Background
Touchless interaction systems have grown in prevalence in recent years, including gesture-based interaction systems. Gesture recognition forms an integral part of human-computer interaction (HCI) technologies that deal with recognizing various movements of the human body, and interpreting them as commands to interact with a machine. Hand gesture recognition using wearable devices has many applications in robotics, medicine, linguistics, virtual reality, and gaming.
Typical hand gesture recognition techniques are either vision/radar-based, or wearable systems. Existing gesture recognition and interaction techniques are limited by many challenges, including sensitivity to light and occlusion, the requirement of gloves or electrodes to be attached to the skin, lack of miniaturization, complex computation algorithms, and expensive implementations.
Invention Description
Researchers at Arizona State University have developed a radio-frequency (RF)-based gesture recognition technique designed for human-computer interaction (HCI) systems. This technology uses an RF sensor that can detect the electric field changes resulting from the motion of tendons, blood vessels, muscles, and other tissues in the human hand. The changes in field distribution can be mapped to different gestures employing machine learning algorithms and used to interact with a computer. The sensor is designed to effectively radiate in a lossy inhomogeneous medium (e.g., human wrist) to capture the detailed field changes caused by the micromotions of various tissues/muscles in the region.
Potential Applications
- Wearable devices for hand gesture recognition:
- Robotics
- Sign language
- Assisted mobility
- Virtual reality/gaming
Benefits and Advantages
- Miniaturized design – small enough to be integrated into smartwatches or wristbands
- Near field sensor – can detect micromotions of various tissues/muscles
- Sensor alignment correction – detection of main arteries through pulse tracking
- Improved accuracy – detects presence of air gaps