Edge Computing-Based Real-Time Forest Fire Detection Using UAV Thermal and Color Images

Abstract

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 article, an edge computing-based real-time forest fire detection strategy is designed using the uncrewed 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 preprocessed 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 34.6 FPS on the ground computer. On the public dataset, the mAP is 97.53%, and the inference speed reaches 16 FPS on the edge computing device iCrest 2-s. Compared to several state-of-the-art methods, our proposed method achieves a good tradeoff between accuracy and speed.