Optimizing Pothole Detection in Pavements: A Comparative Analysis of Deep Learning Models

Engineering Proceedings

article

Tiago Tamagusko¹  Adelino Ferreira¹ 

[1] Research Centre for Territory, Transports and Environment ,(CITTA), Department of Civil Engineering, University of Coimbra

关键词: computer vision;    object detection;    pothole;    road pavements;    YOLO;    deep learning;   

DOI  :  10.3390/engproc2023036011

来源: mdpi

【 摘 要 】

Advancements in computer vision applications have led to improved object detection (OD) in terms of accuracy and processing time, enabling real-time solutions across various fields. In pavement engineering, detecting visual defects such as potholes, cracking, and rutting is of particular interest. This study aims to evaluate YOLO models on a dataset of 665 road pavement images labeled with potholes for OD. Pre-trained deep learning models were customized for pothole detection using transfer learning techniques. The assessed models include You Only Look Once (YOLO) versions 3, 4, and 5. It was found that YOLOv4 achieves the highest mean average precision (mAP), while its shortened version, YOLOv4-tiny, offers the best-reduced inference time, making it ideal for mobile applications. Furthermore, the YOLOv5s model demonstrates potential, attaining good results and standing out for its ease of implementation and scalability.

【 授权许可】

Unknown