Evaluating the covariance matrix constraints for data-driven statistical human motion reconstruction

Mousas, Christos, Newbury, Paul and Anagnostopoulos, Christos-Nikolaos (2014) Evaluating the covariance matrix constraints for data-driven statistical human motion reconstruction. ACM/Eurographics Spring Conference on Computer Graphics, Vienna, 28th - 30th May 2014. Published in: SCCG '14: Proceedings of the 30th Spring Conference on Computer Graphics. 99-106. Association for Computing Machinery, New York, NY, United States. ISBN 9781450330701

This is the latest version of this item.

[img] PDF (For REF only) - Published Version
Restricted to SRO admin only

Download (708kB)


This paper presents the evaluation process of the character's motion reconstruction while constraints are applied to the covariance matrix of the motion prior learning process. For the evaluation process, a maximum a posteriori (MAP) framework is first generated, which receives input trajectories and reconstructs the motion of the character. Then, using various methods to constrain the covariance matrix, information that reflects certain assumptions about the motion reconstruction process is retrieved. Each of the covariance matrix constraints are evaluated by its ability to reconstruct the desired motion sequences either by using a large amount of motion data or by using a small dataset that contains only specific motions.

Item Type: Conference Proceedings
Schools and Departments: School of Engineering and Informatics > Informatics
Subjects: Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Depositing User: Christos Mousas
Date Deposited: 29 Sep 2014 08:39
Last Modified: 30 Oct 2020 14:08
URI: http://sro.sussex.ac.uk/id/eprint/47155

Available Versions of this Item

View download statistics for this item

📧 Request an update