US 11,869,351 B2
Automated incident detection for vehicles
Wende Zhang, Birmingham, MI (US); Esther Anderson, Canton, MI (US); Robert A. Dziurda, Waterford, MI (US); and Mark T. Gaylord, Lake Orion, MI (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Sep. 9, 2021, as Appl. No. 17/470,454.
Prior Publication US 2023/0074620 A1, Mar. 9, 2023
Int. Cl. G08G 1/0962 (2006.01); G06T 11/00 (2006.01); H04N 5/76 (2006.01); G06N 20/20 (2019.01); G06V 20/40 (2022.01); G06V 20/56 (2022.01); G06F 18/25 (2023.01)
CPC G08G 1/09626 (2013.01) [G06F 18/251 (2023.01); G06N 20/20 (2019.01); G06T 11/00 (2013.01); G06V 20/41 (2022.01); G06V 20/56 (2022.01); H04N 5/76 (2013.01); G06V 20/44 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving first data from a sensor of a target vehicle;
accessing data from an other vehicle,
determining, by a processing device, whether an incident external to the target vehicle has occurred by processing the first data and the data from the other vehicle using a machine learning model;
responsive to determining that an incident external to the target vehicle has occurred, initiating recording of second data by the sensor;
responsive to determining that an incident external to the target vehicle has occurred, taking an action to control the target vehicle;
reconstructing, at a remote processing system, a three-dimensional scene of the incident based at least in part on the second data and the data accessed from the other vehicle.