Pedestrian Classification for 79 GHz Automotive Radar Systems

Conference contribution
(Conference Contribution)

Publication Details

Author(s): Prophet R, Hoffmann M, Ossowska A, Malik W, Sturm C, Vossiek M
Publisher: IEEE
Publication year: 2018
Language: English


Radar sensors have become an integral part of advanced driver assistance
systems. Merely detecting targets will not, however, advance their
contribution. Rather, an object classification capability is required to
distinguish vulnerable road users from other objects, such as vehicles.
To achieve this, targets that are determined from the
range-Doppler-Matrix created by a 79 GHz chirp sequence radar are
clustered to objects. Different classifiers then use previously
calculated characteristic features of moving objects to generate the
object classes “Pedestrian” and “Other”. As a result, the success rate
of one measurement reaches up to 95.3% for well-suited classifiers and a
bandwidth of 1.6 GHz. Moreover, the robustness of the classification
process is increased by tracking the objects. The proposed algorithm for
pedestrian classification is not only faster than conventional
approaches using micro-Doppler signatures, but also requires less
computational effort. Implemented in vehicles, this can be a major
contribution to protect vulnerable road users such as pedestrians.

FAU Authors / FAU Editors

Hoffmann, Marcel
Lehrstuhl für Hochfrequenztechnik
Prophet, Robert
Lehrstuhl für Hochfrequenztechnik
Vossiek, Martin Prof. Dr.-Ing.
Lehrstuhl für Hochfrequenztechnik

External institutions with authors

Valeo Schalter und Sensoren GmbH

How to cite

Prophet, R., Hoffmann, M., Ossowska, A., Malik, W., Sturm, C., & Vossiek, M. (2018). Pedestrian Classification for 79 GHz Automotive Radar Systems. In Proceedings of the 29th IEEE Intelligent Vehicles Symposium. Chang Shu, CN: IEEE.

Prophet, Robert, et al. "Pedestrian Classification for 79 GHz Automotive Radar Systems." Proceedings of the 29th IEEE Intelligent Vehicles Symposium, Chang Shu IEEE, 2018.


Last updated on 2019-16-04 at 22:23