A Realistic Radar Ray Tracing Simulator for Hand Pose Imaging

Bräunig J, Schüßler C, Wirth V, Stamminger M, Ullmann I, Vossiek M (2023)


Publication Language: English

Publication Type: Conference contribution

Publication year: 2023

Event location: Berlin

Abstract

With the increasing popularity of human-computer interaction applications, there is also growing
interest in generating sufficiently large and diverse data sets for automatic radar-based recognition of hand poses and gestures.
Radar simulations are a vital approach to generating training data (e.g., for machine learning). Therefore, this work applies  a ray tracing method to radar imaging of the hand. The performance of the proposed simulation approach is verified by a comparison of simulation and measurement data based on
an imaging radar with a high lateral resolution. In addition, the surface material model incorporated into the ray tracer is highlighted in more detail and parameterized for radar hand imaging. Measurements and simulations show a very high similarity between synthetic and real radar image captures. The
presented results demonstrate that it is possible to generate very realistic simulations of radar measurement data even for complex radar hand pose imaging systems.


Authors with CRIS profile

Additional Organisation(s)

Related research project(s)

How to cite

APA:

Bräunig, J., Schüßler, C., Wirth, V., Stamminger, M., Ullmann, I., & Vossiek, M. (2023). A Realistic Radar Ray Tracing Simulator for Hand Pose Imaging. In Proceedings of the EuRAD 2023. Berlin.

MLA:

Bräunig, Johanna, et al. "A Realistic Radar Ray Tracing Simulator for Hand Pose Imaging." Proceedings of the EuRAD 2023, Berlin 2023.

BibTeX: Download