University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Learning Markerless Human Pose Estimation from Multiple Viewpoint Video

Trumble, Matthew, Gilbert, Andrew, Hilton, Adrian and Collomosse, John (2016) Learning Markerless Human Pose Estimation from Multiple Viewpoint Video In: VARVAI 2016 in conjunction with ECCV 2016, 2016-10-08 - 2016-10-16, Amsterdam, Netherlands.

[img]
Preview
Text
0002.pdf - Accepted version Manuscript
Available under License : See the attached licence file.

Download (2MB) | Preview
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

We present a novel human performance capture technique capable of robustly estimating the pose (articulated joint positions) of a performer observed passively via multiple view-point video (MVV). An affine invariant pose descriptor is learned using a convolutional neural network (CNN) trained over volumetric data extracted from a MVV dataset of diverse human pose and appearance. A manifold embedding is learned via Gaussian Processes for the CNN descriptor and articulated pose spaces enabling regression and so estimation of human pose from MVV input. The learned descriptor and manifold are shown to generalise over a wide range of human poses, providing an efficient performance capture solution that requires no fiducials or other markers to be worn. The system is evaluated against ground truth joint configuration data from a commercial marker-based pose estimation system

Item Type: Conference or Workshop Item (Conference Paper)
Subjects : Electronic Engineering
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Trumble, Matthewmatthew.trumble@surrey.ac.ukUNSPECIFIED
Gilbert, AndrewA.Gilbert@surrey.ac.ukUNSPECIFIED
Hilton, AdrianA.Hilton@surrey.ac.ukUNSPECIFIED
Collomosse, JohnJ.Collomosse@surrey.ac.ukUNSPECIFIED
Date : 24 November 2016
Identification Number : 10.1007/978-3-319-49409-8_70
Copyright Disclaimer : The final publication is available at link.springer.com
Contributors :
ContributionNameEmailORCID
UNSPECIFIEDSpringer, UNSPECIFIEDUNSPECIFIED
Uncontrolled Keywords : Deep learning Pose estimation Multiple viewpoint video
Related URLs :
Additional Information : Part of the Lecture Notes in Computer Science book series (LNCS, volume 9915)
Depositing User : Symplectic Elements
Date Deposited : 21 Oct 2016 15:21
Last Modified : 07 Jul 2017 14:11
URI: http://epubs.surrey.ac.uk/id/eprint/812552

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800