Simultaneous Estimation of Pose and Motion at Highly Dynamic Turn Maneuvers

The (Extended) Kalman filter has been established as a standard method for object tracking. While a constraining motion model stabilizes the tracking results given noisy measurements, it limits the ability to follow an object in non-modeled maneuvers. In the context of a stereo-vision based vehicle tracking approach, we propose and compare three different strategies to automatically adapt the dynamics of the filter to the dynamics of the object. These strategies include an IMM-based multi-filter setup, an extension of the motion model considering higher order terms, as well as the adaptive parametrization of the filter variances using an independent maximum likelihood estimator. For evaluation, various recorded real world trajectories and simulated maneuvers, including skidding, are used. The experimental results show significant improvements in the simultaneous estimation of pose and motion.