Presentation 2007-03-15
Object Tracking using Particle Filter based on Displacement Estimation by Reconnoitering
Keiichi SUZUKAWA, Yasushi KANAZAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a robust object tracking method using an extended particle filter. In object tracking using a normal particle filter, we often fail tracking the object which has large or rapid motion. If we distribute the particles widely in such cases, the accuracy of tracking is decreased unfortunately. Here, we extend the prediction framework of a particle filter for tracking such a quickly or largely moving object. We first distribute some particles for reconnoitering the moving object and compute the likelihoods of the reconnaissances. We then estimate the displacement of the target from the likelihoods and distribute all the particles using the estimated displacement. If the obtained likelihoods are insufficiently, we repeat the reconnoitering cycle. This framework makes tracking be robustly and accurately. We show the effectiveness of our method by the real image examples.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) object tracking / particle filter / reconnoitering / displacement estimation
Paper # PRMU2006-242
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/3/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Object Tracking using Particle Filter based on Displacement Estimation by Reconnoitering
Sub Title (in English)
Keyword(1) object tracking
Keyword(2) particle filter
Keyword(3) reconnoitering
Keyword(4) displacement estimation
1st Author's Name Keiichi SUZUKAWA
1st Author's Affiliation Department of Knowledge-based Information Engineering, Toyohashi University of Technology()
2nd Author's Name Yasushi KANAZAWA
2nd Author's Affiliation Department of Knowledge-based Information Engineering, Toyohashi University of Technology
Date 2007-03-15
Paper # PRMU2006-242
Volume (vol) vol.106
Number (no) 605
Page pp.pp.-
#Pages 6
Date of Issue