MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring Systems

Traffic monitoring reduces congestion, improves safety, and supports environmental sustainability. Real-time flow tracking, anomaly detection, and efficient management are key. Convolutional Neural Networks (CNNs) have become integral due to their compact size and easy deployment. However, their eff...

Full description

Saved in:
Bibliographic Details
Main Authors: Mark Bugeja, Matthias Bartolo, Matthew Montebello, Dylan Seychell
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11071529/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849340428908756992
author Mark Bugeja
Matthias Bartolo
Matthew Montebello
Dylan Seychell
author_facet Mark Bugeja
Matthias Bartolo
Matthew Montebello
Dylan Seychell
author_sort Mark Bugeja
collection DOAJ
description Traffic monitoring reduces congestion, improves safety, and supports environmental sustainability. Real-time flow tracking, anomaly detection, and efficient management are key. Convolutional Neural Networks (CNNs) have become integral due to their compact size and easy deployment. However, their effectiveness depends heavily on the quality of the input data, especially image resolution. With high-resolution cameras, especially 4K, balancing image quality, detection accuracy, and system efficiency is critical. We propose the Multi-Resolution Traffic Monitoring Dataset (MRTMD), which captures transport scenes at resolutions ranging from 2160p to 360p. This dataset serves as a benchmark for standard object detection models, enabling the development of more efficient and cost-effective traffic monitoring solutions. MRTMD will be freely available on GitHub, offering a valuable resource for researchers and practitioners. We evaluate leading object detection models—YOLOv9, YOLOv8, YOLOv7, Faster R-CNN, FCOS, SSD, and RT-DETR—across varied resolutions. Our analysis focuses on mean Average Precision (mAP), recall, and processing time. We also assess the accuracy of Number Plate Recognition (NPR) for tasks that require fine-grained detail extraction. Our findings show that detection performance typically varies within ±0.01 to ±0.03 in mAP and recall across resolutions, suggesting higher resolutions are not always advantageous. However, they remain crucial for tasks like NPR. The multi-resolution dataset enables a comprehensive evaluation of the trade-off between image quality and task performance. Ultimately, our analysis highlights the importance of resolution selection in large-scale deployments, informing system designers and policymakers. This dataset is a vital tool for balancing performance, cost, and practical constraints in real-world traffic monitoring.
format Article
id doaj-art-dc9fec6a429c41ed8497e223e197904e
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-dc9fec6a429c41ed8497e223e197904e2025-08-20T03:43:55ZengIEEEIEEE Access2169-35362025-01-011313446013448310.1109/ACCESS.2025.358598611071529MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring SystemsMark Bugeja0https://orcid.org/0000-0002-7836-9161Matthias Bartolo1https://orcid.org/0009-0006-1353-4556Matthew Montebello2Dylan Seychell3https://orcid.org/0000-0002-2377-9833Department of Artificial Intelligence, University of Malta, Msida, MaltaDepartment of Artificial Intelligence, University of Malta, Msida, MaltaDepartment of Artificial Intelligence, University of Malta, Msida, MaltaDepartment of Artificial Intelligence, University of Malta, Msida, MaltaTraffic monitoring reduces congestion, improves safety, and supports environmental sustainability. Real-time flow tracking, anomaly detection, and efficient management are key. Convolutional Neural Networks (CNNs) have become integral due to their compact size and easy deployment. However, their effectiveness depends heavily on the quality of the input data, especially image resolution. With high-resolution cameras, especially 4K, balancing image quality, detection accuracy, and system efficiency is critical. We propose the Multi-Resolution Traffic Monitoring Dataset (MRTMD), which captures transport scenes at resolutions ranging from 2160p to 360p. This dataset serves as a benchmark for standard object detection models, enabling the development of more efficient and cost-effective traffic monitoring solutions. MRTMD will be freely available on GitHub, offering a valuable resource for researchers and practitioners. We evaluate leading object detection models—YOLOv9, YOLOv8, YOLOv7, Faster R-CNN, FCOS, SSD, and RT-DETR—across varied resolutions. Our analysis focuses on mean Average Precision (mAP), recall, and processing time. We also assess the accuracy of Number Plate Recognition (NPR) for tasks that require fine-grained detail extraction. Our findings show that detection performance typically varies within ±0.01 to ±0.03 in mAP and recall across resolutions, suggesting higher resolutions are not always advantageous. However, they remain crucial for tasks like NPR. The multi-resolution dataset enables a comprehensive evaluation of the trade-off between image quality and task performance. Ultimately, our analysis highlights the importance of resolution selection in large-scale deployments, informing system designers and policymakers. This dataset is a vital tool for balancing performance, cost, and practical constraints in real-world traffic monitoring.https://ieeexplore.ieee.org/document/11071529/Dataset vehicle detectionhigh resolution image datasetnumber plate recognitioncomputer vision
spellingShingle Mark Bugeja
Matthias Bartolo
Matthew Montebello
Dylan Seychell
MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring Systems
IEEE Access
Dataset vehicle detection
high resolution image dataset
number plate recognition
computer vision
title MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring Systems
title_full MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring Systems
title_fullStr MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring Systems
title_full_unstemmed MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring Systems
title_short MRTMD: A Multi-Resolution Dataset for Evaluating Object Detection in Traffic Monitoring Systems
title_sort mrtmd a multi resolution dataset for evaluating object detection in traffic monitoring systems
topic Dataset vehicle detection
high resolution image dataset
number plate recognition
computer vision
url https://ieeexplore.ieee.org/document/11071529/
work_keys_str_mv AT markbugeja mrtmdamultiresolutiondatasetforevaluatingobjectdetectionintrafficmonitoringsystems
AT matthiasbartolo mrtmdamultiresolutiondatasetforevaluatingobjectdetectionintrafficmonitoringsystems
AT matthewmontebello mrtmdamultiresolutiondatasetforevaluatingobjectdetectionintrafficmonitoringsystems
AT dylanseychell mrtmdamultiresolutiondatasetforevaluatingobjectdetectionintrafficmonitoringsystems