Finger Air Writing - Movement Reconstruction with Low-cost IMU Sensor

Junaid Younas, Hector Margarito, Sizhen Bian, Paul Lukowicz

In: MobiQuitous 2020 - 17th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services. ACM International Conference on Mobile and Ubiquitous Systems (MobiQuitous-2020) December 7-9 Darmstadt Germany Pages 69-75 ISBN 978-1-4503-8840-5 ACM New York, NY, United States 2021.


In this paper, we present and evaluate a method for trajectory reconstruction from IMU signals generated when a person ”air writes” text with a finger worn IMU to make the resulting text as human-readable as possible. The vision is to provide a virtual ”sticky note” allowing people to digitally attach simple texts to locations. Thus, for example, we envision a person walking by someone’s locked office door and simply air writing, ”let me know when you are back”. The other person would then have, for example, their phone vibrate when they come into the office and would see the message on their screen. The problem that we address is how to extract from such ”air writing”, performed without visual feedback or a real surface to write, de-noised 2D trajectories that can be later displayed on a screen in a way that is well readable to humans. We describe the sensor and its signals, the trajectory extraction algorithm, and a user study that shows that we can achieve a high degree of readability.

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz