Occluded object tracking based on Bayesian Decision theory and particle filtering

In this paper, we propose an algorithm based on Bayesian Decision theory and Particle Filtering, here, the appearance change and occlusion are distinguished by a Bayesian discriminating function. The particles´ spatial uncertainty is applied to measure the tracking accuracy, which is used to update the object template. 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.