Invention Grant
- Patent Title: System and method for exercise type recognition using wearables
-
Application No.: US17419368Application Date: 2020-07-29
-
Publication No.: US11842571B2Publication Date: 2023-12-12
- Inventor: Mark Fralick , Brian Chen
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Lerner David LLP
- International Application: PCT/US2020/043997 2020.07.29
- International Announcement: WO2022/025877A 2022.02.03
- Date entered country: 2021-06-29
- Main IPC: G06V40/20
- 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.
Public/Granted literature
- US20220198833A1 System And Method For Exercise Type Recognition Using Wearables Public/Granted day:2022-06-23
Information query