公开(公告)号：US20250116732A1

公开(公告)日：2025-04-10

申请号：US18565891

申请日：2022-09-22

Applicant: Google LLC

Inventor： Shandor Glenn Dektor ,  Martin Johannes Kraemer ,  Mark Fralick ,  Chuck Tally

IPC: G01R33/00

Abstract: Methods, systems, and apparatus, for calibration quality control using multiple magnetometers. One of the methods includes: receiving measurements by two or more magnetic field sensors of a device over a period of time, wherein each measurement measures a magnetic field at each magnetic field sensor, wherein each measurement at each time point over the period of time includes a vector in one or more spatial axes of a three-dimensional space; computing a difference between the measurements over the period of time, wherein the difference at each time point over the period of time is a result of computing a difference based on one or more pairs of the vectors at the time point; determining that the difference does not remain within a predetermined range over the period of time; and in response, classifying calibration quality of the device as unsuitable for computing a heading of the device.

公开(公告)号：US12249185B2

公开(公告)日：2025-03-11

申请号：US18524615

申请日：2023-11-30

Applicant: Google LLC

Inventor： Mark Fralick ,  Brian Chen

IPC: G06V40/20 ,  G06V10/778 ,  G06V10/80

Abstract: The present disclosure provides for using multiple inertial measurement units (IMUs) to recognize particular user activity, such as particular types of exercises and repetitions of such exercises. The IMUs may be located in consumer products, such as smartwatches and earbuds. Each IMU may include an accelerometer and a gyroscope, each with three axes of measurement, for a total of 12 raw measurement streams. A training image includes a plurality of subplots or tiles, each depicting a separate data stream. The training image is then used to train a machine learning model to recognize IMU data as corresponding to a particular type of exercise.

公开(公告)号：US20240096136A1

公开(公告)日：2024-03-21

申请号：US18524615

申请日：2023-11-30

Applicant: Google LLC

Inventor： Mark Fralick ,  Brian Chen

IPC: G06V40/20 ,  G06V10/778 ,  G06V10/80

CPC classification number: G06V40/20 ,  G06V10/778 ,  G06V10/809

Abstract: The present disclosure provides for using multiple inertial measurement units (IMUs) to recognize particular user activity, such as particular types of exercises and repetitions of such exercises. The IMUs may be located in consumer products, such as smartwatches and earbuds. Each IMU may include an accelerometer and a gyroscope, each with three axes of measurement, for a total of 12 raw measurement streams. A training image includes a plurality of subplots or tiles, each depicting a separate data stream. The training image is then used to train a machine learning model to recognize IMU data as corresponding to a particular type of exercise.

公开(公告)号：US11842571B2

公开(公告)日：2023-12-12

申请号：US17419368

申请日：2020-07-29

Applicant: Google LLC

Inventor： Mark Fralick ,  Brian Chen

IPC: G06V40/20 ,  G06V10/778 ,  G06V10/80

CPC classification number: G06V40/20 ,  G06V10/778 ,  G06V10/809

Abstract: The present disclosure provides for using multiple inertial measurement units (IMUs) to recognize particular user activity, such as particular types of exercises and repetitions of such exercises. The IMUs may be located in consumer products, such as smartwatches and earbuds. Each IMU may include an accelerometer and a gyroscope, each with three axes of measurement, for a total of 12 raw measurement streams. A training image includes a plurality of subplots or tiles, each depicting a separate data stream. The training image is then used to train a machine learning model to recognize IMU data as corresponding to a particular type of exercise.

公开(公告)号：US20220198833A1

公开(公告)日：2022-06-23

申请号：US17419368

申请日：2020-07-29

Applicant: Google LLC

Inventor： Mark Fralick ,  Brian Chen

IPC: G06V40/20 ,  G06V10/80 ,  G06V10/778

Abstract: The present disclosure provides for using multiple inertial measurement units (IMUs) to recognize particular user activity, such as particular types of exercises and repetitions of such exercises. The IMUs may be located in consumer products, such as smartwatches and earbuds. Each IMU may include an accelerometer and a gyroscope, each with three axes of measurement, for a total of 12 raw measurement streams. A training image includes a plurality of subplots or tiles, each depicting a separate data stream. The training image is then used to train a machine learning model to recognize IMU data as corresponding to a particular type of exercise.