Multitarget Tracking Using Orientation Estimation for Optical Belt Sorting

In optical belt sorting, accurate predictions of the bulk material particles' motions are required for high-quality results. By implementing a multitarget tracker tailored to the scenario and deriving novel motion models, the predictions are greatly enhanced. The tracker's reliability is improved by also considering the particles' orientations. To this end, new estimators for directional quantities based on orthogonal basis functions are presented and shown to outperform the state of the art.