Detection of insulator defects based on improved YOLOv7 method

Hai Li; Ruirong Tan; Chengyang Liu; Yongchang Xu

doi:10.1117/12.3030635

5 June 2024 Detection of insulator defects based on improved YOLOv7 method

Hai Li, Ruirong Tan, Chengyang Liu, Yongchang Xu

Proceedings Volume 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024); 131633O (2024) https://doi.org/10.1117/12.3030635
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 2024, Xi'an, China

Abstract

The smooth operation of power equipment is an important prerequisite for ensuring the production and life of residents. The insulator is an important component in the distribution network system. The defect size of the distribution network line insulator is small, and it is easy to be missing in the outdoor environment for a long time. The traditional target detection algorithm usually makes it difficult to identify the defect. Therefore, this paper proposes an insulator missing detection method based on improved YOLOv7 algorithm. Firstly, the insulator image data in the distribution network line is collected by the UAV; secondly, using the powerful feature extraction ability of the improved algorithm, the insulator is detected from the sample photo, and whether the insulator is normal or not is distinguished. Finally, the accuracy of the method is verified by experiments. The experimental results show that the accuracy of the method is 1.07 % higher than that of the original YOLOv7 algorithm, which can effectively distinguish whether the insulator is missing.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Hai Li, Ruirong Tan, Chengyang Liu, and Yongchang Xu "Detection of insulator defects based on improved YOLOv7 method", Proc. SPIE 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 131633O (5 June 2024); https://doi.org/10.1117/12.3030635

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available