3D Gesture Recognition Through RF Sensing

Human interaction with devices is constrained to the surface of these devices through widely used touch sensors. In this work, we enable touchless interfaces that allow humans to interact with devices from a distance. Our approach is based on the design of a two-dimensional array of RF sensors specifically designed to detect the proximity of human body. Each sensor in the array acts as a near-field RF proximity sensor. When parts of the human body come to close proximity to the sensor, they slightly disturb its frequency response, allowing the detection of human fingers or hands. Since our approach is RF-based, it presents several distinct advantages over current sensing technologies which include the ability to work without line of sight, the ability to be easily embedded behind any type of surface, and the ability to scale to almost any size; all while operating at a similar power domain to current proximity sensing technologies. Using a prototype implementation and data collected through a user study, we demonstrate that the RF-array can detect the position and distance of a human hand located at a distance of up to 2 inches with higher than 75% accuracy.

[1]  Joseph A. Paradiso,et al.  Applying electric field sensing to human-computer interfaces , 1995, CHI '95.

[2]  Akira Kimoto,et al.  A Multifunction Tactile and Proximity Sensing Method by Optical and Electrical Simultaneous Measurement , 2012, IEEE Transactions on Instrumentation and Measurement.

[3]  K. Sawa,et al.  Loss estimation and sensing property enhancement for eddy-current-type proximity sensor , 2006, IEEE Transactions on Magnetics.

[4]  Shahram Izadi,et al.  SideSight: multi-"touch" interaction around small devices , 2008, UIST '08.

[5]  Cheng-Ta Chiang,et al.  A Semicylindrical Capacitive Sensor With Interface Circuit Used for Flow Rate Measurement , 2006, IEEE Sensors Journal.

[6]  S. Cohn Parallel-Coupled Transmission-Line-Resonator Filters , 1958 .

[7]  Christopher C. Jobes,et al.  Development of a method to determine operator location using electromagnetic proximity detection , 2010, 2010 IEEE International Workshop on Robotic and Sensors Environments.

[8]  Bryce Osoinach Proximity Capacitive Sensor Technology for Touch Sensing Applications , 2008 .

[9]  Vladimir Pavlovic,et al.  Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Behraad Bahreyni,et al.  Touchless capacitive sensor for hand gesture detection , 2011, 2011 IEEE SENSORS Proceedings.

[11]  Ivan Poupyrev,et al.  Touché: enhancing touch interaction on humans, screens, liquids, and everyday objects , 2012, CHI.

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.