A flexible approach to high performance visualization enabled Augmented Reality

Hughes, CJ ORCID: https://orcid.org/0000-0002-4468-6660 and John, NW 2007, A flexible approach to high performance visualization enabled Augmented Reality , in: EG UK Theory and Practice of Computer Graphics 2007, 13th-15th June 2007, University of Wales, Bangor, UK.

[img]
Preview
PDF (Accepted version with branding) - Accepted Version
Download (247kB) | Preview
Access Information: This paper may be used for non-commercial purposes.

Abstract

Commonly registration and tracking within Augmented Reality (AR) applications have been built around computervision techniques that use limited bold markers, which allow for their orientation to be estimated in real-time. Allattempts to implement AR without specific markers have increased the computational requirements and someinformation about the environment is still needed. In this paper we describe a method that not only provides aflexible platform for supporting AR but also seamlessly deploys High Performance Computing (HPC) resourcesto deal with the additional computational load, as part of the distributed High Performance Visualization (HPV)pipeline used to render the virtual artifacts. Repeatable feature points are extracted from known views of a realobject and then we match the best stored view to the users viewpoint using the matched feature points to estimatethe objects pose. We also show how our AR framework can then be used in the real world by presenting a marker-less AR interface for Transcranial Magnetic Stimulation (TMS).

Item Type: Conference or Workshop Item (Paper)
Schools: Schools > School of Computing, Science and Engineering
Journal or Publication Title: EG UK Theory and Practice of Computer Graphics
Publisher: The Eurographics Association
ISBN: 9783905673630
Related URLs:
Depositing User: Dr Chris Hughes
Date Deposited: 04 Dec 2020 08:50
Last Modified: 04 Dec 2020 11:41
URI: http://usir.salford.ac.uk/id/eprint/59023

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year