Occlusion detection and tracking method based on bayesian decision theory

Authors:
Yan Zhou;Bo Hu;Jianqiu Zhang
Affiliations:
Department of Electronic Engineering, Fudan University, Shanghai;Department of Electronic Engineering, Fudan University, Shanghai;Department of Electronic Engineering, Fudan University, Shanghai
Venue:
PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology
Year:
2006

Citing 5
Cited 2

On sequential Monte Carlo sampling methods for Bayesian filtering

Statistics and Computing
Mean Shift, Mode Seeking, and Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking

IEEE Transactions on Signal Processing
A survey on visual surveillance of object motion and behaviors

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Visual tracking and recognition using appearance-adaptive models in particle filters

IEEE Transactions on Image Processing

Occlusion detection and recovery in video object tracking based on adaptive particle filters

CCDC'09 Proceedings of the 21st annual international conference on Chinese Control and Decision Conference
Invariants for homology classes with application to optimal search and planning problem in robotics

Annals of Mathematics and Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In order to track an occluded target in an image sequence, the Bayesian decision theory is, here, introduced to the problem of distinguishing occlusions and appearance changes according to their different risk possibilities. A new target template combining image intensity and histogram is designed. The corresponding updating method is also derived based on particle filter. If the target is totally occluded by another target, the template can be kept unchanged. The occlusion of a target will not influence tracking. Simulation results show that the presented method can efficiently justify whether the occlusion occurs and realize target tracking in image sequences even though the tracked target is totally occluded with long time.