IP Library › Granted Patent US 12694546
Granted Patent B2
US 12694546 · App. 18/566,408 · Granted Jul 28, 2026

Method and system for correcting a position of at least one feature in the surroundings of an ego vehicle

Inventor: Peter Barth (Wolnzach, DE)
Assignee: Continental Autonomous Mobility Germany GmbH
G06T7/50G06F17/17G06T7/73G06V10/80G06T2207/10028G06T2207/30252
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12694546
App. No.
18/566,408
Granted
Jul 28, 2026
Kind
B2
Abstract

A method for correcting a position of at least one feature in the surroundings of an ego vehicle by means of a fusion of data from at least a first and a second surroundings detection sensor, including: recording the surroundings of the ego vehicle using the first surroundings detection sensor and generating a first representation of the surroundings; recording the surroundings of the ego vehicle using the second surroundings detection sensor and generating a second representation of the surroundings; detecting at least one feature in the first representation of the surroundings; determining the position of the at least one feature based on the first representation of the surroundings; determining a height profile in an area in front of the ego vehicle based on the second representation of the surroundings; fusing the position of the at least one detected feature and the determined height profile and determining a corrected position; and correcting the position of the at least one feature based on the determined corrected position.

Claims (12)

1 . A method for correcting a position of at least one feature in surroundings of an ego vehicle by means of a fusion of data from at least a first surroundings detection sensor and a second surroundings detection sensor, the method comprising:

recording the surroundings of the ego vehicle using the first surroundings detection sensor;

generating a first representation of the surroundings based on the surroundings of the ego vehicle recorded using the first surroundings detection sensor;

recording the surroundings of the ego vehicle using the second surroundings detection sensor;

generating a second representation of the surroundings based on the surroundings of the ego vehicle recorded using the second surroundings detection sensor;

detecting a feature in the first representation of the surroundings;

determining a position of the feature based on the first representation of the surroundings;

determining a height profile in an area in front of the ego vehicle based on the second representation of the surroundings; and

determining a corrected position based on the feature and the height profile, wherein determining of the corrected position is accomplished by intersecting a line of sight of the first surroundings detection sensor with the height profile.

2 . The method according to claim 1 , further comprising outputting the position of the feature in a flat world assumption in x- and y-coordinates in the first representation of the surroundings.

3 . The method according to claim 1 , wherein determining the height profile comprises applying a regression method to the height profile.

4 . The method according to claim 3 , wherein applying the regression method comprises applying a least squares method to the height profile.