Researchers at the University of Bristol have found a new way to use a smartwatch to sense hand gestures.
“Our research is a first step towards what could be the most accurate method for detecting hand gestures in smartwatches”
Professor Mike Fraser, Asier Marzo and Jess McIntosh from the Bristol Interaction Group (BIG) at the University of Bristol worked with the University Hospitals Bristol NHS Foundation Trust to use ultrasound to detect the movement of muscles in the forearm and so determine the gesture.
Ultrasonic imaging is already used in medicine, such as pregnancy scans along with muscle and tendon movement, and the researchers saw the potential for this to be used as a way of understanding hand movement.
For instance, a gesture could be used to dim the lights in the living room, or to open or close a window. Hand gesture recognition can be achieved in many ways, but the placement of a sensor is a major restriction and often rules out certain techniques. However, with smartwatches becoming the leading wearable device this allows sensors to be put in the watch to sense hand movement.
“With current technologies, there are many practical issues that prevent a small, portable ultrasonic imaging sensor integrated into a smartwatch. Nevertheless, our research is a first step towards what could be the most accurate method for detecting hand gestures in smartwatches,” says Jess McIntosh, PhD student in the Department of Computer Science and BIG Group.
The team used image processing algorithms and machine learning to classify muscle movement as gestures. The researchers also carried out a user study to find the best sensor placement for this technique. You can see more on how this ‘EchoFlex’ technology works in the video below:
The research showed a very high recognition accuracy, and importantly this sensing method worked well at the wrist so that it can be used for future wearable devices, such as smartwatches, to sense gestures.
You can follow the Bristol Interaction Group on Twitter to keep up to date with the latest from thr Department of Computer Science, University of Bristol: @BristolIG
