A localization system that exploits L1-GPS estimates, vehicle data, and features from a video camera as well as lane markings embedded in digital navigation maps is presented. A sensitivity analysis of the detected lane markings is proposed in order to quantify both the lateral and longitudinal errors caused by 2D-world hypothesis violation. From this, a camera observation model for vehicle localization is proposed. The paper presents also a method to build a map of the lane markings in a first stage. The solver is based on dynamical Kalman filtering with a two-stage map-matching process which is described in details. This is a software-based solution using existing automotive components. Experimental results in urban conditions demonstrate an significant increase in the positioning quality.