US 12,282,846 B2
Method, apparatus, and computer program product for surveillance of road environments via deep learning
Brad Keserich, Eindhoven (NL); and Joshua Michael Finken, Park City, UT (US)
Assigned to HERE GLOBAL B.V., Eindhoven (NL)
Filed by HERE GLOBAL B.V., Eindhoven (NL)
Filed on Dec. 23, 2020, as Appl. No. 17/133,086.
Prior Publication US 2022/0198262 A1, Jun. 23, 2022
Int. Cl. G06N 3/08 (2023.01); G01C 21/00 (2006.01); G06F 16/29 (2019.01); G06N 3/04 (2023.01); G06Q 20/38 (2012.01); G08G 1/01 (2006.01)
CPC G06N 3/08 (2013.01) [G01C 21/3815 (2020.08); G01C 21/3844 (2020.08); G06F 16/29 (2019.01); G06N 3/04 (2013.01); G06Q 20/3821 (2013.01); G08G 1/0129 (2013.01); G06Q 2220/00 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method for surveillance of road environments via deep learning, the computer-implemented method comprising:
determining one or more features for vehicle sensor data associated with one or more vehicles traveling along a road segment proximate to a vehicle, wherein the vehicle comprises one or more sensors that captures the vehicle sensor data;
predicting, using a machine learning model that receives the one or more features, vehicle behavior data associated with the one or more vehicles, wherein the machine learning model is trained for detection of vehicle behavior based on historical vehicle sensor data and one or more rules associated with the road segment;
generating incentive data indicative of a first incentive or a second incentive based on the vehicle behavior data;
encoding the vehicle behavior data onto a first map data layer associated with a database;
encoding the incentive data onto a second map data layer associated with the database to enable provision of the first incentive or the second incentive to an account for a user identity associated with the vehicle; and
causing at least one of routing of the vehicle via an electronic control unit of the vehicle or rendering of data via a map display based on the vehicle behavior data, the incentive data, or a combination of the vehicle behavior data and the incentive data.