Fast human pose estimation using 3D Zernike descriptors

Berjón Díez, Daniel and Morán Burgos, Francisco (2012). Fast human pose estimation using 3D Zernike descriptors. In: "Three-Dimensional Image Processing (3DIP) and Applications II", 24/01/2012 - 26/01/2012, Burlingame, California, USA. pp. 1-6. https://doi.org/10.1117/12.908963.

Description

Title: Fast human pose estimation using 3D Zernike descriptors
Author/s:
  • Berjón Díez, Daniel
  • Morán Burgos, Francisco
Item Type: Presentation at Congress or Conference (Article)
Event Title: Three-Dimensional Image Processing (3DIP) and Applications II
Event Dates: 24/01/2012 - 26/01/2012
Event Location: Burlingame, California, USA
Title of Book: Three-Dimensional Image Processing (3DIP) and Applications II
Date: 2012
Volume: 8290
Subjects:
Freetext Keywords: Human pose estimation, computer vision, Zernike moments, parallel computing
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img] PDF - Users in campus UPM only - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (545kB)

Abstract

Markerless video-based human pose estimation algorithms face a high-dimensional problem that is frequently broken down into several lower-dimensional ones by estimating the pose of each limb separately. However, in order to do so they need to reliably locate the torso, for which they typically rely on time coherence and tracking algorithms. Their losing track usually results in catastrophic failure of the process, requiring human intervention and thus precluding their usage in real-time applications. We propose a very fast rough pose estimation scheme based on global shape descriptors built on 3D Zernike moments. Using an articulated model that we configure in many poses, a large database of descriptor/pose pairs can be computed off-line. Thus, the only steps that must be done on-line are the extraction of the descriptors for each input volume and a search against the database to get the most likely poses. While the result of such process is not a fine pose estimation, it can be useful to help more sophisticated algorithms to regain track or make more educated guesses when creating new particles in particle-filter-based tracking schemes. We have achieved a performance of about ten fps on a single computer using a database of about one million entries.

More information

Item ID: 30512
DC Identifier: http://oa.upm.es/30512/
OAI Identifier: oai:oa.upm.es:30512
DOI: 10.1117/12.908963
Deposited by: Memoria Investigacion
Deposited on: 13 Sep 2014 08:32
Last Modified: 22 Sep 2014 11:49
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM