A Bayesian Solution to Track Multiple and Dynamic Objects Robustly from Visual Data

Different solutions have been proposed for multiple objects tracking based on probabilistic algorithms. In this paper, the authors propose the use of an only particle filter to track a variable number of objects. The estimator robustness and adaptability are increased by the use of a clustering algorithm. Measurements used in the tracking process are extracted from a stereovision system, and thus, the 3D position of the tracked objects is obtained at each time step. Tracking results are presented at the end of the paper