Dynamical Simulation Priors for Human Motion Tracking

We propose a simulation-based dynamical motion prior for tracking human motion from video in presence of physical ground-person interactions. Most tracking approaches to date have focused on efficient inference algorithms and/or learning of prior kinematic motion models; however, few can explicitly...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on pattern analysis and machine intelligence Vol. 35; no. 1; pp. 52 - 65
Main Authors:	Vondrak, Marek, Sigal, L., Jenkins, O. C.
Format:	Journal Article
Language:	English
Published:	Los Alamitos, CA IEEE 01.01.2013 IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Applied sciences Articulated tracking Artificial Intelligence Bayesian analysis Bayesian filtering Biological system modeling Computer science; control theory; systems Computer Simulation Dynamics Exact sciences and technology Filtering Filtration Human human motion human pose tracking Human subjects Humans Image Interpretation, Computer-Assisted - methods Inference Joints Joints - anatomy & histology Joints - physiology Kinematics Logical, boolean and switching functions Models, Biological Motors Movement - physiology particle filtering Pattern Recognition, Automated - methods Pattern recognition. Digital image processing. Computational geometry physical simulation physics-based priors Studies Theoretical computing Tracking Trajectory Whole Body Imaging - methods Tracking Video signal Articulated tracking Modeling Multidimensional analysis particle filtering Kinematics Dynamic model Learning algorithm Rigid bodies Bayes estimation Monte Carlo method physical simulation Filtering Motion estimation physics-based priors human pose tracking Monocular vision Inference State space method Bayesian filtering Image analysis Control loop human motion Body movement Motion control Artificial intelligence
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	We propose a simulation-based dynamical motion prior for tracking human motion from video in presence of physical ground-person interactions. Most tracking approaches to date have focused on efficient inference algorithms and/or learning of prior kinematic motion models; however, few can explicitly account for the physical plausibility of recovered motion. Here, we aim to recover physically plausible motion of a single articulated human subject. Toward this end, we propose a full-body 3D physical simulation-based prior that explicitly incorporates a model of human dynamics into the Bayesian filtering framework. We consider the motion of the subject to be generated by a feedback "control loop" in which Newtonian physics approximates the rigid-body motion dynamics of the human and the environment through the application and integration of interaction forces, motor forces, and gravity. Interaction forces prevent physically impossible hypotheses, enable more appropriate reactions to the environment (e.g., ground contacts), and are produced from detected human-environment collisions. Motor forces actuate the body, ensure that proposed pose transitions are physically feasible, and are generated using a motion controller. For efficient inference in the resulting high-dimensional state space, we utilize an exemplar-based control strategy that reduces the effective search space of motor forces. As a result, we are able to recover physically plausible motion of human subjects from monocular and multiview video. We show, both quantitatively and qualitatively, that our approach performs favorably with respect to Bayesian filtering methods with standard motion priors.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Article-2 ObjectType-Feature-1 content type line 23
ISSN:	0162-8828 1939-3539 2160-9292 1939-3539
DOI:	10.1109/TPAMI.2012.61