A new Approach for Pedestrian Detection in Vehicles by Ultrasonic Signal Analysis

This paper introduces a new approach for pedestrian detection by means of a sophisticated analysis of ultrasonic signals. The main objective is to enable driver assistance systems in vehicles to recognize whether an obstacle in front is a pedestrian or a car. In case of a likely collision the sensor allows to activate pedestrian protection systems in an early stage. The sensor evaluates ultrasonic signals backscattered from the obstacle by task specific signal analysis methods. It consists of an ultrasonic transducer, an embedded system for transducer control and signal acquisition as well as a computer for signal analysis and feature extraction. Unlike Radar systems this pedestrian detection approach is also able to detect non-moving persons and even children.