Journal cover Journal topic
Advances in Radio Science An open-access journal of the U.R.S.I. Landesausschuss in der Bundesrepublik Deutschland e.V.
Journal topic

Journal metrics

Journal metrics

  • CiteScore value: 0.46 CiteScore
    0.46
  • SNIP value: 0.339 SNIP 0.339
  • SJR value: 0.199 SJR 0.199
  • IPP value: 0.35 IPP 0.35
  • h5-index value: 6 h5-index 6
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 17 Scimago H
    index 17
Volume 10
Adv. Radio Sci., 10, 45-55, 2012
https://doi.org/10.5194/ars-10-45-2012
© Author(s) 2012. This work is distributed under
the Creative Commons Attribution 3.0 License.
Adv. Radio Sci., 10, 45-55, 2012
https://doi.org/10.5194/ars-10-45-2012
© Author(s) 2012. This work is distributed under
the Creative Commons Attribution 3.0 License.

  18 Sep 2012

18 Sep 2012

Pedestrian recognition using automotive radar sensors

A. Bartsch, F. Fitzek, and R. H. Rasshofer A. Bartsch et al.
  • BMW Group Research and Technology, Munich, Germany

Abstract. The application of modern series production automotive radar sensors to pedestrian recognition is an important topic in research on future driver assistance systems. The aim of this paper is to understand the potential and limits of such sensors in pedestrian recognition. This knowledge could be used to develop next generation radar sensors with improved pedestrian recognition capabilities. A new raw radar data signal processing algorithm is proposed that allows deep insights into the object classification process. The impact of raw radar data properties can be directly observed in every layer of the classification system by avoiding machine learning and tracking. This gives information on the limiting factors of raw radar data in terms of classification decision making. To accomplish the very challenging distinction between pedestrians and static objects, five significant and stable object features from the spatial distribution and Doppler information are found. Experimental results with data from a 77 GHz automotive radar sensor show that over 95% of pedestrians can be classified correctly under optimal conditions, which is compareable to modern machine learning systems. The impact of the pedestrian's direction of movement, occlusion, antenna beam elevation angle, linear vehicle movement, and other factors are investigated and discussed. The results show that under real life conditions, radar only based pedestrian recognition is limited due to insufficient Doppler frequency and spatial resolution as well as antenna side lobe effects.

Publications Copernicus
Download
Citation
Share