Tracking 3D Human Pose with Large Root Node Uncertainty

Ben Daubney*, Xianghua Xie

*Awdur cyfatebol y gwaith hwn

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion CynhadleddCyfraniad i gynhadleddadolygiad gan gymheiriaid


Representing articulated objects as a graphical model has gained much popularity in recent years, often the root node of the graph describes the global position and orientation of the object. In this work a method is presented to robustly track 3D human pose by permitting greater uncertainty to be modeled over the root node than existing techniques allow. Significantly, this is achieved without increasing the uncertainty of remaining parts of the model. The benefit is that a greater volume of the posterior can be supported making the approach less vulnerable to tracking failure. Given a hypothesis of the root node state a novel method is presented to estimate the posterior over the remaining parts of the body conditioned on this value. All probability distributions are approximated using a single Gaussian allowing inference to be carried out in closed form. A set of deterministically selected sample points are used that allow the posterior to be updated for each part requiring just seven image likelihood evaluations making it extremely efficient. Multiple root node states are supported and propagated using standard sampling techniques. We believe this to be the first work devoted to efficient tracking of human pose whilst modeling large uncertainty in the root node and demonstrate the presented method to be more robust to tracking failures than existing approaches.

Iaith wreiddiolSaesneg
Teitl2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
CyhoeddwrInstitute of Electrical and Electronics Engineers
Nifer y tudalennau8
ISBN (Electronig)978-1-4577-0395-9
ISBN (Argraffiad)978-1-4577-0394-2
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 2011
Cyhoeddwyd yn allanolIe
DigwyddiadIEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Colorado Springs, Colombia
Hyd: 20 Meh 201125 Meh 2011

Cyfres gyhoeddiadau

EnwIEEE Conference on Computer Vision and Pattern Recognition
ISSN (Argraffiad)1063-6919


CynhadleddIEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DinasColorado Springs

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'Tracking 3D Human Pose with Large Root Node Uncertainty'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn