DETECTION AND LOCALISATION OF STATIONARY OBJECTS WITH A PAIR OF PTZ CAMERAS

Constant Guillot, Quoc-Cuong Pham, Patrick Sayd, Christophe Tilmant, Jean-Marc Lavest

2012

Abstract

We propose a novel approach for detecting and localising stationary objects using a pair of PTZ cameras monitoring a wide scene. First we propose a stationary object detection and labelling algorithm. It relies on the re-identification of foreground blocks of the image and an MRF framework to detect and separate the stationary objects of the scene. Second we propose a geometric approach for robustly matching the detected silhouettes of stationary objects from a pair of PTZ cameras. Our system is tested on challenging sequences which prove its robustness to occlusions even in an unknown non planar 3D scene.

Paper Citation

in Harvard Style

Guillot C., Pham Q., Sayd P., Tilmant C. and Lavest J. (2012). DETECTION AND LOCALISATION OF STATIONARY OBJECTS WITH A PAIR OF PTZ CAMERAS . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 591-596. DOI: 10.5220/0003827205910596

in Bibtex Style

@conference{visapp12,
author={Constant Guillot and Quoc-Cuong Pham and Patrick Sayd and Christophe Tilmant and Jean-Marc Lavest},
title={DETECTION AND LOCALISATION OF STATIONARY OBJECTS WITH A PAIR OF PTZ CAMERAS},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={591-596},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003827205910596},
isbn={978-989-8565-03-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - DETECTION AND LOCALISATION OF STATIONARY OBJECTS WITH A PAIR OF PTZ CAMERAS
SN - 978-989-8565-03-7
AU - Guillot C.
AU - Pham Q.
AU - Sayd P.
AU - Tilmant C.
AU - Lavest J.
PY - 2012
SP - 591
EP - 596
DO - 10.5220/0003827205910596