Recovering 3D human pose from monocular images - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2006

Recovering 3D human pose from monocular images

Ankur Agarwal
  • Fonction : Auteur
  • PersonId : 844845
Bill Triggs

Résumé

We describe a learning-based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor prior labeling of body parts in the image. Instead, it recovers pose by direct nonlinear regression against shape descriptor vectors extracted automatically from image silhouettes. For robustness against local silhouette segmentation errors, silhouette shape is encoded by histogram-of-shape-contexts descriptors. We evaluate several different regression methods: ridge regression, relevance vector machine (RVM) regression, and support vector machine (SVM) regression over both linear and kernel bases. The RVMs provide much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. The loss of depth and limb labeling information often makes the recovery of 3D pose from single silhouettes ambiguous. To handle this, the method is embedded in a novel regressive tracking framework, using dynamics from the previous state estimate together with a learned regression value to disambiguate the pose. We show that the resulting system tracks long sequences stably. For realism and good generalization over a wide range of viewpoints, we train the regressors on images resynthesized from real human motion capture data. The method is demonstrated for several representations of full body pose, both quantitatively on independent but similar test data and qualitatively on real image sequences. Mean angular errors of 4-6° are obtained for a variety of walking motions.
Fichier principal
Vignette du fichier
Agarwal-pami05.pdf (12.2 Mo) Télécharger le fichier
Vignette du fichier
silscpca.jpg (12.03 Ko) Télécharger le fichier
backgroundsub.mpeg (1.33 Mo) Télécharger le fichier
icmldemo1.mpeg (2.4 Mo) Télécharger le fichier
mansilboy.mpeg (1.7 Mo) Télécharger le fichier
silscpca.mpeg (980.76 Ko) Télécharger le fichier
videopami.mpeg (661.21 Ko) Télécharger le fichier
videosyn.mpeg (668.39 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Format : Figure, Image
Format : Autre
Format : Autre
Format : Autre
Format : Autre
Format : Autre
Format : Autre
Loading...

Dates et versions

inria-00548619 , version 1 (20-12-2010)

Identifiants

Citer

Ankur Agarwal, Bill Triggs. Recovering 3D human pose from monocular images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28 (1), pp.44--58. ⟨10.1109/TPAMI.2006.21⟩. ⟨inria-00548619⟩
487 Consultations
1153 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More