Abstract
The increased popularity of gesture-controlled devices and local position detection advances the needs for powerful yet compact IoT-solutions featuring machine learningmodels. There is already a variety of systems able to capture the position of a hand or
recognise specific gestures to control or interact with devices. Most of them use camera
systems sometimes combined with detection devices in or on a person’s hand. This paper introduces a way of achieving both, position detection and gesture recognition, by
using three IMU sensors. An IMU is an Inertial Measurement Unit which consists of a
gyroscope, an accelerometer, and a magnetometer. Using these sensors enables for accurate measurements of the movement and orientation of a device. To recognise specific
gestures, a machine learning model is trained with data from the IMU sensors to create
a system which can accurately detect the gesture in real time.
| Date of Award | 2024 |
|---|---|
| Original language | English (American) |
| Supervisor | Stephan Selinger (Supervisor) |