Lightweight wildfire smoke monitoring algorithm based on unmanned aerial vehicle vision

Forest fires have a serious impact on people’s living environment. Currently, drones enable rapid detection of forest fires. Due to the limited processing capabilities of onboard drones, the accuracy of smoke detection algorithms is low, and the processing speed is slow. This paper proposes an early wildfire smoke detection system designed for unmanned aerial vehicle (UAV) images, leveraging a modified YOLOv7 model, termed YOLOv7-MS(Modified Smoke). A dataset of more than 4,000 wildfire images was curated using existing UAV imagery. Our approach introduces several advancements. First, we propose a novel 3FIoU loss function to enhance stability and expedite convergence during training. Second, we optimize the backbone network by employing the FasterNet technique to reduce the number of parameters and increase the detection speed. Third, we address information loss and quality degradation problems by implementing the Asymptotic Feature Pyramid Network (AFPN) to counter indirect interactions between non-adjacent layers. Finally, we integrate a three-dimensional attention mechanism into the network to enhance focus on the target. Experimental findings showcase the efficacy of our YOLOv7-MS method, achieving a mean Average Precision (mAP) of 79.3% while maintaining a frame rate of 175 fps, outperforming other one-stage object detectors when evaluated on customized image datasets and public datasets.