University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Putting the pieces together: Connected Poselets for human pose estimation

Holt, B, Ong, E-J, Cooper, H and Bowden, R (2011) Putting the pieces together: Connected Poselets for human pose estimation In: ICCV Workshops 2011, 2011-11-06 - 2011-11-13, Barcelona, Spain.

[img]
Preview
PDF
Holt2011Putting.pdf
Available under License : See the attached licence file.

Download (1109Kb)
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf

Download (32Kb)

Abstract

We propose a novel hybrid approach to static pose estimation called Connected Poselets. This representation combines the best aspects of part-based and example-based estimation. First detecting poselets extracted from the training data; our method then applies a modified Random Decision Forest to identify Poselet activations. By combining keypoint predictions from poselet activitions within a graphical model, we can infer the marginal distribution over each keypoint without any kinematic constraints. Our approach is demonstrated on a new publicly available dataset with promising results.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Copyright 2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Divisions: Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Depositing User: Symplectic Elements
Date Deposited: 22 May 2012 09:17
Last Modified: 23 Sep 2013 19:24
URI: http://epubs.surrey.ac.uk/id/eprint/531437

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