Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11822729-B2
Publication Date
2023-11-21
Expiration Date
Abstract
Systems and methods for gesture-based control are provided. A system may include a wearable device comprising a plurality of biopotential channels and a location sensor. The system may be configured to generate a data stream and classify a gesture based on an analysis of an analytical segment. The gesture classification may include (a) determining that a first portion of the analytical segment shows a signal parameter at a baseline; (b) determining that a second portion of the analytical segment shows the signal parameter satisfying a first threshold condition; (c) determining that a third portion of the analytical segment shows the signal parameter satisfying a second threshold condition; (d) determining that a time between the second portion and the third portion is greater than a threshold; and (e) while the signal parameter satisfies the first and/or second threshold condition, detecting a change in location of the wearable device.
Core Innovation
The invention provides a wearable device configured to be worn by a person and to perform gesture-based control using a plurality of biopotential channels and a location sensor. Each biopotential channel includes a pair of electrodes and outputs signals indicating biopotentials at a respective location on a body part of the person, with at least a first biopotential channel varying in response to motions or intended motions of an index finger. A processor generates a data stream based on outputs from the plurality of biopotential channels and/or the location sensor.
The processor classifies a gesture based on an analysis of an analytical segment of the data stream using baseline determination and threshold transitions. The classification determines that a first portion shows a signal parameter at a baseline, followed by a second portion satisfying a first threshold condition different from the baseline, and then a third portion satisfying a second threshold condition different from the baseline. The classification further determines that a time between the second portion and the third portion is greater than a threshold period of time.
While the signal parameter satisfies the first and/or second threshold condition, the system detects, based on the output of the location sensor, a change in location of the wearable device in a first direction relative to a frame of reference of the person. Based on the gesture classification including the baseline-to-threshold logic and the location-based detection, the system generates a command that causes an application to make a selection or move an object or a selector in the first direction relative to the frame of reference of the person.
Claims Coverage
The provided excerpt includes two independent claims, one for a system and one for a method, each centered on a gesture classification pipeline driven by biopotential-channel baseline/threshold analysis combined with location-sensor detection, and ending with command generation to an application.
Wearable device with biopotential channels and location sensor for gesture-based control
A wearable device comprises a plurality of biopotential channels including at least a first biopotential channel and a second biopotential channel, each including a pair of electrodes configured to output signals indicating biopotentials at a respective location, with the output of at least the first biopotential channel varying in response to motions or intended motions of an index finger; the wearable device also comprises a location sensor configured to output data indicating a location of the body part; and a processor.
Analytical-segment gesture classification using baseline-to-first-threshold-to-second-threshold transitions with time constraint
The system generates a data stream based on outputs from the plurality of biopotential channels and/or the location sensor; classifies a gesture based on an analysis of an analytical segment by determining a first portion showing a signal parameter at a baseline, a second portion following the first portion showing the signal parameter satisfying a first threshold condition different than the baseline, and a third portion following the second portion showing the signal parameter satisfying a second threshold condition different than the baseline, and determining that a time between the second portion and the third portion is greater than a threshold period of time.
Location-sensor directional change detection during threshold satisfaction relative to a frame of reference
While the signal parameter satisfies the first and/or second threshold condition, the system detects, based on the output of the location sensor, a change in location of the wearable device in a first direction relative to a frame of reference of the person.
Application command generation to make a selection or move an object or selector
Based on the gesture classification, the system generates a command that causes an application to make a selection or move an object or a selector in the first direction relative to the frame of reference of the person.
Method implementation of gesture-based control with command generation from classified gesture and location change
The method includes generating a data stream based on outputs from a plurality of biopotential channels and/or a location sensor of a wearable device worn by a person, classifying a gesture using baseline-to-first-threshold-to-second-threshold transitions over an analytical segment with a time constraint, detecting a change in location in a first direction relative to a frame of reference while the signal parameter satisfies the first and/or second threshold condition, and generating a command causing an application to make a selection or move an object or a selector in the first direction relative to the frame of reference of the person.
Across both independent claims, the inventive coverage is the combination of data-stream generation from biopotential channels and a location sensor, gesture classification via analytical-segment baseline and threshold-condition transitions with a threshold period of time constraint, concurrent location-sensor-based detection of a change in location in a first direction relative to a frame of reference, and command generation to cause an application to make a selection or move an object or a selector in that first direction.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?