11 pages, 5 figures, 3 tables. ; This paper proposes an action specific model which automatically learns the variability of 3D human postures observed in a set of training sequences. First, a Dynamic Programing synchronization algorithm is presented in order to establish a mapping between postures from different walking cycles, so the whole training set can be synchronized to a common time pattern. Then, the model is trained using the public CMU motion capture dataset for the walking action, and a mean walking performance is automatically learnt. Additionally statistics about the observed variability of the postures and motion direction are also computed at each time step. As a result, in this work we have extended a similar action model successfully used for tracking, by providing facilities for gait analysis and gait recognition applications. ; This work has been supported by EC grants IST-027110 for the HERMES project and IST-045547 for the VIDI-Video project, and by Spanish MEC under projects TIN2006-14606 and DPI-2004-5414. Jordi Gonzàlez also acknowledges the support of a Juan de la Cierva Postdoctoral fellowship from the Spanish MEC. The database used in this project was obtained from mocap.cs.cmu.edu which was created with funding from NSF EIA-0196217. ; http://hdl.handle.net/2117/2702 ; Peer reviewed
Automatic learning of 3D pose variability in walking performances for gait analysis
2008-01-01
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC: | 629 |
Gait Pose Estimation Based on Manifold Learning
British Library Conference Proceedings | 2014
|Gait Pose Estimation Based on Manifold Learning
Springer Verlag | 2014
|Metronome cueing of walking reduces gait variability after a cerebellar stroke
BASE | 2016
|Towards Pose Invariant Gait Reconstruction
British Library Conference Proceedings | 2005
|Towards pose invariant gait reconstruction
IEEE | 2005
|