Deep Learning Models for UAV-Assisted Bridge Inspection: A YOLO Benchmark Analysis

TL;DR

This paper benchmarks 23 YOLO models to identify the best lightweight options for UAV-based bridge inspections, balancing accuracy and speed on a specialized dataset.

Contribution

It provides a comprehensive benchmark of recent YOLO variants for bridge inspection, aiding in optimal model selection for UAV applications.

Findings

YOLOv8n and YOLOv7tiny offer high accuracy with fast inference times.

YOLOv6m6 achieves the highest mAP@50 score of 0.872.

Selected models balance accuracy and speed for efficient UAV bridge inspections.

Abstract

Visual inspections of bridges are critical to ensure their safety and identify potential failures early. This inspection process can be rapidly and accurately automated by using unmanned aerial vehicles (UAVs) integrated with deep learning models. However, choosing an appropriate model that is lightweight enough to integrate into the UAV and fulfills the strict requirements for inference time and accuracy is challenging. Therefore, our work contributes to the advancement of this model selection process by conducting a benchmark of 23 models belonging to the four newest YOLO variants (YOLOv5, YOLOv6, YOLOv7, YOLOv8) on COCO-Bridge-2021+, a dataset for bridge details detection. Through comprehensive benchmarking, we identify YOLOv8n, YOLOv7tiny, YOLOv6m, and YOLOv6m6 as the models offering an optimal balance between accuracy and processing speed, with mAP@50 scores of 0.803, 0.837, 0.853, and 0.872, and inference times of 5.3ms, 7.5ms, 14.06ms, and 39.33ms, respectively. Our findings accelerate the model selection process for UAVs, enabling more efficient and reliable bridge inspections.