Finding Moving Shapes by Continuous-Model Evidence Gathering
Finding Moving Shapes by Continuous-Model Evidence Gathering
Two recent approaches are combined in a new technique to find moving arbitrary shapes. We combine the Velocity Hough Transform, which extracts moving conic sections, with a continuous formulation for arbitrary shape extraction, which avoids discretisation errors associated with GHT methods. The new approach has been evaluated on synthetic and real imagery and is demonstrated to provide motion analysis that is resilient to noise and to be able to detect its target shapes, which are both moving and arbitrary. Further, it is shown to have performance advantages over contemporaneous single-image extraction techniques. Finally, it appears to offer improved immunity to noise and occlusion, consistent with evidence gathering techniques, as shown by results on real images.
554-563
Grant, Michael G.
835c848a-f26c-4474-b0f7-8465d44bdacf
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Pridmore, Tony
f3982d50-b541-4f12-8868-350427c8ea9f
Elliman, David
c37c0afa-4d5e-4604-968a-54f254214619
September 1999
Grant, Michael G.
835c848a-f26c-4474-b0f7-8465d44bdacf
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Pridmore, Tony
f3982d50-b541-4f12-8868-350427c8ea9f
Elliman, David
c37c0afa-4d5e-4604-968a-54f254214619
Grant, Michael G., Nixon, Mark S. and Lewis, Paul H.
(1999)
Finding Moving Shapes by Continuous-Model Evidence Gathering.
Pridmore, Tony and Elliman, David
(eds.)
Proceedings British Machine Vision Conference 1999, BMVC99.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
Two recent approaches are combined in a new technique to find moving arbitrary shapes. We combine the Velocity Hough Transform, which extracts moving conic sections, with a continuous formulation for arbitrary shape extraction, which avoids discretisation errors associated with GHT methods. The new approach has been evaluated on synthetic and real imagery and is demonstrated to provide motion analysis that is resilient to noise and to be able to detect its target shapes, which are both moving and arbitrary. Further, it is shown to have performance advantages over contemporaneous single-image extraction techniques. Finally, it appears to offer improved immunity to noise and occlusion, consistent with evidence gathering techniques, as shown by results on real images.
More information
Published date: September 1999
Venue - Dates:
Proceedings British Machine Vision Conference 1999, BMVC99, 1999-09-01
Organisations:
Web & Internet Science, Southampton Wireless Group
Identifiers
Local EPrints ID: 251949
URI: http://eprints.soton.ac.uk/id/eprint/251949
PURE UUID: eb888aea-2630-4b2b-b79d-feba5401a2a2
Catalogue record
Date deposited: 05 Jul 2001
Last modified: 15 Mar 2024 02:34
Export record
Contributors
Author:
Michael G. Grant
Author:
Paul H. Lewis
Editor:
Tony Pridmore
Editor:
David Elliman
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
