EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FireMambaNet: A Multi-Scale Mamba Network for Tiny Fire Segmentation in Satellite Imagery

Bo Song, Bo Li, Hong Huang, Zhiyong Zhang, Zhili Chen, Tao Yue, Yun Chen

Remote Sensing · 29.03.2026 · 18 (7) · 1021

DOI: 10.3390/rs18071021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 29.03.2026. Verfasst von Bo Song und 6 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Science and Technology Project, National Natural Science Foundation of China https://ror.org/01h0zpd94.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Satellite remote sensing plays an essential role in wildfire monitoring due to its large-scale observation capability. However, fire targets in satellite imagery are typically extremely small, sparsely distributed, and embedded in complex backgrounds, making accurate segmentation highly challenging for existing methods. To address these challenges, this paper proposes a multi-scale Mamba-based network for tiny fire segmentation, named FireMambaNet. The network adopts a nested U-shaped encoder-decoder architecture, primarily consisting of three modules: the Cross-layer Gated Residual U-shaped module (CG-RSU), the Fire-aware Directional Context Modulation module (FDCM), and the Multi-scale Mamba Attention Module (M2AM). The CG-RSU, as the core building block, adaptively suppresses background redundancy and enhances weak fire responses by extracting multi-scale features through cross-layer gating. The FDCM explicitly enhances the network’s ability to perceive anisotropic expansion features of fire points, such as those along the wind direction and terrain orientation, by modeling multi-directional context. The M2AM model employs a Mamba state-space model to suppress background interference through global context modeling during cross-scale feature fusion, while enhancing consistency among sparsely distributed tiny fire targets. In addition, experimental validation is conducted using two subsets from the Active Fire dataset, which have significant pixel-level sparse features: Oceania and Asia4. The results show that the proposed method significantly outperforms various mainstream CNN, Transformer, and Mamba baseline models on both datasets. It achieves an IoU of 88.51% and F1 score of 93.76% on the Oceania dataset, and an IoU of 85.65% and F1 score of 92.26% on the Asia4 dataset. Compared to the best-performing CNN baseline model, the IoU is improved by 1.81% and 2.07%, respectively. Overall, the FireMambaNet demonstrates significant advantages in detecting tiny fire points in complex backgrounds.

Förderung

  • Guangxi Science and Technology Project
  • National Natural Science Foundation of China https://ror.org/01h0zpd94

Zitieren

APA

Song, B., Li, B., Huang, H., Zhang, Z., Chen, Z., Yue, T., & Chen, Y. (2026). FireMambaNet: A Multi-Scale Mamba Network for Tiny Fire Segmentation in Satellite Imagery. Remote Sensing, 18(7), 1021. https://doi.org/10.3390/rs18071021

Vancouver

Song B, Li B, Huang H, Zhang Z, Chen Z, Yue T, et al. FireMambaNet: A Multi-Scale Mamba Network for Tiny Fire Segmentation in Satellite Imagery. Remote Sensing. 2026;18(7):1021. doi:10.3390/rs18071021

BibTeX
@article{Song2026,
  author = {Song, Bo and Li, Bo and Huang, Hong and Zhang, Zhiyong and Chen, Zhili and Yue, Tao and Chen, Yun},
  title = {FireMambaNet: A Multi-Scale Mamba Network for Tiny Fire Segmentation in Satellite Imagery},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {7},
  pages = {1021},
  doi = {10.3390/rs18071021}
}
Kostenlos starten →