US 12,380,710 B2
System and method for deep learning based lane curvature detection from 2D images
Andrei Polzounov, Seattle, WA (US); Vikram Vijayanbabu Appia, San Jose, CA (US); and Ravi Kumar Satzoda, Milpitas, CA (US)
Assigned to Rivian IP Holdings, LLC, Plymouth, MI (US)
Filed by Rivian IP Holdings, LLC, Plymouth, MI (US)
Filed on Feb. 28, 2023, as Appl. No. 18/115,427.
Claims priority of provisional application 63/436,215, filed on Dec. 30, 2022.
Prior Publication US 2024/0221389 A1, Jul. 4, 2024
Int. Cl. G06K 9/00 (2022.01); B60W 50/14 (2020.01); G06T 7/13 (2017.01); G06T 7/64 (2017.01); G06V 10/74 (2022.01); G06V 20/56 (2022.01)
CPC G06V 20/588 (2022.01) [B60W 50/14 (2013.01); G06T 7/13 (2017.01); G06T 7/64 (2017.01); G06V 10/761 (2022.01); G06T 2207/30256 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
detecting, using processing circuitry, an instance of a line in a two-dimensional image captured by a vehicle;
determining, using the processing circuitry, that the instance of the line is a lane boundary for a lane associated with the vehicle;
determining, using the processing circuitry, a curve fit for the lane boundary based on the instance of the line;
determining, using the processing circuitry, a sinuosity of the lane based on the curve fit by dividing a length of the curve fit by a distance of shortest path between a starting point and an ending point of the curve fit; and
facilitating, using the processing circuitry, execution of a vehicle action based on the determined sinuosity.