TU-DAT: A Computer Vision Dataset on Road Traffic Anomalies

This paper introduces TU-DAT, a novel, freely downloadable computer vision dataset for analyzing traffic accidents using roadside cameras. TU-DAT addresses the lack of public datasets for training and evaluating models focused on automatic detection and prediction of road anomalies. It comprises app...

Full description

Saved in:
Bibliographic Details
Main Authors: Pavana Pradeep Kumar, Krishna Kant
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3259
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850160698377633792
author Pavana Pradeep Kumar
Krishna Kant
author_facet Pavana Pradeep Kumar
Krishna Kant
author_sort Pavana Pradeep Kumar
collection DOAJ
description This paper introduces TU-DAT, a novel, freely downloadable computer vision dataset for analyzing traffic accidents using roadside cameras. TU-DAT addresses the lack of public datasets for training and evaluating models focused on automatic detection and prediction of road anomalies. It comprises approximately 280 real-world and simulated videos, collected from traffic CCTV footage, news reports, and high-fidelity simulations generated using BeamNG.drive. This hybrid composition captures aggressive driving behaviors—such as tailgating, weaving, and speeding—under diverse environmental conditions. It includes spatiotemporal annotations and structured metadata such as vehicle trajectories, collision types, and road conditions. These features enable robust model training for anomaly detection, spatial reasoning, and vision–language model (VLM) enhancement. TU-DAT has already been utilized in experiments demonstrating improved performance of hybrid deep learning- and logic-based reasoning frameworks, validating its practical utility for real-time traffic monitoring, autonomous vehicle safety, and driver behavior analysis. The dataset serves as a valuable resource for researchers, engineers, and policymakers aiming to develop intelligent transportation systems that proactively reduce road accidents.
format Article
id doaj-art-d8a150c0b4d24e1e9f1aff983f4af4c2
institution OA Journals
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-d8a150c0b4d24e1e9f1aff983f4af4c22025-08-20T02:23:05ZengMDPI AGSensors1424-82202025-05-012511325910.3390/s25113259TU-DAT: A Computer Vision Dataset on Road Traffic AnomaliesPavana Pradeep Kumar0Krishna Kant1Computer and Information Sciences Department, Temple University, Philadelphia, PA 19122, USAComputer and Information Sciences Department, Temple University, Philadelphia, PA 19122, USAThis paper introduces TU-DAT, a novel, freely downloadable computer vision dataset for analyzing traffic accidents using roadside cameras. TU-DAT addresses the lack of public datasets for training and evaluating models focused on automatic detection and prediction of road anomalies. It comprises approximately 280 real-world and simulated videos, collected from traffic CCTV footage, news reports, and high-fidelity simulations generated using BeamNG.drive. This hybrid composition captures aggressive driving behaviors—such as tailgating, weaving, and speeding—under diverse environmental conditions. It includes spatiotemporal annotations and structured metadata such as vehicle trajectories, collision types, and road conditions. These features enable robust model training for anomaly detection, spatial reasoning, and vision–language model (VLM) enhancement. TU-DAT has already been utilized in experiments demonstrating improved performance of hybrid deep learning- and logic-based reasoning frameworks, validating its practical utility for real-time traffic monitoring, autonomous vehicle safety, and driver behavior analysis. The dataset serves as a valuable resource for researchers, engineers, and policymakers aiming to develop intelligent transportation systems that proactively reduce road accidents.https://www.mdpi.com/1424-8220/25/11/3259intelligent transport systemsanomaly detection in road traffic
spellingShingle Pavana Pradeep Kumar
Krishna Kant
TU-DAT: A Computer Vision Dataset on Road Traffic Anomalies
Sensors
intelligent transport systems
anomaly detection in road traffic
title TU-DAT: A Computer Vision Dataset on Road Traffic Anomalies
title_full TU-DAT: A Computer Vision Dataset on Road Traffic Anomalies
title_fullStr TU-DAT: A Computer Vision Dataset on Road Traffic Anomalies
title_full_unstemmed TU-DAT: A Computer Vision Dataset on Road Traffic Anomalies
title_short TU-DAT: A Computer Vision Dataset on Road Traffic Anomalies
title_sort tu dat a computer vision dataset on road traffic anomalies
topic intelligent transport systems
anomaly detection in road traffic
url https://www.mdpi.com/1424-8220/25/11/3259
work_keys_str_mv AT pavanapradeepkumar tudatacomputervisiondatasetonroadtrafficanomalies
AT krishnakant tudatacomputervisiondatasetonroadtrafficanomalies