Monocular Human Motion Capture with a Mixture of Regressors - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2005

Monocular Human Motion Capture with a Mixture of Regressors

Ankur Agarwal
  • Function : Author
  • PersonId : 844845
Bill Triggs


We address 3D human motion capture from monocular images, taking a learning based approach to construct a probabilistic pose estimation model from a set of labelled human silhouettes. To compensate for ambiguities in the pose reconstruction problem, our model explicitly calculates several possible pose hypotheses. It uses locality on a manifold in the input space and connectivity in the output space to identify regions of multi-valuedness in the mapping from silhouette to 3D pose. This information is used to fit a mixture of regressors on the input manifold, giving us a global model capable of predicting the possible poses with corresponding probabilities. These are then used in a dynamicalmodel based tracker that automatically detects tracking failures and re-initializes in a probabilistically correct manner. The system is trained on conventional motion capture data, using both the corresponding real human silhouettes and silhouettes synthesized artificially from several different models for improved robustness to inter-person variations. Static pose estimation is illustrated on a variety of silhouettes. The robustness of the method is demonstrated by tracking on a real image sequence requiring multiple automatic re-initializations.
Vignette du fichier
0001.png (30.56 Ko) Télécharger le fichier Fichier principal
Vignette du fichier
Agarwal_v4hci05.pdf (1.22 Mo) Télécharger le fichier
Agarwal_v4hci05-poster.pdf (1.56 Mo) Télécharger le fichier
Agarwal_v4hci05-talk.pdf (898.88 Ko) Télécharger le fichier
auto_init.mpeg (5.65 Mo) Télécharger le fichier
upper_body.mpeg (7.39 Mo) Télécharger le fichier
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Other
Format : Other
Format : Other
Format : Other

Dates and versions

inria-00548522 , version 1 (20-12-2010)



Ankur Agarwal, Bill Triggs. Monocular Human Motion Capture with a Mixture of Regressors. IEEE Workshop on Vision for Human Computer Interaction at Computer Vision and Pattern Recognition (CVPR '05), Jun 2005, San Diego, United States. pp.72, ⟨10.1109/CVPR.2005.496⟩. ⟨inria-00548522⟩
163 View
635 Download



Gmail Facebook Twitter LinkedIn More