US 12,437,444 B2
Dynamic autocalibration of a vehicle camera system behind a windshield
Aless Lasaruk, Meckenbeuren (DE); and Felix Hachfeld, Lindau (DE)
Assigned to Continental Autonomous Mobility Germany GmbH, Ingolstadt (DE)
Appl. No. 18/718,348
Filed by AUMOVIO Autonomous Mobility Germany GmbH, Ingolstadt (DE)
PCT Filed Nov. 10, 2022, PCT No. PCT/DE2022/200263
§ 371(c)(1), (2) Date Jun. 10, 2024,
PCT Pub. No. WO2023/104254, PCT Pub. Date Jun. 15, 2023.
Claims priority of application No. 10 2021 214 040.8 (DE), filed on Dec. 9, 2021.
Prior Publication US 2025/0139829 A1, May 1, 2025
Int. Cl. G06T 7/80 (2017.01); G06T 7/246 (2017.01); H04N 17/00 (2006.01)
CPC G06T 7/80 (2017.01) [G06T 7/246 (2017.01); H04N 17/002 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/30261 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method for vehicle camera autocalibration during travel of a vehicle, wherein the vehicle camera images a region of surroundings of the vehicle through a window, the method comprising:
a) providing a projection model of the vehicle camera, wherein the projection model comprises, as parameters, multiple extrinsic parameters, at least one intrinsic parameter of the vehicle camera and at least one parameter characterizing the window,
b) capturing a sequence of images by the vehicle camera during cornering by the vehicle,
c) determining a curve type on the basis of current movement of the vehicle during cornering by a curve estimator,
d) estimating the parameters, based on
pixels in the sequence of images corresponding to stationary objects in the surroundings of the vehicle,
the current movement of the vehicle, and
the determined curve type,
by minimizing or reducing an error function indicating a deviation between pixels which correspond to the stationary objects in the surroundings of the vehicle and which are established from the sequence of images and pixels of the stationary objects which are projected by the projection model, and
e) outputting at least one of the estimated parameters.