Modeling the target extent with multiplicative noise

Extended target tracking deals with simultaneously tracking the shape and the kinematic parameters of a target. In this work, we formulate the extended target tracking problem as a state estimation problem with both multiplicative and additive measurement noise. In case of extended targets with known orientation, we show that the best linear estimator is not consistent and, hence, is unsuitable for this problem. In order to overcome this issue, we propose a quadratic estimator for a recursive closed-form measurement update. Simulations demonstrate the performance of the estimator.