Model-Based 3D Hand Pose Estimation from Monocular Video

Abstract : A novel model-based approach to 3D hand tracking from monocular video is presented. The 3D hand pose, the hand texture, and the illuminant are dynamically estimated through minimization of an objective function. Derived from an inverse problem formulation, the objective function enables explicit use of temporal texture continuity and shading information while handling important self-occlusions and time-varying illumination. The minimization is done efficiently using a quasi-Newton method, for which we provide a rigorous derivation of the objective function gradient. Particular attention is given to terms related to the change of visibility near self-occlusion boundaries that are neglected in existing formulations. To this end, we introduce new occlusion forces and show that using all gradient terms greatly improves the performance of the method. Qualitative and quantitative experimental results demonstrate the potential of the approach.
Document type :
Journal articles
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00856313
Contributor : Enzo Ferrante <>
Submitted on : Friday, August 30, 2013 - 6:18:07 PM
Last modification on : Thursday, February 7, 2019 - 5:29:20 PM

Links full text

Identifiers

Collections

Citation

Martin de La Gorce, J. Fleet D, Nikos Paragios. Model-Based 3D Hand Pose Estimation from Monocular Video. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2011, 33 (9), pp.1793 - 1805. ⟨10.1109/TPAMI.2011.33⟩. ⟨hal-00856313⟩

Share

Metrics

Record views

5717