Global Positioning Systems (GPS) provide detailed information on the location of an object on the Earth's surface. Among the information they provide are the latitude and longitude coordinates, the time in which it was taken, the direction to which it was traveling, the speed and other parameters. This information is analyzed and stored to support decision making in various sectors. At present, the number of devices equipped with receivers for these systems is increasing considerably as well as the amount of information, which makes the data analysis process difficult and demands greater storage needs. In order to reduce the amount of data to be stored, a set of algorithms for GPS data simplification, that carry out the spatial-temporal analysis of the data are proposed; however, the nature of the data is not taken into account. In the present investigation a comparison of different algorithms for GPS data simplification is carried, taking into account the noisy nature of the same ones. In order to reduce the noise present in vehicular trajectories, the Kalman filter is selected because it predicts the next state starting from the previous state, taking into account the dynamics of movement of objects. As a result, a comparison is obtained among some of the algorithms for vehicular GPS trajectories simplification that constitute the base of the formulation of more complex algorithms before carrying out the filtering and after the data filtering is carried out.