English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor

MPS-Authors
/persons/resource/persons134216

Mueller,  Franziska
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons129023

Mehta,  Dushyant
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons199773

Sotnychenko,  Oleksandr
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons79499

Sridhar,  Srinath
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45610

Theobalt,  Christian       
Computer Graphics, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

arXiv:1704.02201.pdf
(Preprint), 7MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Mueller, F., Mehta, D., Sotnychenko, O., Sridhar, S., Casas, D., & Theobalt, C. (2017). Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor. Retrieved from http://arxiv.org/abs/1704.02201.


Cite as: https://hdl.handle.net/11858/00-001M-0000-002D-8BBD-F
Abstract
We present an approach for real-time, robust and accurate hand pose estimation from moving egocentric RGB-D cameras in cluttered real environments. Existing methods typically fail for hand-object interactions in cluttered scenes imaged from egocentric viewpoints, common for virtual or augmented reality applications. Our approach uses two subsequently applied Convolutional Neural Networks (CNNs) to localize the hand and regress 3D joint locations. Hand localization is achieved by using a CNN to estimate the 2D position of the hand center in the input, even in the presence of clutter and occlusions. The localized hand position, together with the corresponding input depth value, is used to generate a normalized cropped image that is fed into a second CNN to regress relative 3D hand joint locations in real time. For added accuracy, robustness and temporal stability, we refine the pose estimates using a kinematic pose tracking energy. To train the CNNs, we introduce a new photorealistic dataset that uses a merged reality approach to capture and synthesize large amounts of annotated data of natural hand interaction in cluttered scenes. Through quantitative and qualitative evaluation, we show that our method is robust to self-occlusion and occlusions by objects, particularly in moving egocentric perspectives.