Comparing Different Template Features for Recognizing People by Their Gait
Comparing Different Template Features for Recognizing People by Their Gait
To recognize people by their gait from a sequence of images, we have proposed a statistical approach which combined eigenspace transformation (EST) with canonical space transformation (CST) for feature transformation of spatial templates. This approach is used to reduce data dimensionality and to optimize the class separability of different gait sequences simultaneously. Good recognition rates have been achieved. Here, we incorporate temporal information from optical flows into three kinds of temporal templates and use them as features for gait recognition in addition to the spatial templates. The recognition performance for four kinds of template features has been evaluated in this paper. Experimental results show that spatial templates, horizontal-flow templates and the combined horizontal-flow and vertical-flow templates are better than vertical-flow templates for gait recognition.
639-648
Huang, P.S.
a46d0155-1e6b-4874-ae22-b199c22d2f28
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
Nixon, M.S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
September 1998
Huang, P.S.
a46d0155-1e6b-4874-ae22-b199c22d2f28
Harris, C.J.
c4fd3763-7b3f-4db1-9ca3-5501080f797a
Nixon, M.S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Huang, P.S., Harris, C.J. and Nixon, M.S.
(1998)
Comparing Different Template Features for Recognizing People by Their Gait.
Proc. of Ninth British Machine Vision Conference.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
To recognize people by their gait from a sequence of images, we have proposed a statistical approach which combined eigenspace transformation (EST) with canonical space transformation (CST) for feature transformation of spatial templates. This approach is used to reduce data dimensionality and to optimize the class separability of different gait sequences simultaneously. Good recognition rates have been achieved. Here, we incorporate temporal information from optical flows into three kinds of temporal templates and use them as features for gait recognition in addition to the spatial templates. The recognition performance for four kinds of template features has been evaluated in this paper. Experimental results show that spatial templates, horizontal-flow templates and the combined horizontal-flow and vertical-flow templates are better than vertical-flow templates for gait recognition.
More information
Published date: September 1998
Additional Information:
Organisation: BMVA Address: Southampton, UK
Venue - Dates:
Proc. of Ninth British Machine Vision Conference, 1998-09-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 250437
URI: http://eprints.soton.ac.uk/id/eprint/250437
PURE UUID: 306cbe6a-4958-4b11-b22d-b01f4272e0b9
Catalogue record
Date deposited: 01 Dec 1999
Last modified: 15 Mar 2024 02:34
Export record
Contributors
Author:
P.S. Huang
Author:
C.J. Harris
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
