Data compression using dynamic Markov modelling
The Computer Journal
Text compression
Elements of information theory
Elements of information theory
The power of amnesia: learning probabilistic automata with variable memory length
Machine Learning - Special issue on COLT '94
CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Learning variable-length Markov models of behavior
Computer Vision and Image Understanding - Modeling people toward vision-based underatanding of a person's shape, appearance, and movement
Unsupervised Learning of Finite Mixture Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Human Body Model Acquisition and Tracking Using Voxel Data
International Journal of Computer Vision
Visual Tracking of High DOF Articulated Structures: an Application to Human Hand Tracking
ECCV '94 Proceedings of the Third European Conference-Volume II on Computer Vision - Volume II
Implicit Probabilistic Models of Human Motion for Synthesis and Tracking
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
A high performance multi-perspective vision studio
ICS '03 Proceedings of the 17th annual international conference on Supercomputing
3-D model-based tracking of humans in action: a multi-view approach
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Learning Structured Behavior Models Using Variable Length Markov Models
MPEOPLE '99 Proceedings of the IEEE International Workshop on Modelling People
Model-based tracking of self-occluding articulated objects
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Design of a linguistic postprocessor using variable memory length Markov models
ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) - Volume 1
Free-viewpoint video of human actors
ACM SIGGRAPH 2003 Papers
Wormholes in Shape Space: Tracking through Discontinuous Changes in Shape
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
A Mixed-State Condensation Tracker with Automatic Model-Switching
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Constraining Human Body Tracking
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Style-based inverse kinematics
ACM SIGGRAPH 2004 Papers
Real-Time Markerless Human Body Tracking Using Colored Voxels and 3-D Blobs
ISMAR '04 Proceedings of the 3rd IEEE/ACM International Symposium on Mixed and Augmented Reality
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Feasibility of the living canvas: restricting projection to a performer on stage
MM '08 Proceedings of the 16th ACM international conference on Multimedia
A survey on vision-based human action recognition
Image and Vision Computing
Markerless human articulated tracking using hierarchical particle swarm optimisation
Image and Vision Computing
Markerless articulated human body tracking from multi-view video with GPU-PSO
ICES'10 Proceedings of the 9th international conference on Evolvable systems: from biology to hardware
Multiview human pose estimation with unconstrained motions
Pattern Recognition Letters
EvoApplicatons'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I
Shape from pairwise silhouettes for plan-view map generation
Image and Vision Computing
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
Real-time pose estimation using constrained dynamics
AMDO'12 Proceedings of the 7th international conference on Articulated Motion and Deformable Objects
Particle Swarm Optimization and Differential Evolution for model-based object detection
Applied Soft Computing
| Hi-index | 0.01 |
In this paper, we introduce a 3-D human-body tracker capable of handling fast and complex motions in real-time. We build upon the Monte-Carlo Bayesian framework, and propose novel prediction and evaluation methods improving the robustness and efficiency of the tracker. The parameter space, augmented with first order derivatives, is automatically partitioned into Gaussian clusters each representing an elementary motion: hypothesis propagation inside each cluster is therefore accurate and efficient. The transitions between clusters use the predictions of a variable length Markov model which can explain high-level behaviours over a long history. Using Monte-Carlo methods, evaluation of model candidates is critical for both speed and robustness. We present a new evaluation scheme based on hierarchical 3-D reconstruction and blob-fitting, where appearance models and image evidences are represented by mixtures of Gaussian blobs. Our tracker is also capable of automatic-initialisation and self-recovery. We demonstrate the application of our tracker to long video sequences exhibiting rapid and diverse movements.