Fast R-CNN based UAV inspection system for insulator detection

Yingzhao Xie; Xing Zhang; Xun Zuo

doi:10.1117/12.2639887

19 October 2022 Fast R-CNN based UAV inspection system for insulator detection

Yingzhao Xie, Xing Zhang, Xun Zuo

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 122945R (2022) https://doi.org/10.1117/12.2639887
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

In the traditional power grid inspection, manual identification of insulators has a heavy workload and the real-time performance of defect detection is poor. This problem is becoming more and more serious with the large-scale development of power grid. In this paper we proposed a target fast detection algorithm based on Faster R-CNN for insulator detection and built a UAV inspection system. The proposed algorithm extracts the key features of insulator and accomplishes fast identification and inspection of insulator by matching the defect insulator sample sets. The proposed algorithm is transplanted to UAV computing platform for practical verification. The result shows that the proposed algorithm can identification the insulator in 35ms, reach the 90% accuracy. It can meet the requirement of the smart grid in future.

Citation Download Citation

Yingzhao Xie, Xing Zhang, and Xun Zuo "Fast R-CNN based UAV inspection system for insulator detection", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 122945R (19 October 2022); https://doi.org/10.1117/12.2639887

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