This article proposes a perception scheme in the field of intelligent vehicles. The method exploits prior map knowledge and makes use of evidential grids constructed from the sensor data. Evidential grids are based on the occupancy grids and the formalism of the Dempster-Shafer theory. Prior knowledge is obtained from a geographic map which is considered as an additional source of information and combined with a grid representing sensor data. Since the vehicle environment is dynamic, stationary and mobile objects has to be distinguished. In order to achieve this objective, the evidential conflict information is used for mobile cell detection. As well, an accumulator is introduced and used as a factor for mass function specialisation in order to detect static cells. Different pieces of information become obsolete at different rates. To take this fact into account, contextual discounting is employed to control the cell remanence. Experiments carried out real-world data recorded in urban conditions illustrate the benefits of the presented approach.