Visual Tracking of Multiple Targets by Multi-Bernoulli Filtering of Background Subtracted Image Data

Hoseinnezhad, R, Vo, B and Nguyen-Vu, T 2011, 'Visual Tracking of Multiple Targets by Multi-Bernoulli Filtering of Background Subtracted Image Data', in Gerhard Goos, Juris Hartmanis, and Jan van Leeuwen (ed.) ICSI 2011, Part II, LNCS 6729, Chongqing, China, 12-15 June, 2011, pp. 509-518.


Document type: Conference Paper
Collection: Conference Papers

Title Visual Tracking of Multiple Targets by Multi-Bernoulli Filtering of Background Subtracted Image Data
Author(s) Hoseinnezhad, R
Vo, B
Nguyen-Vu, T
Year 2011
Conference name International Conference on Swarm Intelligence
Conference location Chongqing, China
Conference dates 12-15 June, 2011
Proceedings title ICSI 2011, Part II, LNCS 6729
Editor(s) Gerhard Goos, Juris Hartmanis, and Jan van Leeuwen
Publisher Springer-Verlag
Place of publication Berlin Heidelberg
Start page 509
End page 518
Total pages 10
Abstract Most visual multi-target tracking techniques in the literature employ a detection routine to map the image data to point measurements that are usually further processed by a filter. In this paper, we present a visual tracking technique based on a multi-target filtering algorithm that operates directly on the image observations and does not require any detection nor training patterns. Instead, we use the recent history of image data for non-parametric background subtraction and apply an efficient multi-target filtering technique, known as the multi-Bernoulli filter, on the resulting grey scale image data. In our experiments, we applied our method to track multiple people in three video sequences from the CAVIAR dataset. The results show that our method can automatically track multiple interacting targets and quickly finds targets entering or leaving the scene.
Subjects Computer Vision
Control Systems, Robotics and Automation
Signal Processing
Keyword(s) visual tracking
Bayesian estimation
multi-target tracking
random finite sets
multi-Bernoulli
DOI - identifier 10.1007/978-3-642-21524-7_63
Copyright notice © 2011 Springer-Verlag.
ISBN 9783642215230
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 6 times in Scopus Article | Citations
Altmetric details:
Access Statistics: 175 Abstract Views  -  Detailed Statistics
Created: Fri, 06 Jan 2012, 07:48:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us