Guard rail detection using radar and vision data fusion for vehicle detection algorithm improvement and speed-up

Abstract

This paper describes a method for detecting guard rails fusing radar and vision data in order to improve and speed-up vehicle detection algorithms. The method is based on the search for uninterrupted oblique lines that cross an interest area. The interest area is dynamically indicated by a radar sensor. A method to manage overlapping areas is also described. The method's efficiency, both in terms of time saving and correct detection rate, is numerically shown.