Contour Tracking by Stochastic Propagation of Conditional Density
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
A General Framework for Combining Visual Trackers --- The "Black Boxes" Approach
International Journal of Computer Vision
A probabilistic framework for combining tracking algorithms
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
| Hi-index | 0.00 |
This paper presents a novel representation of information within tracking applications, called the Spatial Probability Density Function (PDF) representation. This representation allows a level of uncertainty (or confidence) in target position to be expressed and maintained throughout the tracking process. Target position, velocity and acceleration are sampled at pixel resolutions and are propagated using a Bayesian statistical framework. An example application of the PDF representation is presented in an analogue of the classical alpha beta tracker. The results are promising, with key benefits being robust tracking in the presence of noise, occlusion and clutter. Directions for further research are discussed.