LIDAR Extended Object Tracking of a Maritime Vessel Using an Ellipsoidal Contour Model
Kristian Amundsen Ruud, Edmund Brekke, Jo Eidsvik · 2018
Extended object tracking (EOT) plays an important role when creating autonomous systems like self-driving cars or surface vehicles. For accurate estimation of the target extent, it is important to have a sensor with high resolution and low measurement noise. In this paper we use the LIDAR sensor to track a single elliptical target in clutter with a contour measurement model. The model enables the use of extended Kalman filter (EKF) which is combined with a generalized probabilistic data association (GPDA) filter. The EKF method comes favorably out of a comparison with a random matrix parametrized EOT approach. The testing is done through simulation studies and on real LIDAR data from a passenger boat.