Switching observation models for contour tracking in clutter

Authors:
Ying Wu;Gang Hua;Ting Yu
Affiliations:
Department of Electrical & Computer Engineering, Northwestern University, Evanston, IL;Department of Electrical & Computer Engineering, Northwestern University, Evanston, IL;Department of Electrical & Computer Engineering, Northwestern University, Evanston, IL
Venue:
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Year:
2003

Citing 9
Cited 12

Tracking and data association

Tracking and data association
On sequential Monte Carlo sampling methods for Bayesian filtering

Statistics and Computing
Contour Tracking by Stochastic Propagation of Conditional Density

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Statistical Foreground Modelling for Object Localisation

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
A Probabilistic Background Model for Tracking

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
A Dynamic Bayesian Network Approach to Tracking Using Learned Switching Dynamic Models

HSCC '00 Proceedings of the Third International Workshop on Hybrid Systems: Computation and Control
Object Localization by Bayesian Correlation

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
A Probabilistic Contour Discriminant for Object Localisation

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

Variational Maximum A Posteriori by Annealed Mean Field Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Analyzing and Capturing Articulated Hand Motion in Image Sequences

IEEE Transactions on Pattern Analysis and Machine Intelligence
Sequential mean field variational analysis of structured deformable shapes

Computer Vision and Image Understanding
Contour graph based human tracking and action sequence recognition

Pattern Recognition
Visual-model-based, real-time 3D pose tracking for autonomous navigation: methodology and experiments

Autonomous Robots
Accurate appearance-based Bayesian tracking for maneuvering targets

Computer Vision and Image Understanding
Sequential mean field variational analysis of structured deformable shapes

Computer Vision and Image Understanding
Switching Hidden Markov Models for Learning of Motion Patterns in Videos

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
A video-based indoor occupant detection and localization algorithm for smart buildings

ICIC'09 Proceedings of the 5th international conference on Emerging intelligent computing technology and applications
Integrated region matching approach for tracking target objects in video sequences using HSV colour space

International Journal of Computational Vision and Robotics
Exemplar-Based human contour tracking

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
A hierarchical dynamic bayesian network approach to visual tracking

PCM'04 Proceedings of the 5th Pacific Rim Conference on Advances in Multimedia Information Processing - Volume Part II

Quantified Score

Hi-index	0.01

Visualization

Abstract

We propose a generative model approach to contour tracking against non-stationary clutter and to coping with occlusions by explicit modelling and inferring. The proposed dynamic Bayesian networks consist of multiple hidden processes which model the target, the clutter and the occlusions. The image observation models, which depict the generation of the image features, are conditioned on all the hidden processes. Based on this framework, the tracker can automatically switch among different observation models according to the hidden states of the clutter and occlusions. In addition, the inference of these hidden states provides self-evaluations for the tracker. The tracking and inferencing are implemented based on sequence Monte Carlo techniques. The effectiveness of the proposed approach to robust tracking and inferring non-stationary clutter and occlusion is demonstrated for a variety of image sequences.