Share Email Print
cover

Proceedings Paper

Real-time vehicle matching for multi-camera tunnel surveillance
Author(s): Vedran Jelača; Jorge Oswaldo Niño Castañeda; Andrés Frías-Velázquez; Aleksandra Pižurica; Wilfried Philips
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Tracking multiple vehicles with multiple cameras is a challenging problem of great importance in tunnel surveillance. One of the main challenges is accurate vehicle matching across the cameras with non-overlapping fields of view. Since systems dedicated to this task can contain hundreds of cameras which observe dozens of vehicles each, for a real-time performance computational efficiency is essential. In this paper, we propose a low complexity, yet highly accurate method for vehicle matching using vehicle signatures composed of Radon transform like projection profiles of the vehicle image. The proposed signatures can be calculated by a simple scan-line algorithm, by the camera software itself and transmitted to the central server or to the other cameras in a smart camera environment. The amount of data is drastically reduced compared to the whole image, which relaxes the data link capacity requirements. Experiments on real vehicle images, extracted from video sequences recorded in a tunnel by two distant security cameras, validate our approach.

Paper Details

Date Published: 2 February 2011
PDF: 8 pages
Proc. SPIE 7871, Real-Time Image and Video Processing 2011, 78710R (2 February 2011); doi: 10.1117/12.876671
Show Author Affiliations
Vedran Jelača, Ghent Univ. (Belgium)
Jorge Oswaldo Niño Castañeda, Ghent Univ. (Belgium)
Andrés Frías-Velázquez, Ghent Univ. (Belgium)
Aleksandra Pižurica, Ghent Univ. (Belgium)
Wilfried Philips, Ghent Univ. (Belgium)


Published in SPIE Proceedings Vol. 7871:
Real-Time Image and Video Processing 2011
Nasser Kehtarnavaz; Matthias F. Carlsohn, Editor(s)

© SPIE. Terms of Use
Back to Top