Techniques for gesture recognition using photoplethysmographic (PPMG) sensor and low-power wearable gesture recognition device using the same

Patent metadata

Field	Value
Publication number	US-10348355-B2
Application number	US-201514855746-A
Country	US
Kind code	B2
Filing date	Sep 16, 2015
Priority date	Sep 16, 2015
Publication date	Jul 9, 2019
Grant date	Jul 9, 2019

Abstract

A wearable gesture recognition device is disclosed that provides gesture recognition for gestures that may include a hold or steady-state component, and may account and adapt for real-time fit-level changes. The wearable gesture recognition device may integrate a photoplethysmographic (PPMG) and a piezoelectric (PZE) sensor such that respective sensor signals may be used individually, or in concert for gesture recognition. Thus the wearable gesture recognition device generally disclosed herein may advantageously perform gesture recognition through the fusion of PPMG and PZE signals. To support continuous gesture recognition, the wearable gesture recognition device may use a low-power activity detection scheme that analyzes a PZE signal prior to higher-power gesture classification. Moreover, the wearable gesture recognition device may provide power management by controlling a duty-cycle of the PPMG sensor without necessarily reducing recognition performance. The PPMG sensor and the PZE sensor may be co-located and housed within a same sensor package.

First claim

What is claimed is:

1. A device comprising: a photoplethysmographic (PPMG) sensor including at least one infrared light emitting diode (IR LED) and at least one photodetector, the PPMG sensor to couple to a user at a first body location and output a first signal;
a piezoelectric (PZE) sensor to couple to the user at the first body location and output a second signal, the second signal representing mechanical vibrations caused by movement of the user;
a memory having a gesture dictionary, the gesture dictionary to store at least a part of one or more reference waveforms; and
a controller including a gesture recognition mode configured to receive the first signal from the PPMG sensor and the second signal from the PZE sensor, and determine an identified gesture based in part on comparing an aggregate waveform to the one or more reference waveforms, the aggregate waveform including at least a portion of the first signal and the second signal;
wherein the PZE sensor includes at least one through-hole, wherein the at least one IR LED and the at least one photodetector are at least partially disposed within the through-hole.

2. The device of claim 1 , wherein the controller is further configured to receive an impedance measurement for the second signal.

3. The device of claim 2 , wherein the controller is further configured to determine a current fit-level based in part on the impedance measurement, and wherein the one or more reference waveforms correspond to the determined current fit-level.

4. The device of claim 2 , wherein the controller is further configured to:
determine a current fit-level based in part on the impedance measurement; and
provide an alert to a user when the determined current fit-level is different from a previously known fit-level.

5. The device of claim 1 , wherein the controller includes a signal combiner configured to normalize at least a portion of each of the first and second signals and generate the aggregate waveform based on concatenating the normalized portions of the first and second signals.

6. A computer-implemented method for gesture detection, the method comprising:
receiving, by a processor, a first signal from a low-power stage, the low-power stage utilizing a piezoelectric (PZE) sensor, the PZE sensor to couple to a user at a first body location, wherein the first signal represents mechanical vibrations caused by movement of the user;
detecting, by the processor, a probable gesture based on the first signal from the low- power stage;
in response to detecting the probable gesture, receiving by the processor a second signal from a high-power stage, the high-power stage utilizing more power relative to the low-power stage and utilizing a photoplethysmographic (PPMG) sensor, the PPMG sensor to couple to the user at the first body location;
and identifying, by a processor, a gesture based in part on comparing an aggregate waveform to one or more reference waveforms, the aggregate waveform including at least a portion of the first signal from the low-power stage and the second signal from the high-power stage.

7. The method of claim 6 , further comprising determining a fit-level timer has elapsed, and in response thereto, receiving a current impedance measurement for the second signal.

8. The method of claim 7 , further comprising:
determining a current fit-level based in part on the current impedance measurement, and wherein the one or more reference waveforms are associated with the determined current fit-level.

9. The method of claim 7 , further comprising:
determining a current fit-level based at least in part on the current impedance measurement, and
providing an alert to a user when the determined current fit-level is different from a previously known fit-level.

Assignees

• Intel Corp

Inventors

• Camacho Perez Jose Rodrigo
• Moncada Gonzalez Hector Raul
• Cordourier Maruri Hector Alfonso
• Zamora Esquivel Julio Cesar
• Lopez Meyer Paulo
• Ibarra Von Borstel Alejandro

Classifications

• H04B1/40 Primary

  Circuits · CPC title

• G06F3/015

  Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection · CPC title

• Y02D70/00

  Cross-Sectional Technologies · mapped topic

• G06F1/163 Primary

  Wearable computers, e.g. on a belt · CPC title

• Y02D30/70

  in wireless communication networks · CPC title