基于改进YOLOv3的红外电力设备目标检测模型

Target Detection Model of Infrared Power Equipment based on Improved YOLOv3

为了实现红外电力设备图像的快速准确检测,在目标检测网络YOLOv3的基础上,提出了一个实时检测红外电力设备图像的轻量级目标检测模型,通过改进特征提取网络、加入轻量级注意力模块和改变特征层检测尺度等方式,提升模型的检测精度和速度。实验表明,本文中的方法相比于YOLOv3,在检测速度相近的同时,具有更高的检测精度,为电力设备红外图像智能检测提供了新的思路。

In order to achieve rapid and accurate detection of infrared power equipment images,based on the target detection network YOLOv3,a lightweight target detection model for real-time detection of infrared power equipment images is proposed.The feature extraction network is improved and a lightweight attention module is added.And change the detection scale of the feature layer to improve the detection accuracy and speed of the model.Experiments show that compared with YOLOv3,the method in this paper has higher detection accuracy while the detection speed is similar,which provides a new idea for the intelligent detection of infrared images of power equipment.