Model-based detection and tracking of vehicle using a scanning laser rangefinder: A particle filtering approach

Abstract

A method derived from the Sequential Monte Carlo approaches is proposed here to solve the vehicle detection and tracking problem using a scanning laser rangefinder. The originality of this approach lies in a joint detection and tracking of the objects that avoid the usual pre-detection stage. The proposed modeling is strongly nonlinear. To improve the efficiency of the solution, we use a Rao-Blackwell particle filter: the non-linearity of the state-space equations is taken into account by a particle filter and the linearity is optimally processed by a Kalman filter. The solution of the proposed modeling is based on a matched filter (to the object) which uses a predefined vehicle model. A central point here is to calculate the weights of the matched particle filter according to the vehicle model. The efficiency of the method is shown in terms of estimation accuracies and detection.