Manifold regularized particle filter for articulated human motion tracking

Adam Gonczarek*, Jakub M. Tomczak

*Corresponding author for this work

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

In this paper, a fully Bayesian approach to articulated human motion tracking from video sequences is presented. First, a filtering procedure with a low-dimensional manifold is derived. Next, we propose a general framework for approximating this filtering procedure based on the particle filter technique. The low-dimensional manifold can be treated as a regularizer which restricts the space of all possible distributions to the space of distributions concentrated around the manifold. We refer to our method as Manifold Regularized Particle Filter. The proposed approach is evaluated using real-life benchmark dataset HumanEva.

Original languageEnglish
Title of host publicationAdvances in Systems Science - Proceedings of the International Conference on Systems Science, ICSS 2013
EditorsJerzy Świątek, Adam Grzech, Paweł Świątek, Jakub M. Tomczak, Jerzy Świątek
PublisherSpringer Verlag
Pages283-293
Number of pages11
ISBN (Electronic)9783319018560
DOIs
Publication statusPublished - 1 Jan 2014
Externally publishedYes
EventInternational Conference on Systems Science, ICSS 2013 - Wroclaw, Poland
Duration: 10 Sept 201312 Sept 2013

Publication series

NameAdvances in Intelligent Systems and Computing
Volume240
ISSN (Print)2194-5357

Conference

ConferenceInternational Conference on Systems Science, ICSS 2013
Country/TerritoryPoland
CityWroclaw
Period10/09/1312/09/13

Keywords

  • Articulated motion tracking
  • Gaussian process latent variable model
  • Generative approach
  • Manifold regularization
  • Particle filter

Fingerprint

Dive into the research topics of 'Manifold regularized particle filter for articulated human motion tracking'. Together they form a unique fingerprint.

Cite this