Lab
Institute of Microwaves and Photonics (LHFT)
Institution: Friedrich-Alexander-University of Erlangen-Nürnberg
Featured research (4)
The radar-based analysis of human motion is actively being researched due to its contact- and markerless nature and ability to measure motion directly via the Doppler effect. Especially in medical and biomechanical fields, precise movement analysis is crucial. However, existing radar-based studies typically exhibit low lateral resolution, focusing on velocity evaluations and the tracking of scattering centers resolvable in the range or Doppler domains. In this work, we present a novel concept that enables a pixel-wise velocity analysis of human motion in radar near-field imaging scenarios. For this, we utilize the well-established back-projection technique to reconstruct consecutive radar images and perform a subsequent pixel-wise phase comparison. To accurately capture pixel-specific velocities along the depth dimension, this is followed by corrections of near-field geometry distortions accounting for aperture properties and pixel positions. Our theoretical derivations are supported by comprehensive point target simulations. To assess the performance of the proposed approach, we conducted a proof-of-concept study. We tracked a hand surface's movement while performing a finger tapping motion and compared the fingertip position and velocity determined by the radar with the respective values obtained from an optical marker-based system. The results showed a velocity measurement accuracy of
$8.1 \,\mathrm{mms}^{-1}$
and a tracking accuracy of
$1.4 \,\mathrm{m}\mathrm{m}$
, demonstrating the great potential of our approach. The high angular resolution of the velocity measurement enables the tracking of the entire illuminated body shell, extending the range of future applications of radar-based motion analysis.
Contactless hand pose estimation requires sensors that provide precise spatial information and low computational complexity for real-time processing. Unlike vision-based systems, radar offers lighting independence and direct motion assessments. Yet, there is limited research balancing real-time constraints, suitable frame rates for motion evaluations, and the need for precise 3D data. To address this, we extend the ultra-efficient two-tone hand imaging method from our prior work to a three-tone approach. Maintaining high frame rates and real-time constraints, this approach significantly enhances reconstruction accuracy and precision. We assess these measures by evaluating reconstruction results for different hand poses obtained by an imaging radar. Accuracy is assessed against ground truth from a spatially calibrated photogrammetry setup, while precision is measured using 3D-printed hand poses. The results emphasize the method's great potential for future radar-based hand sensing.
Radio detection and ranging-based (radar) sensing offers unique opportunities for biomedical monitoring and can help overcome the limitations of currently established solutions. Due to its contactless and unobtrusive measurement principle, it can facilitate the longitudinal recording of human physiology and can help to bridge the gap from laboratory to real-world assessments. However, radar sensors typically yield complex and multidimensional data that are hard to interpret without domain expertise. Machine learning (ML) algorithms can be trained to extract meaningful information from radar data for medical experts, enhancing not only diagnostic capabilities but also contributing to advancements in disease prevention and treatment. However, until now, the two aspects of radar-based data acquisition and ML-based data processing have mostly been addressed individually and not as part of a holistic and end-to-end data analysis pipeline. For this reason, we present a tutorial on radar-based ML applications for biomedical monitoring that equally emphasizes both dimensions. We highlight the fundamentals of radar and ML theory, data acquisition and representation and outline categories of clinical relevance. Since the contactless and unobtrusive nature of radar-based sensing also raises novel ethical concerns regarding biomedical monitoring, we additionally present a discussion that carefully addresses the ethical aspects of this novel technology, particularly regarding data privacy, ownership, and potential biases in ML algorithms.
Lab head
Department
- Institute of Microwaves and Photonics
About Martin Vossiek
- Martin Vossiek currently works at the Institute of Microwaves and Photonics (LHFT), Friedrich-Alexander-University of Erlangen-Nürnberg (FAU). Martin does in radar, transponder, RF identification, communication, and locating systems.
Members (21)
G. Gold
G. Gold
K. Lomakin
Christian Carlowitz
Ingrid Ullmann
K. Helmreich
Konstantin Root
Tatiana Pavlenko