Stochastic Tracking of 3D Human Figures Using 2D Image Motion
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Laplacian Eigenmaps for dimensionality reduction and data representation
Neural Computation
Generative modeling for continuous non-linearly embedded visual inference
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Style-based inverse kinematics
ACM SIGGRAPH 2004 Papers
Physics-based Animation (Graphics Series)
Physics-based Animation (Graphics Series)
Priors for People Tracking from Small Training Sets
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
3D People Tracking with Gaussian Process Dynamical Models
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Vision-based human motion analysis: An overview
Computer Vision and Image Understanding
Gaussian Process Dynamical Models for Human Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Physics-Based Person Tracking Using the Anthropomorphic Walker
International Journal of Computer Vision
Probabilistic fiber tracking using particle filtering and von Mises-Fisher sampling
EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Gaussian-like spatial priors for articulated tracking
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Stick it articulated tracking using spatial rigid object priors
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
Predicting Articulated Human Motion from Spatial Processes
International Journal of Computer Vision
Conditional-mean estimation via jump-diffusion processes inmultiple target tracking/recognition
IEEE Transactions on Signal Processing
Spatial measures between human poses for classification and understanding
AMDO'12 Proceedings of the 7th international conference on Articulated Motion and Deformable Objects
Unscented Kalman Filtering on Riemannian Manifolds
Journal of Mathematical Imaging and Vision
Hi-index | 0.00 |
In articulated tracking, one is concerned with estimating the pose of a person in every frame of a film. This pose is most often represented as a kinematic skeleton where the joint angles are the degrees of freedom. Least-committed predictive models are then phrased as a Brownian motion in joint angle space. However, the metric of the joint angle space is rather unintuitive as it ignores both bone lengths and how bones are connected. As Brownian motion is strongly linked with the underlying metric, this has severe impact on the predictive models. We introduce the spatial kinematic manifold of joint positions, which is embedded in a high dimensional Euclidean space. This Riemannian manifold inherits the metric from the embedding space, such that distances are measured as the combined physical length that joints travel during movements. We then develop a least-committed Brownian motion model on the manifold that respects the natural metric. This model is expressed in terms of a stochastic differential equation, which we solve using a novel numerical scheme. Empirically, we validate the new model in a particle filter based articulated tracking system. Here, we not only outperform the standard Brownian motion in joint angle space, we are also able to specialise the model in ways that otherwise are both difficult and expensive in joint angle space.