Go to JKU Homepage
Institute for Measurement Technology
What's that?

Institutes, schools, other departments, and programs create their own web content and menus.

To help you better navigate the site, see here where you are at the moment.

Measurement system for gesture recognition

Tobias Kronlachner

Intuitive Human-Machine interaction, especially touchless operation is becoming a more and more important issue. One essential part is the recognition of finger gestures. By avoiding contact crucial benefits regarding hygiene and robustness are achieved since it is possible to build the system encapsulated.

Due to these aspects, the following thesis deals with the development of a measurement system for capacitive position estimation of a human finger. Therefore, a measurement setup is built, which is suitable for characterizing really low capacitances in the fF-range while achieving temporal resolution in the range of ms. This is vital for the sensing of the position and the resultant recognition of gestures. A synchronous demodulation based principle is used, which measures the displacement current and allows the indication of the capacitance. The aim of making the position estimation simple is already considered in the design of the electrode structure. The chosen structure uses a hexagonal shape and is designed in a way that allows differential evaluation. Model based position calculation has high computational cost in the case of non-linear equations. Hence, a method is developed that does not require the solving of an optimization problem. Especially when it comes to real-time processing at a microcontroller this is a decisive criterion.

Keywords: HMI, gesture recognition, touchless, capacitance measurement

August 16th, 2017

Figure 1: This picture shows the measurement unit with the linear axis used for reference measurements. Figure 2: This picture shows a recorded finger gesture.