一种改进YOLOv8n的电力设备红外图像识别网络OA
An Improved Infrared Image Recognition Network for Power Equipment Based on YOLOv8n
针对目前电力设备红外图像识别算法存在检测精度低和模型计算量大的问题,提出一种改进YOLOv8n的电力设备红外图像识别网络YOLOv8n-DCSW.在YOLOv8n主干网络中添加坐标注意力(Coordinate Attention,CA)并使用可变形卷积网络(Deformable Convolution Network,DCN)替换残差模块中的标准卷积,加强复杂环境下对小目标的关注度,提高识别精度;将颈部网络更换为Sim-neck,降低模型运算量;…查看全部>>
In view of the problems of low detection accuracy and large model calculation load in current infrared image recognition algorithms for power equipment,an improved infrared image recognition network for power equipment based on YOLOv8n,or YOLOv8n-DCSW is proposed.Firstly,in the YOLOv8n backbone network,Coordinate Attention(CA)is added and the standard convolution in the residual module is replaced with Deformable Convolution Network(DCN),which enhances the f…查看全部>>
李珅;杜科;李舟演;李宁;熊岑;柳明慧;秦伦明
国网上海市电力公司,上海 200122国网上海市电力公司,上海 200122国网上海市电力公司,上海 200122国网上海市电力公司,上海 200122国网上海市电力公司,上海 200122上海电力大学电子信息工程学院,上海 201306上海电力大学电子信息工程学院,上海 201306
计算机与自动化
电力设备红外图像目标检测YOLOv8n可变形卷积注意力机制边框损失函数
infrared images of power equipmentobject detectionYOLOv8ndeformable convolutionattention mechanismbounding box loss function
《无线电工程》 2024 (10)
2362-2370,9
国家电网有限公司科技项目(SGSH0000AJJS2310204)Science and Technology Project of State Grid Corporation of China(SGSH0000AJJS2310204)
评论