MEDAVET: Traffic Vehicle Anomaly Detection Mechanism based on spatial and temporal structures in vehicle traffic
Authors:
- Ana Rosalía Huamán ReynaARAna Rosalía Huamán Reyna
- Alex Josué Flórez FarfánAFAlex Josué Flórez Farfán
- Geraldo P. Rocha FilhoGFGeraldo P. Rocha Filho
- Sandra SampaioSSSandra Sampaio
- Robson De GrandeRGRobson De Grande
- Luis Hideo Vasconcelos NakamuraLNLuis Hideo Vasconcelos Nakamura
- Rodolfo Ipolito MeneguetteRodolfo Ipolito Meneguette
- 4 March 2024
- journal article
- research article
- Published by Sociedade Brasileira de Computação in Journal of Internet Services and Applications
- Vol. 15 (1) , 25-38
Abstract
Road traffic anomaly detection is vital for reducing the number of accidents and ensuring a more efficient and safer transportation system. In highways, where traffic volume and speed limits are high, anomaly detection is not only essential but also considerably more challenging, given the multitude of fast-moving vehicles, often observed from extended distances and diverse angles, occluded by other objects, and subjected to variations in illumination and adverse weather conditions. This complexity has meant that human error often limits anomaly detection, making the role of computer vision systems integral to its success. In light of these challenges, this paper introduces MEDAVET - a sophisticated computer vision system engineered with an innovative mechanism that leverages spatial and temporal structures for high-precision traffic anomaly detection on highways. MEDAVET is assessed in its object tracking and anomaly detection efficacy using the UA-DETRAC and Track 4 benchmarks and has its performance compared with that of an array of state-of-the-art systems. The results have shown that, when MEDAVET’s ability to delimit relevant areas of the highway, through a bipartite graph and the Convex Hull algorithm, is paired with its QuadTree-based spatial and temporal approaches for detecting occluded and stationary vehicles, it emerges as superior in precision, compared to its counterparts, and with a competitive computational efficiency.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Deep learning based detection and localization of road accidents from traffic surveillance videosICT Express, 2022
- Predictive Congestion Control based on Collaborative Information Sharing for Vehicular Ad hoc NetworksComputer Networks, 2022
- Intelligent deep fusion network for urban traffic flow anomaly identificationComputer Communications, 2022
- Vehicle detection and tracking based on video image processing in intelligent transportation systemNeural Computing and Applications, 2022
- FairMOT: On the Fairness of Detection and Re-identification in Multiple Object TrackingInternational Journal of Computer Vision, 2021
- Vehicle Artificial Intelligence System Based on Intelligent Image Analysis and 5G NetworkInternational Journal of Wireless Information Networks, 2021
- Innovations and new possibilities of vehicle tracking in transport and forwardingWireless Networks, 2021
- Towards Real-Time Multi-Object Tracking2020
- Joint detection and tracking in videos with identification featuresImage and Vision Computing, 2020
- Gaussian Mixture Models2009