UPM Institutional Repository

RT-DETR-Pothole: lightweight real-time detection transformers for improved road pothole detection


Citation

Abd Rahman, Mohd Amiruddin (2025) RT-DETR-Pothole: lightweight real-time detection transformers for improved road pothole detection. In: 2025 9th International Conference on Artificial Intelligence, Automation and Control Technologies (AIACT 2025), 17-21 Feb. 2025, Sapporo, Japan. (pp. 1-6). (Submitted)

Abstract

Assessment of on-time road condition is crucial for ensuring the safety of the motorist. One of the recent approaches to detecting road potholes is to analyze images captured from an unmanned aerial vehicle (UAV). Although the traditional deep learning model could perform accurate detection during offline analysis, there is still a limitation of the available algorithms that could perform real-time evaluation. Therefore, this study proposes a lightweight transformer algorithm, the real-time detection transformer (RT-DETR), for online evaluation of road pothole images. The models were tested in practical deployment scenarios and compared with several other object detection models, such as Faster RCNNSqueezeNet, YOLOv8x, YOLOv9e, YOLOv10x, and YOLO11x. The results show that the RT-DETRPothole outperformed all other models in detection accuracy, achieving the highest mAP0.50 (0.834) and mAP0.50-0.95 (0.565), along with a high F1-Score (0.809), indicating superior precision and recall, and at the same time it could maintain low inference time. Overall, RT-DETR-Pothole is the most suitable model for real-time pothole detection, especially for detecting smaller, less visible potholes, with a resonable inference time for pavement engineering applications.


Download File

[img] Text
115933.pdf - Submitted Version
Restricted to Repository staff only

Download (32MB)

Additional Metadata

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Science
Keywords: Road pothole detection; Real-time object detection; Transformer networks; RT-DETR; Lightweight models; UAV imagery; Computer vision; Deep learning; Object detection algorithms; Faster R-CNN; SqueezeNet; YOLO; mAP; F1-score; Inference time; Pavement engineering
Depositing User: Conference 2025
Date Deposited: 19 Mar 2025 07:48
Last Modified: 19 Mar 2025 07:48
URI: http://psasir.upm.edu.my/id/eprint/115933
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item