US 11,751,800 B2
Seizure detection using contextual motion
Umar Asif, Melbourne (AU); Stefan von Cavallar, Sandringham (AU); Jianbin Tang, Doncaster East (AU); and Stefan Harrer, Hampton (AU)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Oct. 22, 2020, as Appl. No. 17/77,020.
Prior Publication US 2022/0125370 A1, Apr. 28, 2022
Int. Cl. A61B 5/00 (2006.01); G16H 50/70 (2018.01); G06T 7/00 (2017.01); G06T 7/20 (2017.01); G06T 7/70 (2017.01)
CPC A61B 5/4094 (2013.01) [A61B 5/7267 (2013.01); G06T 7/00 (2013.01); G06T 7/20 (2013.01); G06T 7/70 (2017.01); G16H 50/70 (2018.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method for determining abnormal motion from a patient, the method comprising:
receiving sensory data of the patient and a location in which the patient is present, the sensory data including video data over a period of time the patient is being monitored;
generating contextual information based on the sensory data, the contextual information indicative of surroundings of the patient and characteristics of the location;
generating motion information based on the sensory data, the motion information indicative of movement of the patient in the location;
generating contextual motion data; and
determining the abnormal motion based on the contextual motion data,
wherein the contextual motion data is generated by generating a virtual environment based on the contextual information;
generating a model actor representing the patient;
generating a simulation of the movement of the patient via the model actor in the virtual environment; and
processing the simulation.