13 January 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Fire detection using aerial platform is an important technology for forest surveillance. But the real-time detection capability is still a challenging problem. In this paper, an edge computing-based real-time forest fire detection strategy is designed using the unmanned aerial vehicle (UAV). The objective is to improve the timely response capability and the detection accuracy for early-stage small fires. The thermal and color images obtained from the onboard cameras are registered to the same scale and merged with appropriate proportions. These pre-processed dual-modal images become the input for training the fire detection network model. To deploy this model on the resource-constrained UAV edge computing device, it is compressed and accelerated to reduce size and enhance efficiency. Experiments based on self-made UAV dual-modal images of simulated fire scenarios and public datasets derived from real forest environments are conducted to validate the accuracy and speed of the proposed method. Experimental results show that, on the self-made dataset, the mAP is 93.76%, and the inference speed reaches 34.6FPS on the ground computer. On the public dataset, the mAP is 97.53%, and the inference speed reaches 16FPS on the edge computing device iCrest 2-s. Compared to several state-of-the-art methods, our proposed method achieves a good trade-off between accuracy and speed
17 June 2025 in IEEE Geoscience and Remote Sensing Letters
This paper presents a lightweight method for detecting forest fires using dual-modal remote sensing images captured by an unmanned aerial vehicle (UAV). The aim is to achieve efficient fire monitoring on a computationally resource-constrained UAV platform. The proposed detection network is based on the improved YOLOv8, which uses RGB image and thermal image as network input at the same time. A lightweight dual-modal feature fusion module named DFM is designed to effectively combine RGB and thermal features. The existing C2f module in YOLOv8 was replaced by the lightweight module C2f-F, along with the addition of the parameter-free attention module SimAM. This improvement improves the detection performance of the model while minimizing the model parameters. The evaluation experimental results on the FLAME 2 dataset show that the accuracy of the proposed dual-modal forest fire detection method reaches 98.4%, and the model size is only 2.9MB, which achieves a good balance between accuracy and number of parameters compared with other mainstream methods. Additionally, on the iCrest 2-s edge computing device, the detection speed reaches 20.67FPS, further confirming that this lightweight approach satisfies the real-time detection requirements for forest fires.
20 October 2025 in IEEE Internet of Things Journal
In this article, a novel early forest fire detection and localization system is proposed based on an autonomous aerial vehicle (AAV) equipped with RGB and thermal cameras. The forest fire detection is achieved by the proposed bimodal detection network. Fire localization, i.e., fire distance estimation, is realized by the proposed monocular depth estimation network and scale recovery strategy. To validate the effectiveness of the proposed method, the performance of the detection network is tested using the bimodal dataset AAVFire presented in this article and the public dataset FLAME2. The proposed depth estimation network is validated on the public dataset WildAAV. The experimental results show that the proposed bimodal detection network has an AP of 97.9% and 98.2% on the AAVFire and FLAME2 datasets, respectively, with a model parameter of 6.5 MB. Compared with other unimodal detection methods as well as bimodal detection methods, the detection method in this article performs well in terms of both the detection accuracy and the model lightweighting. The model parameter of the proposed monocular depth estimation network is only 0.69 MB, and the comparison results with other methods on the WildAAV dataset prove that the depth estimation method in this article achieves a good balance between accuracy and model lightweighting. Finally, the detection and distance estimation of early small fires are validated on the dataset AAVFire, demonstrating the effectiveness of the proposed method.