Early fire smoke detection model based on YOLOv5

Abstract

Aiming at the low detection accuracy of existing fire early smoke target detection models, this paper designs a fire early fire smoke detection model based on YOLOv5. First, check the data to understand the fire-prone scenes and divide them into two categories: indoor and outdoor; Second, according to different scenes, considering the influence of environmental factors such as light and scale, manually collect and label the smoke pictures in the early stage of the fire; Third, The Focal Loss loss function is used instead to alleviate the problem of unbalanced classification in the data set. Experiments on the self-made early fire smoke dataset show that the improved network mAP value is 2.3% higher than that of YOLOv5. The experimental results verify the effectiveness of the algorithm.