Centralized data fusion for obstacle and road borders tracking in a collision warning system

Abstract

The proposed system, so-called EUCLIDE, is a collision warning and vision enhancement system merging the functionality of a far infrared and mmw radar sensor in order to warn the driver in case of lack of obstacle perception in adverse weather conditions. A centralized fusion scheme is adopted for obstacle and road tracking. A Kalman based curvelinear model predicts drivers' behaviour