基于深度学习的烟雾与火焰目标检测算法
A Deep Learning-Based Algorithm for Smoke and Flame Detection

烟雾与火焰检测在安全领域中具有重要的实际应用，尤其是在复杂环境下，如何精准识别烟雾与火焰目标仍面临较大挑战。本文提出了一种改进的YOLOv8算法，引入CBAM (Convolutional Block Attention Module)注意力机制，增强了网络对不同尺度特征的关注能力，从而提高了小目标和复杂场景下的检测精度。实验结果表明，改进后的YOLOv8模型相比于原YOLOv8模型，平均精度均值(mean Average Precision, mAP)提升了0.57个百分点，对烟雾与火焰两类目标的检测效果较好。
Flame and smoke detection plays an important role in safety applications, especially in complex environments, where accurately identifying smoke and flame targets remains a significant challenge. This paper proposes an improved YOLOv8 algorithm, which introduces the CBAM (Convolutional Block Attention Module) attention mechanism to enhance the network’s ability to focus on features of different scales, thereby improving detection accuracy for small targets and complex scenes. The experimental results demonstrate that the improved YOLOv8 model has seen an enhancement of 0.57 percentage points in mean Average Precision (mAP) compared to the original YOLOv8 model, exhibiting superior detection performance for both smoke and flame targets.