Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/20284

Title: Object localisation via action recognition
Authors: Darby, John
Li, Baihua
Cunningham, Ryan
Costen, Nicholas
Issue Date: 2012
Publisher: IEEE (© ICPR2012 Organizing Committee)
Citation: DARBY, J. ... et al, 2012. Object localisation via action recognition. Proceedings - 21st International Conference on Pattern Recognition, 11th-15th November 2012, Tsukuba, pp.817-820
Abstract: The aim of this paper is to track objects during their use by humans. The task is difficult because these objects are small, fast-moving and often occluded by the user. We present a novel solution based on cascade action recognition, a learned mapping between body-and object-poses, and a hierarchical extension of importance sampling. During tracking, body pose estimates from a Kinect sensor are classified between action classes by a Support Vector Machine and converted to discriminative object pose hypotheses using a {body, object} pose mapping. They are then mixed with generative hypotheses by the importance sampler and evaluated against the image. The approach out-performs a state of the art adaptive tracker for localisation of 14/15 test implements and additionally gives object classifications and 3D object pose estimates.
Description: This is the accepted manuscript version of the paper. IEEE (© ICPR2012 Organizing Committee). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Version: Accepted for publication
URI: https://dspace.lboro.ac.uk/2134/20284
Publisher Link: http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=6460259
ISBN: 9784990644109
ISSN: 1051-4651
Appears in Collections:Conference Papers and Presentations (Computer Science)

Files associated with this item:

File Description SizeFormat
ICPR2012-CR.pdfAccepted version1.68 MBAdobe PDFView/Open

 

SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.