Radar-Based Gesture Recognition

• US 20160041617A1
• Filed: 10/01/2014
• Published: 02/11/2016
• Est. Priority Date: 08/07/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Poupyrev, Ivan
• Granted Patent: US 9,921,660 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01S 13/04 Systems determining presence of a target based on relative movement of target G01S13/56
• CPC Class Codes: G01S 13/06 Systems determining position data of a target
• CPC Class Codes: G01S 7/415 Identification of targets based on measurements of movement associated with the target
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0346 with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231

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.

Claims

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;

determining, based on the one or more initial interactions in the radar field, an identity of the actor;

sensing, through the radar-based gesture-recognition system, an interaction;

determining that the interaction is by the actor having the identity; and

determining, based on information associated with the identity of the actor, a gesture corresponding to the interaction.

2. The computer-implemented method as described in claim 1, 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 actor is a first hand of a person and one of the other actors is a second hand of the person.

4. The computer-implemented method as described in claim 2, wherein the actor is a first person and one of the other actors is a second person.

5. The computer-implemented method as described in claim 4, wherein the interaction is an arm or body movement of the first person and the method further comprises:

receiving a second interaction;

determining that the second interaction is by the second person based on following the second person;

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.

6. The computer-implemented method as described in claim 1, further comprising 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.

7. The computer-implemented method as described in claim 1, 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.

8. The computer-implemented method as described in claim 1, 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.

9. The computer-implemented method as described in claim 8, 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.

10. The computer-implemented method as described in claim 1, further comprising determining that the gesture is associated with a remote device and passing the gesture to the remote device.

11. The computer-implemented method as described in claim 1, 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.

12. 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.

13. The computer-implemented method as described in claim 1, wherein the information associated with the identity of the actor 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.

14. 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 that are 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 one of the multiple human tissue targets from another of the multiple human tissue targets to provide gesture data usable to determine a gesture from the one of the multiple human tissue targets.

15. The radar-based gesture-recognition system of claim 14, wherein the multiple human tissue targets are different parts of a same person.

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

17. The radar-based gesture-recognition system of claim 14, 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.

18. The radar-based gesture-recognition system of claim 14, wherein the radar-emitting element provides the radar field in a three-dimensional volume, the antenna element is capable of receiving reflections in the three-dimensional volume, and the signal processor is configured to process the received reflections in the three-dimensional volume sufficient to provide gesture data usable to determine gestures in three dimensions.

19. The radar-based gesture-recognition system of claim 14, wherein the radar-emitting element is configured to emit microwave radiation over a range of approximately 57 GHz to approximately 63 GHz.

20. An apparatus comprising:

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 human tissue that is within the radar field; and

a signal processor configured to process the received reflections from human tissue within the radar field to provide data associated with the received reflections;

one or more computer processors; and

one or more computer-readable storage media having instructions stored thereon that, responsive to execution by the one or more computer processors, perform operations comprising;

causing the radar-based gesture-recognition system to provide a radar field with the radar-emitting element;

causing the radar-based gesture-recognition system to receive first reflections for a first interaction in the radar field with the antenna element;

causing the signal processor to process the received reflections to provide data for the first interaction;

determining, based on the provided data for the first interaction, an identity of an actor causing the first interaction;

causing the radar-based gesture-recognition system to receive second reflections for a second interaction in the radar field with the antenna element;

causing the signal processor to process the second received reflections to provide second data for the second interaction;

determining, based on the provided second data for the second interaction and the identity of the actor, a gesture corresponding to the second interaction; and

passing the determined gesture to an application or operating system effective to cause the application or operating system to receive an input corresponding to the determined gesture.