US 11,758,350 B2
Posture transition detection and classification using linked biomechanical model
Aditya Sarathy, Santa Clara, CA (US); Xiaoyuan Tu, Sunnyvale, CA (US); Suresh B. Malakar, Cupertino, CA (US); and Hui Lin, Sunnyvale, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Sep. 24, 2021, as Appl. No. 17/485,212.
Prior Publication US 2023/0100254 A1, Mar. 30, 2023
Int. Cl. H04S 7/00 (2006.01); G06F 9/448 (2018.01); G06F 18/2415 (2023.01)
CPC H04S 7/304 (2013.01) [G06F 9/4498 (2018.02); G06F 18/24155 (2023.01); H04S 2400/11 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, with at least one processor, motion data from a headset worn by a user;
selecting, with the at least one processor, features of a linked biomechanical model based on a current posture state;
determining, with the at least one processor, at least one probability that a posture transition occurred based on an output of a classifier, where the output of the classifier is based on the selected features and the motion data;
determining, with the at least one processor, a posture transition based on the at least one probability; and
performing, with the at least one processor, at least one action based on detection of the posture transition.