Abstract
Augmenting arbitrary physical objects with digital content leads to the missing interface problem, because those objects were never designed to incorporate such digital content and so they lack a user interface. A review of related work reveals that current approaches fail due to limited detection fidelity and spatial resolution. Our proposal, based on Google Soli’s radar sensing technology, is designed to detect micro-gestures on objects with sub-millimeter precision. Preliminary results with a custom gesture set show that Soli’s core features and traditional machine learning models (Random Forest and Support Vector Machine) do not lead to robust recognition accuracy, and so more advanced techniques should be used instead, possibly incorporating additional sensor features.