计算机应用与软件2024，Vol.41Issue(12)：43-48,76,7.DOI:10.3969/j.issn.1000-386x.2024.12.007
轻量级网络识别红外图像中电气设备及其热故障
LIGHTWEIGHT NETWORKS APPLIED TO IDENTIFYING ELECTRICAL EQUIPMENT AND THEIR THERMAL FAULTS IN INFRARED IMAGES
摘要
Abstract
A lightweight convolution neural network(LightweightES)for edge computing equipment is proposed to identify electrical equipment and their abnormal heating faults in thermal images.In order to reduce the number of model parameters and improve detection accuracy,the classical SSD was modified as follows.MobileNetV3 lightweight network was used as the backbone network of feature extraction to extract image features efficiently.The efficient channel attention module(ECA)was introduced to improve the detection accuracy of the network.The SoftPool method was used to reduce the loss of the pooling information and improve the classification accuracy.A data set of 10516 labeled infrared images of electrical equipment was established including 6 types of outdoor substation equipment,such as current transformers,arresters,insulators,disconnectors,circuit breakers and drivepipes.The experimental results show that the mAP of LightweightES algorithm reaches 93.8%,which is 7.5 percentage points higher than SSD.The number of parameters is only 1/5 of SSD,while the detection frame rate is up to 55 FPS,which can accurately identify the electrical equipment and local temperature abnormal faults in real time.It is suitable for intelligent field monitoring terminal with limited computing power.关键词
电气设备红外图像/目标检测/轻量级网络/通道注意/池化Key words
Infrared image of electrical equipment/Target detection/Lightweight network/Channel attention/Pooling分类
信息技术与安全科学引用本文复制引用
张惊雷,李婉欣,赵俊亚,温显斌..轻量级网络识别红外图像中电气设备及其热故障[J].计算机应用与软件,2024,41(12):43-48,76,7.基金项目
国家自然科学基金项目(61472278). （61472278）
