semantic segmentation (WSSS) networks on forest fire datasets.

Förderung

  • Chinese Academy of Forestry
  • Zhejiang Science and Technology Major Program on Agricultural New Variety Breeding
  • Postgraduate Research & Practice Innovation Program of Jiangsu Province

Zitieren

APA

Wang, J., Wang, Y., Liu, L., Yin, H., Ye, N., & Xu, C. (2023). Weakly Supervised Forest Fire Segmentation in UAV Imagery Based on Foreground-Aware Pooling and Context-Aware Loss. Remote Sensing, 15(14), 3606. https://doi.org/10.3390/rs15143606

Vancouver

Wang J, Wang Y, Liu L, Yin H, Ye N, Xu C. Weakly Supervised Forest Fire Segmentation in UAV Imagery Based on Foreground-Aware Pooling and Context-Aware Loss. Remote Sensing. 2023;15(14):3606. doi:10.3390/rs15143606

BibTeX
@article{Wang2023,
  author = {Wang, Junling and Wang, Yupeng and Liu, Liping and Yin, Hengfu and Ye, Ning and Xu, Can},
  title = {Weakly Supervised Forest Fire Segmentation in UAV Imagery Based on Foreground-Aware Pooling and Context-Aware Loss},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {14},
  pages = {3606},
  doi = {10.3390/rs15143606}
}
Kostenlos starten →