Title :
An object tracking in particle filtering and data association framework, using SIFT features
Author :
Souded, M. ; Giulieri, Laurent ; Bremond, Francois
Author_Institution :
Digital Barriers, Sophia Antipolis, France
Abstract :
In this paper, we propose a novel approach for multi-object tracking for video surveillance with a single static camera using particle filtering and data association. The proposed method allows for real-time tracking and deals with the most important challenges: (1) selecting and tracking real objects of interest in noisy environments and (2) managing occlusion. We will consider tracker inputs from classic motion detection (based on background subtraction and clustering). Particle filtering has proven very successful for non-linear and non-Gaussian estimation problems. This article presents SIFT feature tracking in a particle filtering and data association framework. The performance of the proposed algorithm is evaluated on sequences from ETISEO, CAVIAR, PETS2001 and VS-PETS2003 datasets in order to show the improvements relative to the current state-of-the-art.
Keywords :
cameras; feature extraction; hidden feature removal; image motion analysis; object tracking; particle filtering (numerical methods); pattern clustering; sensor fusion; transforms; video surveillance; CAVIAR datasets; ETISEO datasets; PETS2001 datasets; SIFT feature tracking; VS-PETS2003 datasets; background subtraction; classic motion detection; clustering; data association framework; multiobject tracking; noisy environments; nonGaussian estimation problem; nonlinear estimation problem; occlusion; particle filtering; real-time tracking; single static camera; video surveillance; Objects tracking; Particle filtering; SIFT; Video surveillance;
Conference_Titel :
Imaging for Crime Detection and Prevention 2011 (ICDP 2011), 4th International Conference on
Conference_Location :
London
Electronic_ISBN :
978-1-84919-565-2
DOI :
10.1049/ic.2011.0104