University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Natural action recognition using invariant 3D motion encoding

Hadfield, S, Lebeda, K and Bowden, R Natural action recognition using invariant 3D motion encoding Proceedings of the European Conference on Computer Vision (ECCV), 8690. pp. 758-771.

[img] Text
Hadfield_ECCV_2014pp.pdf - ["content_typename_Submitted version (pre-print)" not defined]
Restricted to Repository staff only
Available under License : See the attached licence file.

Download (3MB)
[img] PDF (licence)
SRI_deposit_agreement.pdf
Restricted to Repository staff only
Available under License : See the attached licence file.

Download (33kB)

Abstract

We investigate the recognition of actions "in the wild"’ using 3D motion information. The lack of control over (and knowledge of) the camera configuration, exacerbates this already challenging task, by introducing systematic projective inconsistencies between 3D motion fields, hugely increasing intra-class variance. By introducing a robust, sequence based, stereo calibration technique, we reduce these inconsistencies from fully projective to a simple similarity transform. We then introduce motion encoding techniques which provide the necessary scale invariance, along with additional invariances to changes in camera viewpoint. On the recent Hollywood 3D natural action recognition dataset, we show improvements of 40% over previous state-of-the-art techniques based on implicit motion encoding. We also demonstrate that our robust sequence calibration simplifies the task of recognising actions, leading to recognition rates 2.5 times those for the same technique without calibration. In addition, the sequence calibrations are made available.

Item Type: Article
Authors :
AuthorsEmailORCID
Hadfield, SUNSPECIFIEDUNSPECIFIED
Lebeda, KUNSPECIFIEDUNSPECIFIED
Bowden, RUNSPECIFIEDUNSPECIFIED
Identification Number : https://doi.org/10.1007/978-3-319-10605-2_49
Contributors :
ContributionNameEmailORCID
EditorTuytelaars, TUNSPECIFIEDUNSPECIFIED
EditorSchiele, BUNSPECIFIEDUNSPECIFIED
EditorPajdla, TUNSPECIFIEDUNSPECIFIED
EditorFleet, DUNSPECIFIEDUNSPECIFIED
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 28 Mar 2017 10:56
Last Modified : 28 Mar 2017 10:56
URI: http://epubs.surrey.ac.uk/id/eprint/808952

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