RF-Based Micro-Motion Tracking for Gesture Tracking and Recognition

• US 20190155396A1
• Filed: 01/18/2019
• Published: 05/23/2019
• Est. Priority Date: 04/30/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.), Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Original Assignee: Google LLC (Alphabet Inc.), Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Inventors: Lien, Jaime, Olson, Erik M., Amihood, Patrick M., Poupyrev, Ivan
• Granted Patent: US 10,817,070 B2
• Time in Patent Office: Days
• CPC Class Codes: G01S 13/58 Velocity or trajectory determination systems; Sense-of-movement determination systems
• CPC Class Codes: G01S 13/66 Radar-tracking systems; Analogous systems
• CPC Class Codes: G01S 13/88 Radar or analogous systems specially adapted for specific applications electromagnetic prospecting or detecting of objects, e.g. near-field detection, G01V3/00
• CPC Class Codes: G01S 13/89 for mapping or imaging
• CPC Class Codes: G01S 7/415 Identification of targets based on measurements of movement associated with the target
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• 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

Abstract

This document describes techniques for radio frequency (RF) based micro-motion tracking. These techniques enable even millimeter-scale hand motions to be tracked. To do so, radar signals are used from radar systems that, with conventional techniques, would only permit resolutions of a centimeter or more.

Claims

1. One or more non-transitory computer-readable storage media having instructions stored thereon that, responsive to execution by one or more computer processors, implement a micro-motion tracking module and a recognition module:

the micro-motion tracking module configured to;

receive a first radar signal representing reflections of a radar field off first and second points of a hand at a first time, the first and second points of the hand moving relative to one another within the radar field;

determine, based on energies of the first radar signal, velocities of the first and second points of the hand at the first time;

receive a second radar signal representing reflections of the radar field off the first and second points of the hand at a second time;

determine, based on energies of the second radar signal, velocities of the first and second points of the hand at the second time;

calculate, based on the velocities of the first and second points of the hand at the first and second times, a relative velocity between the first and second point of the hand; and

determine, based on the relative velocity between the first and second point of the hand and an elapsed time between the first and second times, a millimeter-scale change in displacement between the first and second points of the hand; and

the recognition module configured to;

determine, based on the change in displacement, a gesture of the first and second points of the hand; and

pass the gesture effective to control or alter a display, function, or capability of a device.

2. The one or more non-transitory computer-readable storage media of claim 1, wherein the velocities of the first and second points at the first and second times are determined based on micro-Doppler centroids of the first and second radar signals.

3. The one or more non-transitory computer-readable storage media of claim 1, wherein the energies of the first and second radar signals are functions of ranges to the first and second points of the hand at the first and second times.

4. The one or more non-transitory computer-readable storage media of claim 1, wherein the radar signals are received via a single antenna element.

5. The one or more non-transitory computer-readable storage media of claim 1, wherein an extended Kalman filter is used in conjunction with Doppler centroids corresponding to the first and second parts of the hand to allow for nonlinear phase unwrapping of the first and second radar signals.

6. A computer-implemented method comprising:

receiving a first radar signal representing reflections of a radar field off first and second points of a hand at a first time, the first and second points of the hand moving relative to one another within the radar field;

determining, based on energies of the first radar signal, velocities of the first and second points of the hand at the first time;

receiving a second radar signal representing reflections of the radar field off the first and second points of the hand at a second time;

determining, based on energies of the second radar signal, velocities of the first and second points of the hand at the second time;

calculating, based on the velocities of the first and second points of the hand at the first and second times, a relative velocity between the first and second points of the hand; and

determining, based on the relative velocity between the first and second points of the hand and an elapsed time between the first and second times, a millimeter-scale change in displacement between the first and second points of the hand.

7. The method of claim 6, wherein the radar field is emitted by a single radar element and the first and second radar signals are received by a single antenna.

8. The method of claim 6, wherein the energies of the first and second radar signals are functions of ranges to the first and second points of the hand at the first and second times.

9. The method of claim 6, wherein the velocities of the first and second points at the first and second times are radial velocities determined through Doppler frequencies of the radar signal.

10. The method of claim 9, wherein the velocities of the first and second points at the first and second times are based on micro-Doppler centroids of the first and second radar signals.

11. The method of claim 6, wherein the first and second radar signals comprise a superposition of energies corresponding to the first and second points of the hand.

12. The method of claim 6, further comprising creating a range-Doppler-time data cube that contains data corresponding to the first and second received radar signals and other received radar signals representing reflections of the radar field off the first and second points of the hand at other times, wherein the velocities of the first and second points of the hand at the first and second times are determined from portions of the range-Doppler-time data cube corresponding to the first and second times.

13. The method of claim 6, wherein the radar field has a wavelength greater than the millimeter-scale.

14. The method of claim 6, wherein the change in displacement is determined by integrating the relative velocity.

15. An apparatus comprising:

one or more computer processors;

a radar system comprising;

one or more radar-emitting elements configured to provide a radar field; and

one or more antenna elements configured to receive radar signals representing reflections of the radar field off two or more points of a hand that are moving relative to one another within the radar field; and

one or more computer-readable storage media having instructions stored thereon that, responsive to execution by the one or more computer processors, implement a micro-motion tracking module and a recognition module;

the micro-motion tracking module configured to;

cause the radar-emitting elements to provide the radar field;

receive a first radar signal from the antenna elements representing reflections of the radar field off the first and second points of a hand at a first time;

determine, based on energies of the first radar signal, velocities of the first and second points of the hand at the first time;

receive a second radar signal from the antenna elements representing reflections of the radar field off the first and second points of the hand at a second time;

determine, based on energies of the second radar signal, velocities of the first and second points of the hand at the second time;

calculate, based on the velocities of the first and second points of the hand at the first and second times, a relative velocity between the first and second point of the hand; and

determine, based on the relative velocity between the first and second point of the hand and an elapsed time between the first and second times, a millimeter-scale change in displacement between the first and second points of the hand; and

the recognition module configured to;

determine, based on the change in displacement, a gesture of the first and second points of the hand; and

pass the gesture effective to control or alter a display, function, or capability of a device.

16. The apparatus of claim 15, wherein the velocities of the first and second points at the first and second times are determined based on micro-Doppler centroids of the first and second radar signals.

17. The apparatus of claim 15, wherein the energies of the first and second radar signals are functions of ranges to the first and second points of the hand at the first and second times.

18. The apparatus of claim 15, wherein the antenna elements are a single antenna element.

19. The apparatus of claim 15, wherein an extended Kalman filter is used in conjunction with Doppler centroids corresponding to the first and second parts of the hand to allow for nonlinear phase unwrapping of the first and second radar signals.

20. The apparatus of claim 15, wherein the apparatus comprises a mobile phone or tablet.