A lightweight insulator defect detection algorithm based on the improved YOLOv5
Unmanned aerial vehicle （UAV） inspections now have emerged as a predominant approach for the examination of transmission lines， with a pivotal focus on the detection of insulator defects. In this context， a lightweight insulator defect detection algorithm， founded on the improved YOLOv5， is introduc...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
zhejiang electric power
2023-12-01
|
| Series: | Zhejiang dianli |
| Subjects: | |
| Online Access: | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=4c48123a-e49b-4912-b5d5-c61138eef6f2 |
| _version_ | 1827392027532197888 |
|---|---|
| author | JI Shichao QU Xinghe SONG Qingbin XIAO Yangming MIAO Zheng LI Yuhang ZOU Guoping |
| author_facet | JI Shichao QU Xinghe SONG Qingbin XIAO Yangming MIAO Zheng LI Yuhang ZOU Guoping |
| author_sort | JI Shichao |
| collection | DOAJ |
| description | Unmanned aerial vehicle （UAV） inspections now have emerged as a predominant approach for the examination of transmission lines， with a pivotal focus on the detection of insulator defects. In this context， a lightweight insulator defect detection algorithm， founded on the improved YOLOv5， is introduced. Firstly， the lightweight Ghost convolution is employed to replace conventional convolution. Subsequently， the original feature extraction network is replaced with a repeated weighted bidirectional feature pyramid network （BiFPN） to bolster feature extraction capability across various scales. Finally， the coordinate attention （CA） mechanism is introduced to enhance the efficiency of backbone feature extraction. Experimental results reveal a significant 1.7% enhancement in the average precision of insulator detection， accompanied by a 13.1% reduction in the model’s size. This refined algorithm model not only elevates detection accuracy but also streamlines its footprint， thereby enabling more efficient and rapid insulator defect detection. |
| first_indexed | 2024-03-08T17:24:00Z |
| format | Article |
| id | doaj.art-c073de9e950940038a92557a9318824d |
| institution | Directory Open Access Journal |
| issn | 1007-1881 |
| language | zho |
| last_indexed | 2024-03-08T17:24:00Z |
| publishDate | 2023-12-01 |
| publisher | zhejiang electric power |
| record_format | Article |
| series | Zhejiang dianli |
| spelling | doaj.art-c073de9e950940038a92557a9318824d2024-01-03T00:45:29Zzhozhejiang electric powerZhejiang dianli1007-18812023-12-014212647210.19585/j.zjdl.2023120081007-1881（2023）12-0064-09A lightweight insulator defect detection algorithm based on the improved YOLOv5JI Shichao0QU Xinghe1SONG Qingbin2XIAO Yangming3MIAO Zheng4LI Yuhang5ZOU Guoping6State Grid Huzhou Power Supply Company, Huzhou, Zhejiang 313000, ChinaZhejiang Tailun Power Group Co., Ltd., Huzhou, Zhejiang 313000, ChinaState Grid Huzhou Power Supply Company, Huzhou, Zhejiang 313000, ChinaZhejiang Tailun Power Group Co., Ltd., Huzhou, Zhejiang 313000, ChinaState Grid Huzhou Power Supply Company, Huzhou, Zhejiang 313000, ChinaCollege of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, ChinaCollege of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, ChinaUnmanned aerial vehicle （UAV） inspections now have emerged as a predominant approach for the examination of transmission lines， with a pivotal focus on the detection of insulator defects. In this context， a lightweight insulator defect detection algorithm， founded on the improved YOLOv5， is introduced. Firstly， the lightweight Ghost convolution is employed to replace conventional convolution. Subsequently， the original feature extraction network is replaced with a repeated weighted bidirectional feature pyramid network （BiFPN） to bolster feature extraction capability across various scales. Finally， the coordinate attention （CA） mechanism is introduced to enhance the efficiency of backbone feature extraction. Experimental results reveal a significant 1.7% enhancement in the average precision of insulator detection， accompanied by a 13.1% reduction in the model’s size. This refined algorithm model not only elevates detection accuracy but also streamlines its footprint， thereby enabling more efficient and rapid insulator defect detection.https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=4c48123a-e49b-4912-b5d5-c61138eef6f2transmission lineinsulatordefect detectionyolov5 |
| spellingShingle | JI Shichao QU Xinghe SONG Qingbin XIAO Yangming MIAO Zheng LI Yuhang ZOU Guoping A lightweight insulator defect detection algorithm based on the improved YOLOv5 Zhejiang dianli transmission line insulator defect detection yolov5 |
| title | A lightweight insulator defect detection algorithm based on the improved YOLOv5 |
| title_full | A lightweight insulator defect detection algorithm based on the improved YOLOv5 |
| title_fullStr | A lightweight insulator defect detection algorithm based on the improved YOLOv5 |
| title_full_unstemmed | A lightweight insulator defect detection algorithm based on the improved YOLOv5 |
| title_short | A lightweight insulator defect detection algorithm based on the improved YOLOv5 |
| title_sort | lightweight insulator defect detection algorithm based on the improved yolov5 |
| topic | transmission line insulator defect detection yolov5 |
| url | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=4c48123a-e49b-4912-b5d5-c61138eef6f2 |
| work_keys_str_mv | AT jishichao alightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT quxinghe alightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT songqingbin alightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT xiaoyangming alightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT miaozheng alightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT liyuhang alightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT zouguoping alightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT jishichao lightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT quxinghe lightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT songqingbin lightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT xiaoyangming lightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT miaozheng lightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT liyuhang lightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 AT zouguoping lightweightinsulatordefectdetectionalgorithmbasedontheimprovedyolov5 |