University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Guided Optimisation through Classification and Regression for Hand Pose Estimation

Krejov, Philip, Gilbert, Andrew and Bowden, Richard (2016) Guided Optimisation through Classification and Regression for Hand Pose Estimation Computer Vision and Image Understanding, 155. pp. 124-138.

[img] Text
Krejov_CVIU_2016.pdf - Accepted version Manuscript
Restricted to Repository staff only until 29 November 2017.
Available under License : See the attached licence file.

Download (13MB)
[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

This paper presents an approach to hand pose estimation that combines discriminative and model-based methods to leverage the advantages of both. Randomised Decision Forests are trained using real data to provide fast coarse segmentation of the hand. The segmentation then forms the basis of constraints applied in model fitting, using an efficient projected Gauss-Seidel solver, which enforces temporal continuity and kinematic limitations. However, when fitting a generic model to multiple users with varying hand shape, there is likely to be residual errors between the model and their hand. Also, local minima can lead to failures in tracking that are difficult to recover from. Therefore, we introduce an error regression stage that learns to correct these instances of optimisation failure. The approach provides improved accuracy over the current state of the art methods, through the inclusion of temporal cohesion and by learning to correct from failure cases. Using discriminative learning, our approach performs guided optimisation, greatly reducing model fitting complexity and radically improves efficiency. This allows tracking to be performed at over 40 frames per second using a single CPU thread.

Item Type: Article
Subjects : Electronic Engineering
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
NameEmailORCID
Krejov, Philipp.krejov@surrey.ac.ukUNSPECIFIED
Gilbert, AndrewA.Gilbert@surrey.ac.ukUNSPECIFIED
Bowden, RichardR.Bowden@surrey.ac.ukUNSPECIFIED
Date : 29 November 2016
Identification Number : 10.1016/j.cviu.2016.11.005
Copyright Disclaimer : © 2016. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
Uncontrolled Keywords : Hand Pose Estimation, Human Computer Interaction, Hand Tracking,, Finger Tracking, Model Optimisation, Random Decision Forest, Discriminative, Learning, Regression
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 30 Nov 2016 14:13
Last Modified : 07 Jul 2017 11:43
URI: http://epubs.surrey.ac.uk/id/eprint/813012

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