- Patent Title: Supervised and unsupervised techniques for motion classification
-
Application No.: US17884456Application Date: 2022-08-09
-
Publication No.: US12008092B2Publication Date: 2024-06-11
- Inventor: Lucas Allen Budman , Amitabh Agrawal , Andrew Weber Spott
- Applicant: TruU, Inc.
- Applicant Address: US CA Palo Alto
- Assignee: TruU, Inc.
- Current Assignee: TruU, Inc.
- Current Assignee Address: US CA Palo Alto
- Agency: Fenwick & West LLP
- Main IPC: G06F21/32
- IPC: G06F21/32 ; G06F18/23213 ; G06N20/00 ; G06T17/00 ; G06V10/764 ; G06V40/10 ; G06V40/20

Abstract:
A system and method are disclosed for identifying a user based on the classification of user movement data. An identity verification system receives a sequence of motion data characterizing movements performed by a target user. The sequence of motion data is received as a point cloud of the motion data. The point cloud is input a machine-learned model trained based on manually labeled point clusters of a training set of motion data that each represent a movement. The machine-learned model identifies a movement represented by the point cloud of the motion data and assigns a label describing the movement the point cloud. The system generates a labeled representation of the sequence of motion data comprising the label identifying a portion of the sequence of motion data corresponding to the identified movement.
Public/Granted literature
- US20220382845A1 Supervised and Unsupervised Techniques for Motion Classification Public/Granted day:2022-12-01
Information query