CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
On sequential Monte Carlo sampling methods for Bayesian filtering
Statistics and Computing
A Mixed-State Condensation Tracker with Automatic Model-Switching
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Inferring 3D Structure with a Statistical Image-Based Shape Model
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Generative modeling for continuous non-linearly embedded visual inference
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Discriminative Density Propagation for 3D Human Motion Estimation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Monocular Human Motion Capture with a Mixture of Regressors
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Dynamic Appearance Modeling for Human Tracking
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
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
Transformation invariant component analysis for binary images
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Computational studies of human motion: part 1, tracking and motion synthesis
Foundations and Trends® in Computer Graphics and Vision
Inferring 3D body pose from silhouettes using activity manifold learning
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
3D human pose from silhouettes by relevance vector regression
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Monocular tracking with a mixture of view-dependent learned models
AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects
An efficient euclidean distance transform
IWCIA'04 Proceedings of the 10th international conference on Combinatorial Image Analysis
Multivariate relevance vector machines for tracking
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Monocular tracking of 3d human motion with a coordinated mixture of factor analyzers
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Factor graphs and the sum-product algorithm
IEEE Transactions on Information Theory
Exploiting motion correlations in 3-D articulated human motion tracking
IEEE Transactions on Image Processing
Dual gait generative models for human motion estimation from a single camera
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on gait analysis
Model-based hand gesture tracking in ToF image sequences
AMDO'10 Proceedings of the 6th international conference on Articulated motion and deformable objects
Multiple view human articulated tracking using charting and particle swarm optimisation
Proceedings of the 1st international workshop on 3D video processing
Simultaneous particle tracking in multi-action motion models with synthesized paths
Image and Vision Computing
Charting-based subspace learning for video-based human action classification
Machine Vision and Applications
| Hi-index | 0.00 |
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a low-dimensional embedding of the pose manifolds using Locally Linear Embedding (LLE), as well as the statistical relationship between body poses and their image appearance. In addition, the dynamics in these pose manifolds are modelled. Sparse kernel regressors capture the nonlinearities of these mappings efficiently. Body poses are inferred by a recursive Bayesian sampling algorithm with an activity-switching mechanism based on learned transfer functions. Using a rough foreground segmentation, we compare Binary PCA and distance transforms to encode the appearance. As a postprocessing step, the globally optimal trajectory through the entire sequence is estimated, yielding a single pose estimate per frame that is consistent throughout the sequence. We evaluate the algorithm on challenging sequences with subjects that are alternating between running and walking movements. Our experiments show how the dynamical model helps to track through poorly segmented low-resolution image sequences where tracking otherwise fails, while at the same time reliably classifying the activity type.