电力信息与通信技术2024，Vol.22Issue(4)：21-29,9.DOI:10.16543/j.2095-641x.electric.power.ict.2024.04.03
基于多重注意力和特征对齐的销钉缺陷检测方法
Bolt Defect Detection Method Based on Multiple Attention and Feature Alignment
摘要
Abstract
The rapid expansion of power grid had higher requirements for the detection and maintenance of transmission lines,thus intelligent and efficient automated power inspection algorithms become one of the important research directions.In order to accurately identify the defective bolts in power line inspection image,we proposed a bolt defect detection method based on multiple attention and feature alignment.Firstly,we built a Deformable-DETR(deformable detection transformer)framework based on deformable attention to solve the problem that existing power inspection algorithms could not model the pixel contour-environment relationship through convolutional neural networks.Secondly,we proposed a proposal based local attention module to alleviate the problem of insufficient feature granularity caused by deformable attention.Thirdly,in order to enrich the object feature quality under the existing data,we proposed an object-level based feature alignment module based and a constraint functions.Finally,drone inspection image of a power company in central China were selected for verification.The experimental results show that the overall performance of the proposed algorithm improves by 5.4%compared with the existing convolutional algorithms,and the overall mean average precision reaches 90.5%.关键词
输电线路故障检测/无人机巡检/注意力机制/目标检测/深度学习Key words
transmission line fault detection/drone inspection/attention mechanism/object detection/deep learning分类
信息技术与安全科学引用本文复制引用
焦润海,李恺航,张学成,符哲源..基于多重注意力和特征对齐的销钉缺陷检测方法[J].电力信息与通信技术,2024,22(4):21-29,9.基金项目
中央高校基本科研业务费专项资金资助(2022JG004) （2022JG004）
国家自然基金资助项目(62272117). （62272117）
