Publication Details

Vehicle Re-Identification for Automatic Video Traffic Surveillance

ZAPLETAL Dominik and HEROUT Adam. Vehicle Re-Identification for Automatic Video Traffic Surveillance. In: International Workshop on Automatic Traffic Surveillance (CVPR 2016). Las Vegas: IEEE Computer Society, 2016, pp. 1568-1574. ISBN 978-0-7695-4989-7.
Czech title
Reidentifikace vozidel pro automatické monitorování dopravy
Type
conference paper
Language
english
Authors
Zapletal Dominik, Ing. (FIT BUT)
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT)
Keywords

vehicle re-identification, traffic monitoring, automatic traffic surveillance

Abstract

This paper proposes an approach to the vehicle re-identification problem in a multiple camera system.  We focused on the re-identification itself assuming that the vehicle detection problem is already solved including extraction of a full-fledged 3D bounding box. The re-identification problem is solved by using color histograms and histograms of oriented gradients by a linear regressor.  The features are used in separate models in order to get the best results in the shortest CPU computation time. The proposed method works with a high accuracy (60% true positives retrieved with 10% false positive rate on a challenging subset of the test data) in 85 milliseconds of the CPU (Core i7) computation time per one vehicle re-identification assuming the fullHD resolution video input. The applications of this work include finding important parameters such as travel time, traffic flow, or traffic information in a distributed traffic surveillance and monitoring system.

Published
2016
Pages
1568-1574
Proceedings
International Workshop on Automatic Traffic Surveillance (CVPR 2016)
Conference
Computer Vision and Pattern Recognition 2016, Las Vegas, US
ISBN
978-0-7695-4989-7
Publisher
IEEE Computer Society
Place
Las Vegas, US
DOI
UT WoS
000391572100188
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB11172,
   author = "Dominik Zapletal and Adam Herout",
   title = "Vehicle Re-Identification for Automatic Video Traffic Surveillance",
   pages = "1568--1574",
   booktitle = "International Workshop on Automatic Traffic Surveillance (CVPR 2016)",
   year = 2016,
   location = "Las Vegas, US",
   publisher = "IEEE Computer Society",
   ISBN = "978-0-7695-4989-7",
   doi = "10.1109/CVPRW.2016.195",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11172"
}
Back to top