Real-Time 3D Body Pose Tracking from Multiple 2D Images
AMDO '08 Proceedings of the 5th international conference on Articulated Motion and Deformable Objects
2D Articulated Body Tracking with Self-occultations Handling
AMDO '08 Proceedings of the 5th international conference on Articulated Motion and Deformable Objects
Fast nonparametric belief propagation for real-time stereo articulated body tracking
Computer Vision and Image Understanding
Recognizing events with temporal random forests
Proceedings of the 2009 international conference on Multimodal interfaces
Recognizing Gestures for Virtual and Real World Interaction
ICVS '09 Proceedings of the 7th International Conference on Computer Vision Systems: Computer Vision Systems
Constrained optimization for human pose estimation from depth sequences
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Tracking human pose with multiple activity models
Pattern Recognition
Kinematic self retargeting: A framework for human pose estimation
Computer Vision and Image Understanding
Bayesian 3d human body pose tracking from depth image sequences
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Hi-index | 0.00 |
Classic methods for Bayesian inference effectively constrain search to lie within regions of significant probability of the temporal prior. This is efficient with an accurate dynamics model, but otherwise is prone to ignore significant peaks in the true posterior. A more accurate posterior estimate can be obtained by explicitly finding modes of the likelihood function and combining them with a weak temporal prior. In our approach modes are found using effi- cient example-based matching followed by local refinement to find peaks and estimate peak bandwidth. By reweighting these peaks according to the temporal prior we obtain an estimate of the full posterior model. We show comparative results on real and synthetic images in a high degree of freedom articulated tracking task.