Gabor-YOLONet: A lightweight and efficient detection network for low-voltage power lines from unmanned aerial vehicle images
Maintaining and monitoring low-voltage overhead power lines are of great importance because such lines are the key link between the power system and low-voltage power users. At present, few networks can be detected accurately on intelligent edge identification devices because of the complex backgrou...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2022.960842/full |
| _version_ | 1828069214212063232 |
|---|---|
| author | Lei Feng Lianmei Zhang Zepu Gao Ruoyun Zhou Lan Li |
| author_facet | Lei Feng Lianmei Zhang Zepu Gao Ruoyun Zhou Lan Li |
| author_sort | Lei Feng |
| collection | DOAJ |
| description | Maintaining and monitoring low-voltage overhead power lines are of great importance because such lines are the key link between the power system and low-voltage power users. At present, few networks can be detected accurately on intelligent edge identification devices because of the complex backgrounds and limited characteristics in unmanned aerial vehicle images as well as the low computing abilities of hardware. In order to give consideration to accuracy and speed, a novel power line detection method was proposed, denoted by Gabor-YOLONet, used for intelligent edge identification devices available to UAV. Unlike existing methods, the proposed method uses the Gabor algorithm to extract foreground of power lines from cluttered backgrounds automatically and predict power lines and their auxiliary targets such as insulators in the foreground scene. In addition, a new inference method was introduced, which can summarize the average location and orientation of auxiliary targets by clustering to verify the rationality of the predicted results for power lines. The experiment results showed that the proposed method had the higher accuracy and consumed less computing resources; compared with other methods, the mAP of identification for power lines was 86.6% and the running time was only 25 ms, with excellent performance on intelligent edge devices. |
| first_indexed | 2024-04-11T00:14:47Z |
| format | Article |
| id | doaj.art-e4f5930cdbe54aba811d806e0e4f5f96 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-04-11T00:14:47Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-e4f5930cdbe54aba811d806e0e4f5f962023-01-09T05:30:23ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2023-01-011010.3389/fenrg.2022.960842960842Gabor-YOLONet: A lightweight and efficient detection network for low-voltage power lines from unmanned aerial vehicle imagesLei Feng0Lianmei Zhang1Zepu Gao2Ruoyun Zhou3Lan Li4School of Electrical Engineering and Automation, Wuhan University, Wuhan, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan, ChinaState Grid Henan Extra High Voltage Company, Zhengzhou, ChinaWuhan Power Supply Company of State Grid, Wuhan, ChinaState Grid Henan Extra High Voltage Company, Zhengzhou, ChinaMaintaining and monitoring low-voltage overhead power lines are of great importance because such lines are the key link between the power system and low-voltage power users. At present, few networks can be detected accurately on intelligent edge identification devices because of the complex backgrounds and limited characteristics in unmanned aerial vehicle images as well as the low computing abilities of hardware. In order to give consideration to accuracy and speed, a novel power line detection method was proposed, denoted by Gabor-YOLONet, used for intelligent edge identification devices available to UAV. Unlike existing methods, the proposed method uses the Gabor algorithm to extract foreground of power lines from cluttered backgrounds automatically and predict power lines and their auxiliary targets such as insulators in the foreground scene. In addition, a new inference method was introduced, which can summarize the average location and orientation of auxiliary targets by clustering to verify the rationality of the predicted results for power lines. The experiment results showed that the proposed method had the higher accuracy and consumed less computing resources; compared with other methods, the mAP of identification for power lines was 86.6% and the running time was only 25 ms, with excellent performance on intelligent edge devices.https://www.frontiersin.org/articles/10.3389/fenrg.2022.960842/fullsmart gridlow-voltage distribution networkpower lines extractionGabor-YOLONetinference module |
| spellingShingle | Lei Feng Lianmei Zhang Zepu Gao Ruoyun Zhou Lan Li Gabor-YOLONet: A lightweight and efficient detection network for low-voltage power lines from unmanned aerial vehicle images Frontiers in Energy Research smart grid low-voltage distribution network power lines extraction Gabor-YOLONet inference module |
| title | Gabor-YOLONet: A lightweight and efficient detection network for low-voltage power lines from unmanned aerial vehicle images |
| title_full | Gabor-YOLONet: A lightweight and efficient detection network for low-voltage power lines from unmanned aerial vehicle images |
| title_fullStr | Gabor-YOLONet: A lightweight and efficient detection network for low-voltage power lines from unmanned aerial vehicle images |
| title_full_unstemmed | Gabor-YOLONet: A lightweight and efficient detection network for low-voltage power lines from unmanned aerial vehicle images |
| title_short | Gabor-YOLONet: A lightweight and efficient detection network for low-voltage power lines from unmanned aerial vehicle images |
| title_sort | gabor yolonet a lightweight and efficient detection network for low voltage power lines from unmanned aerial vehicle images |
| topic | smart grid low-voltage distribution network power lines extraction Gabor-YOLONet inference module |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2022.960842/full |
| work_keys_str_mv | AT leifeng gaboryolonetalightweightandefficientdetectionnetworkforlowvoltagepowerlinesfromunmannedaerialvehicleimages AT lianmeizhang gaboryolonetalightweightandefficientdetectionnetworkforlowvoltagepowerlinesfromunmannedaerialvehicleimages AT zepugao gaboryolonetalightweightandefficientdetectionnetworkforlowvoltagepowerlinesfromunmannedaerialvehicleimages AT ruoyunzhou gaboryolonetalightweightandefficientdetectionnetworkforlowvoltagepowerlinesfromunmannedaerialvehicleimages AT lanli gaboryolonetalightweightandefficientdetectionnetworkforlowvoltagepowerlinesfromunmannedaerialvehicleimages |