Publication Details

Fully Automated Real-Time Vehicles Detection and Tracking with Lanes Analysis

SOCHOR Jakub. Fully Automated Real-Time Vehicles Detection and Tracking with Lanes Analysis. In: Proceedings of CESCG 2014. Smolenice: Technical University Wien, 2014, pp. 59-66. ISBN 978-3-9502533-6-8.
Czech title
Plně automatická detekce a sledování vozidel v reálném čase s analýzou pruhů
Type
conference paper
Language
english
Authors
Sochor Jakub, Ing. (DCGM FIT BUT)
Keywords

motion detection, tracking, vehicles, traffic surveillance camera, direction detection, lanes detection, real-time

Abstract

This paper presents a fully automated system for traffic surveillance which is able to count passing cars, determine their direction, and the lane which they are taking. The system works without any manual input whatsoever and it is able to automatically calibrate the camera by detecting vanishing points in the video sequence. The proposed system is able to work in real time and therefore it is ready for deployment in real traffic surveillance applications. The system uses motion detection and tracking with the Kalman filter. The lane detection is based on clustering of trajectories of vehicles. The main contribution is a set of filters which a track has to pass in order to be treated as a vehicle and the full automation of the system. 

Published
2014
Pages
59-66
Proceedings
Proceedings of CESCG 2014
Conference
Central European Seminar on Computer Graphics 2014, Smolenice, SK
ISBN
978-3-9502533-6-8
Publisher
Technical University Wien
Place
Smolenice, SK
BibTeX 
@INPROCEEDINGS{FITPUB10683,
   author = "Jakub Sochor",
   title = "Fully Automated Real-Time Vehicles Detection and Tracking with Lanes Analysis",
   pages = "59--66",
   booktitle = "Proceedings of CESCG 2014",
   year = 2014,
   location = "Smolenice, SK",
   publisher = "Technical University Wien",
   ISBN = "978-3-9502533-6-8",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10683"
}
Back to top