Clustering of high resolution automotive radar detections and subsequent feature extraction for classification of road users

After successful entry into the automotive market some years ago radar sensor technology conquers more and more complex fields of automotive applications like Lane Change Assist or Automatic Emergency Braking systems. Future sensor generations will be challenged by constantly demanding resolution requirements not only requested by consumer rating organizations, but also by very demanding needs to realize automated driving tasks. Facing these novel challenges results in perpetual increasing of resolution requirements to guarantee highly detailed and accurate information of the surrounding area of the vehicle. Due to the high resolution operation mode a plenitude of scattering points reflected by each physical object will flood the detection list. This paper copes with the clustering of all these reflections into appropriate groups in order to exploit the advantages of multidimensional object size estimation and object classification.