Object classification exploiting high level maps of intersections

Abstract

An object classification system is introduced. The system observes the vehicle's environment with a laser scanner. Preprocessing and object tracking algorithms are applied. The object classification combines a pattern classifier with rule based a priori knowledge and high level map information. The pattern classifier uses significant features to calculate membership values for each class. These membership values are verified and corrected by a priori knowledge. Furthermore, a precise position of the test vehicle is estimated. The positions of observed objects in the high level map can be determined exploiting this information. As the object position is restricted for some object classes, this knowledge can be used in the classification, which significantly improves its performance. Finally, the system is evaluated with labeled test data of several sequences at different intersections.