基于改进Faster-RCNN的输电线路巡检图像检测
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TM755

基金项目:

国家自然科学基金资助项目(52007102);湖北省重点研发计划资助项目(2020BAB110)


Transmission line inspection image detection based on improved Faster-RCNN
Author:
Affiliation:

Fund Project:

Study on the electromagnetic vibration of switched reluctance motor using amorphous alloy core considering the inverse magnetostriction effect; Research and application of intelligent sensing technology for UHV transmission tower status

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对传统输电线路目标巡检图像识别方法响应速度慢、准确率不高的问题,文中提出一种改进的更快速区域卷积神经网络(Faster-RCNN)深度学习识别算法。通过轻量化卷积神经网络(ZFnet)提取图像特征,并重置模型参数以获取更多目标细节;利用Faster-RCNN对目标进行检测,由子网络区域提议模型生成目标候选框和快速区域卷积神经网络(Fast-RCNN)进行参数调优,并在Faster-RCNN输出部分引入精炼阶段,增加目标特征的分类细化和回归细化,将存在目标的多个边界框合并,实现精确分类以及坐标定位。实验结果表明:改进Faster-RCNN算法可有效识别线路设备及设备缺陷,总体识别率达到93.5%,响应时间在1 s内。与图像识别法或单步多阶目标检测(SSD)、实时快速目标检测(YOLO)深度学习法相比,所提算法提高了电力设备的识别精度与响应速度,在输电线路智能巡检中具有一定的优越性。

    Abstract:

    To solve the problem of slow response and low accuracy in the traditional image recognition method of transmission line target inspection,an improved faster-region convolutional neural network (Faster-RCNN) deep learning recognition algorithm is proposed. In this paper,the image features are extracted by zeiler and fergus net (ZFnet) and the ZFnet model parameters are reset to obtain more target details. Then,the Faster-RCNN is used to detect the target. The target candidate box is generated by the sub-network region proposal model and the parameters are tuned by the fast-region convolutional neural network (Fast-RCNN). In addition,the refining stage is introduced into the output part of the Faster-RCNN to increase the refinement of classification and regression of the target features. And then the multiple bounding boxes with the target are combined to achieve accurate classification and coordinate positioning. The results of the experiments show that the improved Faster-RCNN algorithm can effectively identify the transmission line equipment and its defects. The overall recognition rate of the method could reach 93.5% within 1 s of the response time. Compared with the image recognition and the deep learning such as single shot multibox detector (SSD) and you only look once (YOLO),the proposed algorithm improves the identification accuracy and response speed of power equipment,and has certain advantages in intelligent inspection of transmission lines.

    参考文献
    相似文献
    引证文献
引用本文

魏业文,李梅,解园琳,戴北城.基于改进Faster-RCNN的输电线路巡检图像检测[J].电力工程技术,2022,41(2):171-178

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-09-18
  • 最后修改日期:2021-12-05
  • 录用日期:2021-09-06
  • 在线发布日期: 2022-03-24
  • 出版日期: 2022-03-28
文章二维码