Power Transmission Line Component Detection Using YOLOv7 on Single-Board Computer Platforms

Abstract

Regular inspection of power transmission line (PTL) systems is required to detect damage early and ensure the efficient and uninterrupted transmission of high-voltage electric power. In the past, these checks were conducted utilizing line crawling, inspection robots, and a helicopter. Yet, these traditional solutions are slow, costly, and hazardous. Advancements in drones, single board computers (SBC), high-resolution cameras, and deep learning technologies may enable real-time PTL inspections using drones. Some research has been conducted on PTL inspection with autonomous drones. However, it is essential to explore how to achieve real-time PTL component detection effectively and efficiently. In this paper, we report our research in PTL component detection using YOLOv7 and single-board computer (SBC). The YOLOv7 is the state-of-the-art method for real-time detection in edge computing. The original PTL dataset in Tokyo is created in this research. In this paper, we evaluate the detection performance with several sizes of training datasets. We also implement simple data augmentation to extend the size of datasets. The YOLOv7 model performance is also evaluated in several SBC platforms, such as Raspberry Pi 4B, Jetson Nano, and Jetson Orin Nano. The simulation results show that the proposed YOLOv7 model can achieve mean average precision (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$mAP$</tex>) over 90%, with a detection time of 0.33 <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$seconds$</tex> on the Jetson N ano platform with floating point 16-bit (FP 16) mode. (Abstract)