A paper presentation at Beyond Radar Waves: The First Workshop on RadarBased HumanComputer Interaction, ACM EICS 2024, Cagliari, Italy.

Authors: Nuwan T. Attygalle, Matjaž Kljun and Klen Čopič Pucihar

Abstract: The development of radarbased humancomputer interaction systems using miniature radaronchip sensors has attracted significant interest. This interest is fuelled by the availability of affordable radar chips and advancements in signal processing and machine learning that improve radar signal interpretation accuracy. However, several challenges remain, particularly when we want to compare different radarbased gesture interaction systems. On dimension to compare different systems can be based on radar signal representations, since raw voltage data can be used to extract these. Different signal representations include among others rangeDoppler, rangeAngle, and point clouds. Existing research often limits comparative testing to the same radar signal representation, focusing mainly on gesture recognition algorithms or minimal variations within digital signal processing pipelines. In order to fill this gap we designed and created an open source tool that enables fast and reliable dataset preparation for comparative testing of radar signal representations. The opensource tool enables visualisation of different radar signal representations, and includes a commandline interface for batch processing in order to streamline dataset preparations.