基于Transformer改进YOLOv5的山火检测方法研究

Research on improved YOLOv5forest fire detection method based on Transformer

构建智慧生态林业中核心环节为对森林火灾的监测及防范,为了第一时间扑灭火源防止火势蔓延并将可能发生的山火隐患于第一时间消除,提出了两种适用于无人机高空巡检的森林火灾检测模型YOLO_MC与YOLO_MCLite。其中YOLO_MC可对标准图像中的明火及烟雾进行检测,并基于YOLO_MC模型进行轻量化设计,提出适用于热图像中高温区域的检测模型YOLO_MCLite。在网络结构的设计中,首先在常规的卷积神经网络中融合加入了Transformer模型,提升了主干网络对于全局特征信息的感知能力;同时对Transformer模型进行轻量化设计,首先在网络结构上通过分组计算的形式减少tokens数量以降低计算量,其次通过通道注意力机制对特征块的通道数进行去冗余并提权来减少tokens的维度参数以降低计算复杂度,并且采用蒸馏算法从所设计的网络中提取出超轻量化网络应用于无人机红外影像的森林高温点检测,以预防森林火灾的发生。经过实验得出以下数据:所设计的两个检测模型中,其中适用于标准图像中对于明火及烟雾的检测准确率可达94.8%,适用于热图像对高温点的检测准确率可达97.2%,并且在英伟达JETSON TX2嵌入式设备上测试两个模型的帧率分别达到了22.5以及32.4。实验结果表明本文所设计网络能够对森林火灾进行有效检测并可以通过检测高温点及时预防火灾发生。

The core link in the construction of smart ecological forestry is the monitoring and prevention of forest fires.In order to put out the fire source to prevent the spread of fire and eliminate the hidden danger of forest fires in the first time,two forest fire detection models,YOLO_MC and YOLO_MCLite,are proposed for UAV aerial inspection.Among them,YOLO_MC can detect open flame and smoke in standard images.Based on the lightweight of YOLO_MC model,a detection model YOLO_MCLite suitable for high temperature region in thermal images is proposed.In the design of the network structure,the Transformer model is firstly integrated into the conventional convolutional neural network,which improves the perception ability of the backbone network for global feature information;at the same time,lightweight design of the Transformer model is performed.First,reduce the number of tokens in the form of group computation on the network structure to reduce the amount of tokens.Second,de-redundant and weighted the number of channels in feature blocks through channel attention mechanism to reduce the dimension parameters of tokens to reduce the computational complexity.And the distillation algorithm is also used to extract the ultra-lightweight network from the designed network and apply it to the detection of forest high temperature points in the infrared image of the UAV to prevent the occurrence of forest fires.After experiments,the following data are obtained:the detection accuracy of the designed detection model for open flame and smoke can reach 94.8%,and the detection accuracy for high temperature points can reach 97.2%.And the test frame rate on the NVIDIA JETSON TX2embedded device reached 22.5and 32.4respectively.The experimental results show that the network designed in this paper can effectively detect forest fires and prevent fires in time by detecting high temperature points.