电力信息与通信技术2024，Vol.22Issue(4)：38-54,17.DOI:10.16543/j.2095-641x.electric.power.ict.2024.04.05
面向电力无人机巡检图像分析处理的自动化深度学习系统:架构设计与关键技术
The Architecture and Key Technologies of an Automatic Deep Learning System for Image Analysis in UAV Transmission Line Inspection
摘要
Abstract
Current models for analysing images captured by Unmanned Aerial Vehicles in transmission line inspection face limitations in their applicability,high development costs,and long development cycle.This paper proposes a new automated deep learning system,with the key principles of system design being generalisability,scalability,and automation.The literature review of related technological advances and the system architecture design are presented.Experimental results with our prototype system show that the automated model constructed by the system achieved Mean Average Precision values of 91.36%and 86.13%,respectively,in identifying insulator explosions and bird nests on inspection images,demonstrating that the system design is sound,and the architecture is feasible.关键词
输电线路巡检/深度学习/自动化训练/图像分析处理Key words
transmission line inspection/deep learning/AutoML/image processing分类
信息技术与安全科学引用本文复制引用
李道兴,王晓辉,李黎,季知祥..面向电力无人机巡检图像分析处理的自动化深度学习系统:架构设计与关键技术[J].电力信息与通信技术,2024,22(4):38-54,17.基金项目
中国电力科学研究院有限公司青年基金项目"面向能源互联网优化运行的数据存储与计算分析关键技术研究"(AI84-22-002). （AI84-22-002）
