Gait Learning-Based Regenerative Model: a Level Set Approach
Gait Learning-Based Regenerative Model: a Level Set Approach
We propose a learning method for gait synthesis from a sequence of shapes(frames) with the ability to extrapolate to novel data. It involves the application of PCA, first to reduce the data dimensionality to certain features, and second to model corresponding features derived from the training gait cycles as a Gaussian distribution. This approach transforms a non Gaussian shape deformation problem into a Gaussian one by considering features of entire gait cycles as vectors in a Gaussian space. We show that these features which we formulate as continuous functions can be modeled by PCA. We also use this model to in-between (generate intermediate unknown) shapes in the training cycle. Furthermore, this paper demonstrates that the derived features can be used in the identification of pedestrians.
Al-Huseiny, Muayed
89bace65-62ba-4531-a4c2-bae3f1dd0c0f
Mahmoodi, Sasan
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12
August 2010
Al-Huseiny, Muayed
89bace65-62ba-4531-a4c2-bae3f1dd0c0f
Mahmoodi, Sasan
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Al-Huseiny, Muayed, Mahmoodi, Sasan and Nixon, Mark
(2010)
Gait Learning-Based Regenerative Model: a Level Set Approach.
the 20th International Conference on Pattern Recognition, Istanbul, Turkey.
Record type:
Conference or Workshop Item
(Paper)
Abstract
We propose a learning method for gait synthesis from a sequence of shapes(frames) with the ability to extrapolate to novel data. It involves the application of PCA, first to reduce the data dimensionality to certain features, and second to model corresponding features derived from the training gait cycles as a Gaussian distribution. This approach transforms a non Gaussian shape deformation problem into a Gaussian one by considering features of entire gait cycles as vectors in a Gaussian space. We show that these features which we formulate as continuous functions can be modeled by PCA. We also use this model to in-between (generate intermediate unknown) shapes in the training cycle. Furthermore, this paper demonstrates that the derived features can be used in the identification of pedestrians.
Text
ICPR2010.pdf
- Accepted Manuscript
More information
Published date: August 2010
Additional Information:
Event Dates: Auguest 2010
Venue - Dates:
the 20th International Conference on Pattern Recognition, Istanbul, Turkey, 2010-08-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 270823
URI: http://eprints.soton.ac.uk/id/eprint/270823
PURE UUID: 0ab0f59d-64ed-4699-a40c-e1bd49b5cdb8
Catalogue record
Date deposited: 13 Apr 2010 09:00
Last modified: 15 Mar 2024 02:35
Export record
Contributors
Author:
Muayed Al-Huseiny
Author:
Sasan Mahmoodi
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
