Wildfires pose serious threats to ecosystems, human life, and climate stability, underscoring the urgent need for accurate monitoring. Traditional approaches based on either optical or thermal imagery often fail under challenging conditions such as lighting interference, varying data sources, or small-scale flames, as they do not account for the hierarchical nature of feature representations. To overcome these limitations, we propose a multimodal deep learning framework that integrates visible (RGB) and thermal infrared (TIR) imagery for accurate wildfire segmentation. The framework incorporates edge-guided supervision and multilevel fusion to capture fine fire boundaries while exploiting complementary information from both modalities. To assess its effectiveness, we constructed a multi-scale flame segmentation dataset and validated the method across diverse conditions, including different data sources, lighting environments, and five flame size categories ranging from small to large. Experimental results show that BFCNet achieves an IoU of 88.25% and an F1 score of 93.76%, outperforming both single-modality and existing multimodal approaches across all evaluation tasks. These results demonstrate the potential of multimodal deep learning to enhance wildfire monitoring, offering practical value for disaster management, ecological protection, and the deployment of autonomous aerial surveillance systems.

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.

Tiny fire spot detection in UAV images under complex forest backgrounds remains challenging due to tiny target size, sparse distribution, weak feature responses, and background interference. This paper proposes a Multi-Scale Feature Enhancement Network (MSF-YOLO) for tiny fire spot detection. Specifically, a lightweight C2f-ARG module is designed by integrating Ghost feature generation and channel recalibration mechanisms to enhance weak fire spot representation while reducing redundant features. A C2f-LGPA module is designed to model local fine-grained information and global contextual dependencies, improving target discrimination under complex forest environments. Additionally, a P2 tiny-object detection branch is incorporated to preserve spatial details and enhance the perception capability of tiny targets. A UAV forest fire spot detection dataset was constructed, and extensive experiments were conducted. Experimental results demonstrate that MSF-YOLO achieves a Recall of 79.27, representing an improvement of 5.09% over the baseline YOLOv8s. The mAP@0.5 and mAP@0.5:0.95 values are improved by 3.99% and 5.35%, respectively. Moreover, compared with eight improved YOLO-based small-object detectors, MSF-YOLO achieves superior overall detection performance, with a 1.35% improvement in mAP@0.5 over the best-performing comparison method. The proposed MSF-YOLO effectively addresses the challenge of early-stage tiny fire spot detection in forest fire.