Outlier rejection in deformable model tracking

Siome Goldenstein, Christian Vogler, Jorge Stolfi, Vladimir Pavlovic, Dimitris Metaxas

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

Abstract

Deformable model tracking is a powerful methodology that allows us to track the evolution of high-dimensional parameter vectors from uncalibrated monocular video sequences. The core of the approach consists of using low-level vision algorithms, such as edge trackers or optical flow, to collect a large number of 2D displacements, or motion measurements, at selected model points and mapping them into 3D space with the model Jacobians. However, the low-level algorithms are prone to errors and outliers, which can skew the entire tracking procedure if left unchecked. There are several known techniques in the literature, such as RANSAC, that can find and reject outliers. Unfortunately, these approaches are not easily mapped into the deformable model tracking framework, where there is no closed-form algebraic mapping from samples to the underlying parameter space. In this paper we present two simple, yet effective ways to find the outliers. We validate and compare these approaches in an 11-parameter deformable face tracking application against ground truth data.

Original languageEnglish (US)
Article number1384808
JournalIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2004-January
Issue numberJanuary
DOIs
StatePublished - 2004
Event2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004 - Washington, United States
Duration: Jun 27 2004Jul 2 2004

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition

Keywords

  • "3D Face Tracking"
  • "Deformable Models"
  • "Outlier Rejection"
  • "Robust Methods"

Fingerprint

Dive into the research topics of 'Outlier rejection in deformable model tracking'. Together they form a unique fingerprint.

Cite this