作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2019, Vol. 45 ›› Issue (8): 275-280. doi: 10.19678/j.issn.1000-3428.0053695

• 开发研究与工程应用 • 上一篇    下一篇

轻量级YOLOV3的绝缘子缺陷检测方法

吴涛1, 王伟斌2, 于力2, 谢蓓敏3, 尹维崴3, 王洪玉1   

  1. 1. 大连理工大学 信息与通信工程学院, 辽宁 大连 116024;
    2. 国家电网有限公司东北分部, 沈阳 110180;
    3. 国网吉林省电力有限公司检修公司, 长春 130000
  • 收稿日期:2019-01-15 修回日期:2019-02-22 出版日期:2019-08-15 发布日期:2019-08-08
  • 作者简介:吴涛(1994-),男,硕士研究生,主研方向为目标参数估测;王伟斌、于力、谢蓓敏,高级工程师;尹维崴,工程师;王洪玉(通信作者),教授。
  • 基金资助:
    国网吉林省电力有限公司科技项目(SGJLJOOYJJS1800122)。

Insulator Defect Detection Method for Lightweight YOLOV3

WU Tao1, WANG Weibin2, YU Li2, XIE Beimin3, YIN Weiwei3, WANG Hongyu1   

  1. 1. School of Information and Communication Engineering, Dalian University of Technology, Dalian, Liaoning 116024, China;
    2. Northeast Branch of State Grid Co., Ltd., Shenyang 110180, China;
    3. Maintenance Company of State Grid Jilin Electric Power Co., Ltd., Changchun 130000, China
  • Received:2019-01-15 Revised:2019-02-22 Online:2019-08-15 Published:2019-08-08

摘要: 绝缘子是输电线路的重要组成部分,其能否正常工作直接影响电网的稳定运行。为此,研究了智能绝缘子缺陷检测方法。通过无人机的航拍图像制作数据集,利用K-means++算法确定先验框,基于YOLOV3检测架构构建一种改进的轻量级网络。实验结果表明,该方法提升了高清绝缘子的图像检测速度,且能够完成绝缘子定位及缺陷检测。

关键词: 无人机, 轻量级网络, 绝缘子定位, 缺陷检测, 实时检测

Abstract: Insulators are an important part of transmission lines,and their normal operation directly affects the stable operation of the power grid.Therefore,intelligent insulator defect detection method is researched.The dataset is made by the aerial image of the drone,the K-means++ algorithm is used to determine the a priori frame,and an improved lightweight network is built based on the YOLOV3 detection architecture.Experimental results show that the method improves the image detection speed of high-definition insulators and can complete insulator positioning and defect detection.

Key words: unmanned aerial vehicle, lightweight network, insulator positioning, defect detection, real-time detection

中图分类号: