Recognising Human and Animal Movement by Symmetry
Recognising Human and Animal Movement by Symmetry
We show how the symmetry of motion, can be extracted by using the Generalised Symmetry Operator for analysing motion and as biometric. This operator, rather than relying on the borders of a shape or on general appearance, locates features by their symmetrical properties. This approach is reinforced by the view from psychology that human gait is a symmetrical pattern of motion, and by other works. We applied our new method to compare animal gait, and for recognition by gait. Results show that the symmetry properties of gait appear to be unique and can indeed be used for analysis and for recognition. We have so far achieved promising recognition rates of over 95%. Performance analysis also suggests that symmetry enjoys practical advantages such as relative immunity to noise with capability to handle occlusion and as such might prove suitable for applications like clip-database browsing.
0-7803-6727-8
290-293
Hayfron-Acquah, James B.
bffee551-1655-495a-92fd-8c548dcef084
Nixon, Mark. S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Carter, John N.
e05be2f9-991d-4476-bb50-ae91606389da
October 2001
Hayfron-Acquah, James B.
bffee551-1655-495a-92fd-8c548dcef084
Nixon, Mark. S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Carter, John N.
e05be2f9-991d-4476-bb50-ae91606389da
Hayfron-Acquah, James B., Nixon, Mark. S. and Carter, John N.
(2001)
Recognising Human and Animal Movement by Symmetry.
Int. Conf. on Image Processing, ICIP 2001.
.
Record type:
Conference or Workshop Item
(Poster)
Abstract
We show how the symmetry of motion, can be extracted by using the Generalised Symmetry Operator for analysing motion and as biometric. This operator, rather than relying on the borders of a shape or on general appearance, locates features by their symmetrical properties. This approach is reinforced by the view from psychology that human gait is a symmetrical pattern of motion, and by other works. We applied our new method to compare animal gait, and for recognition by gait. Results show that the symmetry properties of gait appear to be unique and can indeed be used for analysis and for recognition. We have so far achieved promising recognition rates of over 95%. Performance analysis also suggests that symmetry enjoys practical advantages such as relative immunity to noise with capability to handle occlusion and as such might prove suitable for applications like clip-database browsing.
More information
Published date: October 2001
Additional Information:
Hard Copy & CD-ROM. Organisation: IEEE Signal Processing Society
Venue - Dates:
Int. Conf. on Image Processing, ICIP 2001, 2001-10-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 256143
URI: http://eprints.soton.ac.uk/id/eprint/256143
ISBN: 0-7803-6727-8
PURE UUID: a65d0f9c-3b46-4377-b205-42f91b1fc13f
Catalogue record
Date deposited: 20 Nov 2003
Last modified: 15 Mar 2024 02:34
Export record
Contributors
Author:
James B. Hayfron-Acquah
Author:
John N. Carter
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
