US 12,456,301 B2
Method of training a machine learning algorithm to identify objects or activities in video surveillance data
Kamal Nasrollahi, Brøndby (DK)
Assigned to MILESTONE SYSTEMS A/S, Brøndby (DK)
Filed by MILESTONE SYSTEMS A/S, Brøndby (DK)
Filed on Sep. 6, 2022, as Appl. No. 17/929,995.
Claims priority of application No. 21196002 (EP), filed on Sep. 10, 2021.
Prior Publication US 2023/0081908 A1, Mar. 16, 2023
Int. Cl. G06V 20/52 (2022.01); G06N 20/00 (2019.01); G06T 7/194 (2017.01); G06T 7/70 (2017.01); G06T 17/00 (2006.01); G06V 10/774 (2022.01)
CPC G06V 20/52 (2022.01) [G06N 20/00 (2019.01); G06T 7/194 (2017.01); G06T 7/70 (2017.01); G06T 17/00 (2013.01); G06V 10/7747 (2022.01); G06T 2207/10028 (2013.01); G06T 2207/20081 (2013.01); G06V 2201/07 (2022.01)] 12 Claims
OG exemplary drawing
 
1. A video surveillance method of training a machine learning algorithm to identify activities in video surveillance data by a method comprising the steps of:
generating a 3D simulation of a real environment from video surveillance data captured by at least one video surveillance camera installed in the real environment;
synthesizing activities within the simulated 3D environment; and
using the synthesized activities within the simulated 3D environment as training data to train the machine learning algorithm to identify objects or activities, wherein the synthesized activities within the simulated 3D environment used as training data are all viewed from the same viewpoint in the simulated 3D environment;
installing a video surveillance camera at the same viewpoint in the real environment as the viewpoint from which the synthesized activities within the simulated 3D environment used as training data are viewed; and
applying the trained machine learning algorithm to video surveillance data captured by the video surveillance camera.