Cargando…
A Light-Weight Network for Small Insulator and Defect Detection Using UAV Imaging Based on Improved YOLOv5
Insulator defect detection is of great significance to compromise the stability of the power transmission line. The state-of-the-art object detection network, YOLOv5, has been widely used in insulator and defect detection. However, the YOLOv5 network has limitations such as poor detection rate and h...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10256046/ https://www.ncbi.nlm.nih.gov/pubmed/37299976 http://dx.doi.org/10.3390/s23115249 |
_version_ | 1785057019334492160 |
---|---|
author | Zhang, Tong Zhang, Yinan Xin, Min Liao, Jiashe Xie, Qingfeng |
author_facet | Zhang, Tong Zhang, Yinan Xin, Min Liao, Jiashe Xie, Qingfeng |
author_sort | Zhang, Tong |
collection | PubMed |
description | Insulator defect detection is of great significance to compromise the stability of the power transmission line. The state-of-the-art object detection network, YOLOv5, has been widely used in insulator and defect detection. However, the YOLOv5 network has limitations such as poor detection rate and high computational loads in detecting small insulator defects. To solve these problems, we proposed a light-weight network for insulator and defect detection. In this network, we introduced the Ghost module into the YOLOv5 backbone and neck to reduce the parameters and model size to enhance the performance of unmanned aerial vehicles (UAVs). Besides, we added small object detection anchors and layers for small defect detection. In addition, we optimized the backbone of YOLOv5 by applying convolutional block attention modules (CBAM) to focus on critical information for insulator and defect detection and suppress uncritical information. The experiment result shows the mean average precision (mAP) is set to 0.5, and the mAP is set from 0.5 to 0.95 of our model and can reach 99.4% and 91.7%; the parameters and model size were reduced to 3,807,372 and 8.79 M, which can be easily deployed to embedded devices such as UAVs. Moreover, the speed of detection can reach 10.9 ms/image, which can meet the real-time detection requirement. |
format | Online Article Text |
id | pubmed-10256046 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-102560462023-06-10 A Light-Weight Network for Small Insulator and Defect Detection Using UAV Imaging Based on Improved YOLOv5 Zhang, Tong Zhang, Yinan Xin, Min Liao, Jiashe Xie, Qingfeng Sensors (Basel) Article Insulator defect detection is of great significance to compromise the stability of the power transmission line. The state-of-the-art object detection network, YOLOv5, has been widely used in insulator and defect detection. However, the YOLOv5 network has limitations such as poor detection rate and high computational loads in detecting small insulator defects. To solve these problems, we proposed a light-weight network for insulator and defect detection. In this network, we introduced the Ghost module into the YOLOv5 backbone and neck to reduce the parameters and model size to enhance the performance of unmanned aerial vehicles (UAVs). Besides, we added small object detection anchors and layers for small defect detection. In addition, we optimized the backbone of YOLOv5 by applying convolutional block attention modules (CBAM) to focus on critical information for insulator and defect detection and suppress uncritical information. The experiment result shows the mean average precision (mAP) is set to 0.5, and the mAP is set from 0.5 to 0.95 of our model and can reach 99.4% and 91.7%; the parameters and model size were reduced to 3,807,372 and 8.79 M, which can be easily deployed to embedded devices such as UAVs. Moreover, the speed of detection can reach 10.9 ms/image, which can meet the real-time detection requirement. MDPI 2023-06-01 /pmc/articles/PMC10256046/ /pubmed/37299976 http://dx.doi.org/10.3390/s23115249 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Zhang, Tong Zhang, Yinan Xin, Min Liao, Jiashe Xie, Qingfeng A Light-Weight Network for Small Insulator and Defect Detection Using UAV Imaging Based on Improved YOLOv5 |
title | A Light-Weight Network for Small Insulator and Defect Detection Using UAV Imaging Based on Improved YOLOv5 |
title_full | A Light-Weight Network for Small Insulator and Defect Detection Using UAV Imaging Based on Improved YOLOv5 |
title_fullStr | A Light-Weight Network for Small Insulator and Defect Detection Using UAV Imaging Based on Improved YOLOv5 |
title_full_unstemmed | A Light-Weight Network for Small Insulator and Defect Detection Using UAV Imaging Based on Improved YOLOv5 |
title_short | A Light-Weight Network for Small Insulator and Defect Detection Using UAV Imaging Based on Improved YOLOv5 |
title_sort | light-weight network for small insulator and defect detection using uav imaging based on improved yolov5 |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10256046/ https://www.ncbi.nlm.nih.gov/pubmed/37299976 http://dx.doi.org/10.3390/s23115249 |
work_keys_str_mv | AT zhangtong alightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 AT zhangyinan alightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 AT xinmin alightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 AT liaojiashe alightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 AT xieqingfeng alightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 AT zhangtong lightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 AT zhangyinan lightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 AT xinmin lightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 AT liaojiashe lightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 AT xieqingfeng lightweightnetworkforsmallinsulatoranddefectdetectionusinguavimagingbasedonimprovedyolov5 |