Fault Detection for Split Pins of Power Transmission Fittings in UAV Inspections via Automatic Image Cropping-based Super-Resolution Reconstruction and Enhanced YOLOv8

Abstract

In modern industrial applications, ensuring the reliability of mechanical fittings is critical for maintaining operational safety and efficiency, particularly in power grid systems where split pins serve a pivotal role despite being susceptible to environmental degradation and failure. Existing UAV-based inspection systems are hampered by a low representation of split pin elements and complex backgrounds, leading to challenges in accurate fault detection and timely maintenance. To address this pressing issue, our study proposes an innovative fault detection method for split pins. The approach employs a three-step process: first, cropping operations are used to accurately isolate the fittings containing split pins; second, super-resolution reconstruction is applied to enhance image clarity and detail; and finally, an improved YOLOv8 network, augmented with inner-shape IoU and local window attention mechanisms, is utilized to refine local feature extraction and annotation accuracy. Experimental evaluations on a split pin defect dataset demonstrate robust performance, achieving an accuracy rate of 72.1% and a mean average precision (mAP) of 67.7%, thereby validating the method’s effectiveness under challenging conditions. The proposed approach contributes to the field by specifically targeting the challenges associated with split pin detection in UAV-based inspections, offering a practically applicable and reliably precise method.