Ultrasound based hand gesture recognition
From iis-projects
Contents
Short Description
Ultrasound (US) imaging is a non-invasive imaging technique that provides visible information on the structure of musculoskeletal tissues, organs, and vascular system. Recent research trends include the development of wearable US probes, with minimal power consumption and reduced count of piezoelectric elements. In fact, meaningful physiological information can be derived also from single-element transducers. Within this framework, at IIS we have recently developed an ultra-low power wearable US probe, based on an MSP430 and nRF52 microcontrollers, operating with a single US channel and consuming less than 20mW [1].
In the context of prosthetics control, electromyography (EMG) is the golden standard approach to perform hand gesture recognition tasks. The scope of this project is to implement hand gesture recognition by means of single-channel ultrasound data platforms, such as the probe developed at IIS [1]
Goal & Tasks
In this project, you will work with a novel wearable US probe [1] to perform hand gesture recognitions. The main tasks are:
- Data collection
- development of algorithms for hand gesture recognition based on ultrasound
- porting of the algorithm on the on-board MCU for real-time detection of gestures
Literature
- [1] Ultra low power wearable ultrasound probe
- [2] Ultrasound imaging for hand prosthesis control: a comparative study of features and classification methods
- [3] Ultrasound Imaging as a Human-Machine Interface in a Realistic Scenario
Prerequisites
- embedded C
- Python
- basic Machine Learning
Status: Completed
Matteo Anderegg
- Supervision: Sergei Vostrikov, Andrea Cossettini
Character
- 10% Literature Study
- 20% data collection and analysis
- 40% algorithm development
- 30% system development