Radar-based gesture recognition

Patent metadata

Field	Value
Publication number	US-9921660-B2
Application number	US-201414504038-A
Country	US
Kind code	B2
Filing date	Oct 1, 2014
Priority date	Aug 7, 2014
Publication date	Mar 20, 2018
Grant date	Mar 20, 2018

Abstract

This document describes techniques using, and devices embodying, radar-based gesture recognition. These techniques and devices can enable a great breadth of gestures and uses for those gestures, such as gestures to use, control, and interact with computing and non-computing devices, from software applications to refrigerators. The techniques and devices are capable of providing a radar field that can sense gestures from multiple actors at one time and through obstructions, thereby improving gesture breadth and accuracy over many conventional techniques.

First claim

What is claimed is:

1. A computer-implemented method comprising:
providing, through a radar-based gesture-recognition system, a radar field;
sensing, through the radar-based gesture-recognition system, one or more initial interactions by an actor in the radar field, the actor being one of a particular human finger, hand, or arm;
determining, based on the one or more initial interactions in the radar field, an identifying factor, the identifying factor including a height, weight, skeletal structure, facial shape, or hair of the actor;
associating the identifying factor with an identity, the identity identifying the actor; and
storing the identity of the actor with the identifying factor for the actor, the identifying factor enabling identification of an unknown actor through comparison of a second identifying factor with the identifying factor, the second identifying factor sensed by the radar-based gesture-recognition system or another radar-based gesture-recognition system, the identifying factor and the second identifying factor being equivalent features of the actor and the unknown actor.

2. The computer-implemented method as described in claim 1 , the method further comprising sensing, through the radar-based gesture recognition system, an interaction and determining that the interaction is by the actor having the identity, wherein determining that the interaction is by the actor having the identity follows the actor using the radar-based gesture-recognition system, the following effective to differentiate the actor from other actors.

3. The computer-implemented method as described in claim 2 , wherein the interaction is an arm or body movement of the actor and the method further comprises:
determining, based on information associated with the identity of the actor, a gesture corresponding to the interaction:
receiving a second interaction;
determining that the second interaction is by one of the other actors having the second identifying factor, the one of the other actors associated with a second identity;
determining, based on second information associated with the second person, a second gesture corresponding to the second interaction; and
providing the gesture and the second gesture effective to cause an application or operating system to receive first and second inputs associated with the first gesture and the second gesture, respectively.

4. The computer-implemented method as described in claim 1 , further comprising:
sensing, through the radar-based gesture-recognition system, an interaction;
determining that the interaction is by the actor having the identity;
determining, based on information associated with the identity, a gesture corresponding to the interaction; an
passing the determined gesture to an application or operating system of a computing device performing the method effective to cause the application or operating system to receive an input corresponding to the determined gesture.

5. The computer-implemented method as described in claim 4 , wherein the information aids in determining the gesture based on the interaction, the information indicating historical gesture variances or physical characteristics of the actor affecting determination of the gesture.

6. The computer-implemented method as described in claim 4 , wherein determining the gesture corresponding to the interaction maps, based on the information associated with the identity of the actor, the interaction to an identity-specific gesture associated with the actor.

7. The computer-implemented method as described in claim 6 , wherein the identity-specific gesture is a pre-configured control gesture uniquely associated with the actor and an application, and the method further comprises passing the pre-configured control gesture to the application effective to cause the application to be controlled by the identity-specific gesture.

8. The computer-implemented method as described in claim 4 , further comprising determining that the gesture is associated with a remote device and passing the gesture to the remote device.

9. The computer-implemented method as described in claim 4 , wherein at least a portion of the interaction includes reflections from human tissue having a layer of material interposed between the radar-based gesture-recognition system and the human tissue, the layer of material including glass, wood, nylon, cotton, or wool.

10. The computer-implemented method as described in claim 1 , wherein the radar-based gesture-recognition system is associated with a computing device that performs the method, the radar field is a near radar field, and the interaction is sensed over a range extending from one millimeter to 1.5 meters from a display of the computing device.

11. The computer-implemented method as described in claim 4 , wherein the information associated with the identity indicates a physical size of the actor or a scale for gestures performed by the actor, and wherein determining the gesture corresponding to the interaction is based on the physical size or the scale for gestures.

12. A radar-based gesture-recognition system comprising:
a radar-emitting element configured to provide a radar field, the radar field configured to penetrate fabric and reflect from human tissue;
an antenna element configured to receive reflections from multiple human tissue targets including hands, arms, legs, head, or body from a same or different person within the radar field; and
a signal processor configured to:
process the received reflections from the multiple human tissue targets within the radar field sufficient to differentiate the multiple human tissue targets from one another;
determine, based on the received reflections, an identifying factor, the identifying factor including a height, weight, skeletal structure, facial shape or hair of a first human tissue target of the multiple human tissue targets;
associate the identifying factor with an identity of the first human tissue target of the multiple human tissue targets;
store the identity and the identifying factor of the first human tissue target of the multiple human tissue targets, the identifying factor enabling identification of a second human tissue target of the multiple human tissue targets through comparison of the first human tissue target identifying factor with a second identifying factor associated with the second human tissue target,
the identifying factor and the second identifying factor being equivalent features of the first human tissue target and the second human tissue target; and
provide gesture data usable to determine a gesture from the first human tissue target of the multiple human tissue targets.

13. The radar-based gesture-recognition system of claim 12 , wherein the multiple human tissue targets are different hands of a same person.

14. The radar-based gesture-recognition system of claim 12 , wherein the multiple human tissue targets are hands of different persons and differentiating the first human tissue target of the multiple human tissue targets from the second human tissue target of the multiple human tissue targets is effective to provide gesture data for one of the different persons.

15. The radar-based gesture-recognition system of claim 12 , wherein the radar field is about one to about ten meters in depth and the antenna element or the signal processor are configured to process the received reflections to provide large-body gestures based on reflections from human tissue caused by body, arm, or leg movements.

16. The radar-based gesture-recognition system of claim 12 , wherein the radar- emitting elemen

Assignees

• Google Inc
• Google Llc

Inventors

• Poupyrev Ivan

Classifications

• H04L63/0861

  using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231) · CPC title

• G06F3/0346

  with detection of the device orientation or free movement in a three-dimensional [3D] space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors · CPC title

• G01S13/06

  Systems determining position data of a target · CPC title

• G06F3/017 Primary

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title

• G01S13/04

  Systems determining presence of a target (based on relative movement of target G01S13/56) · CPC title