2015 14th IAPR International Conference on Machine Vision Applications (MVA) 2015
DOI: 10.1109/mva.2015.7153212
|View full text |Cite
|
Sign up to set email alerts
|

Lie Algebra-Based Kinematic Prior for 3D Human Pose Tracking

Abstract: We propose a novel kinematic prior for 3D human pose tracking that allows predicting the position in subsequent frames given the current position. We first define a Riemannian manifold that models the pose and extend it to also be able to represent the kinematics. We then learn a joint Gaussian mixture model of both the human pose and the kinematics on this manifold. Finally by conditioning the kinematics on the pose we are able to obtain a distribution of poses for subsequent frames that which can be used as … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2016
2016
2020
2020

Publication Types

Select...
3
1

Relationship

1
3

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 18 publications
0
3
0
Order By: Relevance
“…Roditakis et al [41] estimates hand pose during hand-object interaction by considering spatial constraints induced by the observed hand-object contact points. Deep-learning based methods [42][43][44][45][46][47] for human pose estimation use large datasets to learn the space of natural human poses. On top of this, Brau et al [45] enforce constraints on body part lengths.…”
Section: Literature Overviewmentioning
confidence: 99%
“…Roditakis et al [41] estimates hand pose during hand-object interaction by considering spatial constraints induced by the observed hand-object contact points. Deep-learning based methods [42][43][44][45][46][47] for human pose estimation use large datasets to learn the space of natural human poses. On top of this, Brau et al [45] enforce constraints on body part lengths.…”
Section: Literature Overviewmentioning
confidence: 99%
“…As the strength of this model holds on the fact it can quickly estimate distributions for missing limbs, if it were feasible to integrate it with an occlusion estimator, it would be possible to handle occlusions in an elegant manner. Furthermore, as we show in (Simo-Serra et al, 2015c), it is possible to use the same framework for tracking. Therefore another logical extension of the work presented in this thesis would be to tackle the problem of 3D human pose tracking.…”
Section: Future Workmentioning
confidence: 98%
“…Additionally, we show that this scales well to large datasets and allows real-time sampling from the model. This work was published in (Simo-Serra et al, 2014b), with an extension for estimating velocities published in (Simo-Serra et al, 2015c).…”
Section: Contributionsmentioning
confidence: 99%