Next Article in Journal
Comparative Study of Machine Learning Models for Textual Medical Note Classification
Previous Article in Journal
ConWave-LoRA: Concept Fusion in Customized Diffusion Models with Contrastive Learning and Wavelet Filtering
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Computers
Volume 15
Issue 1
10.3390/computers15010006
computers-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Federated Learning-Based Road Defect Detection with Transformer Models for Real-Time Monitoring

by
Bushra Abro
1,2,*,
Sahil Jatoi
1,2,
Muhammad Zakir Shaikh
1,2,3,
Enrique Nava Baro
4,
Mariofanna Milanova
5,* and
Bhawani Shankar Chowdhry
1,2
1
National Centre for Robotics, Automation and Artificial Intelligence, Mehran University of Engineering and Technology (MUET), Jamshoro 76062, Pakistan
2
NCRA-CMS Lab, Mehran University of Engineering and Technology (MUET), Jamshoro 76062, Pakistan
3
Mechanical Engineering and Energy Efficiency, School of Industrial Engineering, University of Malaga, C/ Doctor Ortiz Ramos, s/n, Campus de Teatinos, 29071 Málaga, Spain
4
Departamento de Ingeniería de Comunicaciones, Universidad de Malaga, C/ Doctor Ortiz Ramos, s/n, Campus de Teatinos, 29071 Málaga, Spain
5
Department of Computer Science, University of Arkansas at Little Rock, 2801 South University Avenue, Little Rock, AR 72204, USA
*
Authors to whom correspondence should be addressed.
Computers 2026, 15(1), 6; https://doi.org/10.3390/computers15010006
Submission received: 13 November 2025 / Revised: 5 December 2025 / Accepted: 17 December 2025 / Published: 22 December 2025
(This article belongs to the Section AI-Driven Innovations)
Versions Notes

Abstract

This research article presents a novel road defect detection methodology that integrates deep learning techniques and a federated learning approach. Existing road defect detection systems heavily rely on manual inspection and sensor-based techniques, which are prone to errors. To overcome these limitations, a data-acquisition system utilizing a GoPro HERO 9 camera was used to capture high-quality videos and images of road surfaces. A comprehensive dataset consist of multiple road defects, such as cracks, potholes, and uneven surfaces, that were pre-processed and augmented to prepare them for effective model training. A Real-Time Detection Transformer-based architecture model was used that achieved mAP50 of 99.60% and mAP50-95 of 99.55% in cross-validation of road defect detection and object detection tasks. Federated learning helped to train the model in a decentralized manner that enhanced data protection and scalability. The proposed system achieves higher detection accuracy for road defects by increasing speed and efficiency while enhancing scalability, which makes it a potential asset for real-time monitoring.
Keywords: road safety; road defect detection; federated learning; real-time detection transformer; deep learning; computer vision road safety; road defect detection; federated learning; real-time detection transformer; deep learning; computer vision

Share and Cite

MDPI and ACS Style

Abro, B.; Jatoi, S.; Shaikh, M.Z.; Baro, E.N.; Milanova, M.; Chowdhry, B.S. Federated Learning-Based Road Defect Detection with Transformer Models for Real-Time Monitoring. Computers 2026, 15, 6. https://doi.org/10.3390/computers15010006

AMA Style

Abro B, Jatoi S, Shaikh MZ, Baro EN, Milanova M, Chowdhry BS. Federated Learning-Based Road Defect Detection with Transformer Models for Real-Time Monitoring. Computers. 2026; 15(1):6. https://doi.org/10.3390/computers15010006

Chicago/Turabian Style

Abro, Bushra, Sahil Jatoi, Muhammad Zakir Shaikh, Enrique Nava Baro, Mariofanna Milanova, and Bhawani Shankar Chowdhry. 2026. "Federated Learning-Based Road Defect Detection with Transformer Models for Real-Time Monitoring" Computers 15, no. 1: 6. https://doi.org/10.3390/computers15010006

APA Style

Abro, B., Jatoi, S., Shaikh, M. Z., Baro, E. N., Milanova, M., & Chowdhry, B. S. (2026). Federated Learning-Based Road Defect Detection with Transformer Models for Real-Time Monitoring. Computers, 15(1), 6. https://doi.org/10.3390/computers15010006

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop