	US 11,853,741 B2
	Federated learning for connected camera
Wende Zhang, Birmingham, MI (US); Esther Anderson, Canton, MI (US); Mark T Gaylord, Lake Orion, MI (US); and Robert A Dziurda, Waterford, MI (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed on Jan. 10, 2022, as Appl. No. 17/647,524.
Prior Publication US 2023/0221942 A1, Jul. 13, 2023
Int. Cl. G06F 8/65 (2018.01); G06F 8/71 (2018.01); G06F 18/214 (2023.01); G06F 18/2415 (2023.01); G06T 7/70 (2017.01); G06V 10/00 (2022.01); G06V 20/00 (2022.01)

CPC G06F 8/65 (2013.01) [G06F 8/71 (2013.01); G06F 18/2148 (2023.01); G06F 18/2415 (2023.01); G06T 7/70 (2017.01); G06V 10/00 (2022.01); G06V 20/00 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30252 (2013.01)]

19 Claims

1. A method, comprising:

obtaining, at a vehicle, sensor data for a detected object external to the vehicle from a sensor of the vehicle;

obtaining, at the vehicle, location data associated with the detected object;

obtaining, at the vehicle, a localized vehicle classification model associated with a first responder vehicle type;

assigning the first responder vehicle type to the detected object based on an output by the localized vehicle classification model as a function of the sensor data and the location data using the localized vehicle classification model;

automatically determining that an incident external to the vehicle has occurred responsive to assigning the first responder vehicle type to the detected object; and

initiating, at the vehicle, an action responsive to automatically determining the incident has occurred.