Computational studies of human motion: part 1, tracking and motion synthesis
Foundations and Trends® in Computer Graphics and Vision
Pose estimation and tracking using multivariate regression
Pattern Recognition Letters
Animating animal motion from still
ACM SIGGRAPH Asia 2008 papers
Monocular 3D tracking of articulated human motion in silhouette and pose manifolds
Journal on Image and Video Processing - Anthropocentric Video Analysis: Tools and Applications
Fast nonparametric belief propagation for real-time stereo articulated body tracking
Computer Vision and Image Understanding
Learning Generative Models for Multi-Activity Body Pose Estimation
International Journal of Computer Vision
Action recognition feedback-based framework for human pose reconstruction from monocular images
Pattern Recognition Letters
Learning 3-D object orientation from images
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Learning generative models for monocular body pose estimation
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Real-time and marker-free 3D motion capture for home entertainment oriented applications
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Multi-activity tracking in LLE body pose space
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Real-time and markerless 3D human motion capture using multiple views
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Latent gaussian mixture regression for human pose estimation
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
Multiview human pose estimation with unconstrained motions
Pattern Recognition Letters
A new approach for body pose recovery
Proceedings of the 10th International Conference on Virtual Reality Continuum and Its Applications in Industry
Monocular tracking with a mixture of view-dependent learned models
AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects
A local basis representation for estimating human pose from cluttered images
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Multivariate relevance vector machines for tracking
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Graph based semi-supervised human pose estimation: When the output space comes to help
Pattern Recognition Letters
No bias left behind: covariate shift adaptation for discriminative 3d pose estimation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Discriminative fusion of shape and appearance features for human pose estimation
Pattern Recognition
Generative tracking of 3D human motion in latent space by sequential clonal selection algorithm
Multimedia Tools and Applications
| Hi-index | 0.00 |
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.