Pedestrian Classification for 79 GHz Automotive Radar Systems
Prophet R, Hoffmann M, Ossowska A, Malik W, Sturm C, Vossiek M (2018)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2018
Publisher: IEEE
Event location: Chang Shu
Abstract
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.
Authors with CRIS profile
Robert Prophet
Lehrstuhl für Hochfrequenztechnik
Marcel Hoffmann
Lehrstuhl für Hochfrequenztechnik
Martin Vossiek
Lehrstuhl für Hochfrequenztechnik
Involved external institutions
Germany (DE)How to cite
APA:
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.
MLA:
Prophet, Robert, et al. "Pedestrian Classification for 79 GHz Automotive Radar Systems." Proceedings of the 29th IEEE Intelligent Vehicles Symposium, Chang Shu IEEE, 2018.
BibTeX: Download