Abstract
Particle filters allow for visual trackers with nonlinear measurements. In this paper we consider three different non-linear visual measurement cues, based on object detection, foreground segmentation and colour matching. Novel ways to obtain robust measurement likelihoods under a unified representation scheme are discussed, followed by a likelihood combination scheme for fusion. The resulting single and multi-cue particle filter trackers are compared in the scope of face tracking.
Originalsprog | Engelsk |
---|---|
Titel | 2013 18th International Conference on Digital Signal Processing, DSP 2013 |
Antal sider | 6 |
Forlag | IEEE Press |
Publikationsdato | 6 dec. 2013 |
Sider | 1-6 |
Artikelnummer | 6622722 |
ISBN (Trykt) | 978-146735805-7 |
ISBN (Elektronisk) | 978-1-4673-5807-1 |
DOI | |
Status | Udgivet - 6 dec. 2013 |
Begivenhed | International conference on Digital Signal Processing - Fira, Grækenland Varighed: 1 jul. 2013 → 3 jul. 2013 Konferencens nummer: 18 http://dsp2013.dspconferences.org/ |
Konference
Konference | International conference on Digital Signal Processing |
---|---|
Nummer | 18 |
Land/Område | Grækenland |
By | Fira |
Periode | 01/07/2013 → 03/07/2013 |
Internetadresse |
Navn | International Conference on Digital Signal Processing proceedings |
---|---|
ISSN | 1546-1874 |