Estimating Human Pose with Flowing Puppets

Abstract : We address the problem of upper-body human pose estimation in uncontrolled monocular video sequences, without manual initialization. Most current methods focus on isolated video frames and often fail to correctly localize arms and hands. Inferring pose over a video sequence is advantageous because poses of people in adjacent frames exhibit properties of smooth variation due to the nature of human and camera motion. To exploit this, previous methods have used prior knowledge about distinctive actions or generic temporal priors combined with static image likelihoods to track people in motion. Here we take a different approach based on a simple observation: Information about how a person moves from frame to frame is present in the optical flow field. We develop an approach for tracking articulated motions that "links" articulated shape models of people in adjacent frames through the dense optical flow. Key to this approach is a 2D shape model of the body that we use to compute how the body moves over time. The resulting "flowing puppets" provide a way of integrating image evidence across frames to improve pose inference. We apply our method on a challenging dataset of TV video sequences and show state-of-the-art performance.
Type de document :
Communication dans un congrès
ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. IEEE, pp.3312-3319, 2013, 〈10.1109/ICCV.2013.411〉
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00906800
Contributeur : Thoth Team <>
Soumis le : mercredi 20 novembre 2013 - 13:04:39
Dernière modification le : dimanche 26 août 2018 - 17:30:01
Document(s) archivé(s) le : vendredi 21 février 2014 - 04:28:43

Fichiers

ZuffiICCV2013.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Silvia Zuffi, Javier Romero, Cordelia Schmid, Michael J. Black. Estimating Human Pose with Flowing Puppets. ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. IEEE, pp.3312-3319, 2013, 〈10.1109/ICCV.2013.411〉. 〈hal-00906800〉

Partager

Métriques

Consultations de la notice

843

Téléchargements de fichiers

627