Representation of uncertainty in spatial target tracking

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