Radar-Based Gesture Recognition on Deformable Objects
(2026) Radar-Based Human-Computer Interaction — ISBN: [978-3-032-04326-9], p. 117-135, accepted/in-press
Files
No attached file found for this publication.
Details
- Authors
- Abstract
- This chapter investigates the feasibility and challenges of using millimetre-wave radar for gesture recognition on deformable objects, such as plush toys or flexible materials, which are typically not instrumented with sensors. Unlike vision-based systems that suffer from occlusion and require line of sight, radar sensing can detect gestures through non-conductive materials and under partial occlusion. The authors compare prior work on gesture recognition performance across mid-air, on-object, and on-deformable-object contexts using different radar signal representations and deep learning models. In addition, the authors run the experiment demonstrated that object deformations do not negatively impact recognition accuracy. These findings open new possibilities for contactless interaction with soft materials in everyday environments without requiring embedded instrumentation.
- Affiliations
Citations
Pucihar, K. Č., Kljun, M., & Attygalle, N. (2026). Radar-Based Gesture Recognition on Deformable Objects. In Klen Čopič Pucihar, Radu-Daniel Vatavu, Dariush Salami, Nuwan T. Attygalle (eds.) (ed.), Radar-Based Human-Computer Interaction (p. p. 117-135). Springer. https://doi.org/10.1007/978-3-032-04327-6_6