Foreign Object Detection on Insulators Based on Improved YOLO v3

As an important component of transmission lines, insulator plays an essential role in the stable operation of the power grid. However, the outdoor environment in which the insulators are located can easily lead to the hanging of foreign objects. This paper proposes a novel method for foreign object...

Full description

Saved in:
Bibliographic Details
Main Authors: Huankun ZHANG, Junyi LI, Bin ZHANG
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2020-02-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201908009
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053177516228608
author Huankun ZHANG
Junyi LI
Bin ZHANG
author_facet Huankun ZHANG
Junyi LI
Bin ZHANG
author_sort Huankun ZHANG
collection DOAJ
description As an important component of transmission lines, insulator plays an essential role in the stable operation of the power grid. However, the outdoor environment in which the insulators are located can easily lead to the hanging of foreign objects. This paper proposes a novel method for foreign object detection on insulators based on the improved YOLO v3: Dense-YOLO v3. A dense network is designed to replace one of the convolutional layers of the original network in order to realize the multi-layer feature reuse and fusion of the insulator, which improves the detection accuracy. In addition, we amplify the training set to improve the training effect of the network and propose a wrong detection cost function to measure the risk of false detection. The experiment shows that the proposed algorithm has a detection precision rate reaching up to 94.54%. Meanwhile, the Dense-YOLO v3 outperforms YOLO v3 and Faster R-CNN, both in terms of detection accuracy and wrong detection cost. The result shows that the presented approach can be applied to the UAV inspection of transmission lines.
format Article
id doaj-art-02a7ca83517140f7b42b62dfd4ffc1c8
institution DOAJ
issn 1004-9649
language zho
publishDate 2020-02-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-02a7ca83517140f7b42b62dfd4ffc1c82025-08-20T02:52:37ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492020-02-01532495510.11930/j.issn.1004-9649.201908009zgdl-52-12-zhanghuankunForeign Object Detection on Insulators Based on Improved YOLO v3Huankun ZHANG0Junyi LI1Bin ZHANG2School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaAs an important component of transmission lines, insulator plays an essential role in the stable operation of the power grid. However, the outdoor environment in which the insulators are located can easily lead to the hanging of foreign objects. This paper proposes a novel method for foreign object detection on insulators based on the improved YOLO v3: Dense-YOLO v3. A dense network is designed to replace one of the convolutional layers of the original network in order to realize the multi-layer feature reuse and fusion of the insulator, which improves the detection accuracy. In addition, we amplify the training set to improve the training effect of the network and propose a wrong detection cost function to measure the risk of false detection. The experiment shows that the proposed algorithm has a detection precision rate reaching up to 94.54%. Meanwhile, the Dense-YOLO v3 outperforms YOLO v3 and Faster R-CNN, both in terms of detection accuracy and wrong detection cost. The result shows that the presented approach can be applied to the UAV inspection of transmission lines.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201908009insulatorneural networkdense-netforeign object detectionyolo v3
spellingShingle Huankun ZHANG
Junyi LI
Bin ZHANG
Foreign Object Detection on Insulators Based on Improved YOLO v3
Zhongguo dianli
insulator
neural network
dense-net
foreign object detection
yolo v3
title Foreign Object Detection on Insulators Based on Improved YOLO v3
title_full Foreign Object Detection on Insulators Based on Improved YOLO v3
title_fullStr Foreign Object Detection on Insulators Based on Improved YOLO v3
title_full_unstemmed Foreign Object Detection on Insulators Based on Improved YOLO v3
title_short Foreign Object Detection on Insulators Based on Improved YOLO v3
title_sort foreign object detection on insulators based on improved yolo v3
topic insulator
neural network
dense-net
foreign object detection
yolo v3
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201908009
work_keys_str_mv AT huankunzhang foreignobjectdetectiononinsulatorsbasedonimprovedyolov3
AT junyili foreignobjectdetectiononinsulatorsbasedonimprovedyolov3
AT binzhang foreignobjectdetectiononinsulatorsbasedonimprovedyolov3