Back to results
US 11,589,814 B2Granted
System for wearable, low-cost electrical impedance tomography for non-invasive gesture recognition
AssigneeCarnegie Mellon University
InventorsChristopher Harrison, Yang Zhang
Life of this patent
Estimating the term…
Abstract
The disclosure describes a wearable, low-cost and low-power Electrical Impedance Tomography system for gesture recognition. The system measures cross-sectional bio-impedance using electrodes on wearers' skin. Using all-pairs measurements, the interior impedance distribution is recovered, which is then fed to a hand gesture classifier. This system also solves the problem of poor accuracy of gesture recognition often observed with other gesture recognition approaches.
Claims16
A system for recognizing gestures of a user, comprising:
- a plurality of electrodes adapted to be in contact with a body part of the user;
- a signal generator for generating a signal, wherein the signal generator is connected to a transmitting electrode of the plurality of electrodes;
- a data acquisition module for receiving the signal conducted through an electrical circuit comprising the transmitting electrode, an internal portion of the user's body part, and a receiving electrode of the plurality of electrodes,
- wherein the data acquisition module determines an impedance of the electrical circuit based on the received signal,
- wherein the data acquisition module generates an impedance profile of a cross-section of an interior of the body part based on a plurality of impedance measurements from additional electrical circuits formed from the plurality of electrodes;
- and
- a classifier that identifies a gesture associated with a set of features derived from the impedance profile.
4 more elements
A method of recognizing a hand gesture of a user, comprising:
- providing a plurality of electrodes capable of being worn around the user's arm or wrist in contact with skin of the user;
- generating a signal;
- conducting the signal through a circuit comprising a first electrode pair combination and an internal portion of the user's arm or wrist;
- measuring an impedance of the circuit;
- conducting the signal through additional circuits comprised of non-repeating electrode pairs;
- measuring an impedance of the additional circuits;
- generating an impedance profile of a cross-section of an interior of the user's arm or wrist based on the impedance of the circuit and the impedance of the additional circuits;
- deriving a set of features based on the impedance profile;
- and
- associating the set of features with a hand gesture using a classifier.
7 more elements
Dependencies are inferred from the claim text.