Title: Improved YOLOv8 model for foreign object intrusion detection on transmission lines

Authors: Xinqiang Wu; Guangyu Li; Shicheng Li; Qi Cao; Song Yang; Haolin Li; Ming Liu

Addresses: Baishan Power Supply Company, Stare Grid Jilin Electric Power, Co. Ltd., Baishan, Jilin, China ' Baishan Power Supply Company, Stare Grid Jilin Electric Power, Co. Ltd., Baishan, Jilin, China ' Baishan Power Supply Company, Stare Grid Jilin Electric Power, Co. Ltd., Baishan, Jilin, China ' Baishan Power Supply Company, Stare Grid Jilin Electric Power, Co. Ltd., Baishan, Jilin, China ' Baishan Power Supply Company, Stare Grid Jilin Electric Power, Co. Ltd., Baishan, Jilin, China ' Baishan Power Supply Company, Stare Grid Jilin Electric Power, Co. Ltd., Baishan, Jilin, China ' Baishan Power Supply Company, Stare Grid Jilin Electric Power, Co. Ltd., Baishan, Jilin, China

Abstract: Overhead transmission line is an important channel for power transmission, directly related to the safe and stable operation of the power grid. Owing to the complex environment of the area through which the transmission line passes, foreign object intrusion has become the main reason for the line tripping and not reclosing successfully. The traditional defect detection method mainly relies on manual detection, and although this method is widely adopted, it still has several obvious limitations. These include low efficiency, high labour costs and susceptibility to human error. In recent years, the emergence of UAV-based inspection systems has revolutionised the way transmission lines are maintained. In this paper, an improved YOLOv8 model is proposed by replacing the YOLOv8 downsampling layer with the YOLOv9 downsampling layer ADown, and the YOLOv9 feature extraction block RepNCSPELAN4 in place of the C2F module of YOLOv8. It constitutes the YOLOv8-AR model. The method ensures that the detection accuracy of foreign object intrusion on transmission lines is improved while at the same time improving the regression rate of detection and reducing the computational volume. It performs better on the target detection task and is able to detect and localise target objects more accurately.

Keywords: power transmission line inspection; foreign body invasion; YOLOV8; deep learning; image classification.

DOI: 10.1504/IJWMC.2026.151594

International Journal of Wireless and Mobile Computing, 2026 Vol.30 No.2, pp.168 - 179

Received: 03 Apr 2025
Accepted: 22 Jun 2025
Published online: 09 Feb 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article