Extended Object Tracking Based on Set-Theoretic and Stochastic Fusion

摘要

A novel approach for extended object tracking is presented. In contrast to existing approaches, no statistical assumptions about the location of the measurement sources on the extended target object are made. As a consequence, a combined set-theoretic and stochastic estimator is obtained that is robust to systematic errors in the target model. The benefits of the new approach is demonstrated by means of simulations.