Guiding Optical Flow Estimation
Guiding Optical Flow Estimation
We show how optical flow estimates can be combined with boundary estimation to improve estimates of motion. The improvement is associated with blending of estimates from complementary bases of operation. The paper combines a phase-based method for optical flow with a time extended version of the phase congruency operator. By evaluation on synthetic and real image sequences, the combination of the two techniques is shown to improve motion estimation with particular advantages at motion boundaries, regions which have posed considerable difficulty for previous motion estimation techniques. The advantage is derived using the moving feature information in an extended phase congruency operator to constrain correct data in the optical flow field.
Motion Segmentation, Mixture Models, Gait, Moving Objects
681-690
Myerscough, Peter J
f13012e0-da87-40c1-bac6-2ca00cdef8bb
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Carter, John N.
e05be2f9-991d-4476-bb50-ae91606389da
Harvey, Richard
4a98201d-e9d2-4f18-b7d0-b25f4ed474fd
Bagham, J. Andrew
cd70e71d-4d38-4f89-ad7b-9ba6da403a10
2003
Myerscough, Peter J
f13012e0-da87-40c1-bac6-2ca00cdef8bb
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Carter, John N.
e05be2f9-991d-4476-bb50-ae91606389da
Harvey, Richard
4a98201d-e9d2-4f18-b7d0-b25f4ed474fd
Bagham, J. Andrew
cd70e71d-4d38-4f89-ad7b-9ba6da403a10
Myerscough, Peter J, Nixon, Mark S. and Carter, John N.
(2003)
Guiding Optical Flow Estimation.
Harvey, Richard and Bagham, J. Andrew
(eds.)
British Machine Vision Conference, Norwich.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
We show how optical flow estimates can be combined with boundary estimation to improve estimates of motion. The improvement is associated with blending of estimates from complementary bases of operation. The paper combines a phase-based method for optical flow with a time extended version of the phase congruency operator. By evaluation on synthetic and real image sequences, the combination of the two techniques is shown to improve motion estimation with particular advantages at motion boundaries, regions which have posed considerable difficulty for previous motion estimation techniques. The advantage is derived using the moving feature information in an extended phase congruency operator to constrain correct data in the optical flow field.
Text
myerscough_bmvc2003.pdf
- Other
More information
Published date: 2003
Additional Information:
Event Dates: 2003
Venue - Dates:
British Machine Vision Conference, Norwich, 2003-01-01
Keywords:
Motion Segmentation, Mixture Models, Gait, Moving Objects
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 258443
URI: http://eprints.soton.ac.uk/id/eprint/258443
PURE UUID: 6dd2eccc-be90-4237-9f9f-aad390c50e84
Catalogue record
Date deposited: 20 Nov 2003
Last modified: 15 Mar 2024 02:35
Export record
Contributors
Author:
Peter J Myerscough
Author:
John N. Carter
Editor:
Richard Harvey
Editor:
J. Andrew Bagham
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
