Method for determining object information relating to an object in a vehicle environment, control unit and vehicle

Patent metadata

Field	Value
Publication number	US-12541980-B2
Application number	US-202217821378-A
Country	US
Kind code	B2
Filing date	Aug 22, 2022
Priority date	Mar 9, 2020
Publication date	Feb 3, 2026
Grant date	Feb 3, 2026

Abstract

The disclosure relates to a method for determining object information relating to an object in an environment of a vehicle having a camera. The method includes: capturing the environment with the camera from a first position; changing the position of the camera; capturing the environment with the camera from a second position; determining object information relating to an object by selecting at least one first pixel in the first image and at least one second pixel in the second image, by selecting the first pixel and the second pixel such that they are assigned to the same object point of the object, and determining object coordinates of the assigned object point by triangulation. Changing the position of the camera is brought about by controlling an active actuator system in the vehicle. The actuator system adjusts the camera by an adjustment distance without changing a driving condition of the vehicle.

First claim

What is claimed is:

1 . A method for determining object information of an object in an environment of a vehicle, the vehicle having at least one camera, the at least one camera having a position, the method comprising:
capturing the environment with the at least one camera from a first position and, in dependence thereon, generating a first image having first pixels; changing the position of the at least one camera; capturing the environment with the at least one camera from a second position and, in dependence thereon, creating a second image having second pixels; determining object information relating to the object in the captured environment by
selecting at least one first pixel in the first image and at least one second pixel in the second image, the at least one first pixel and the at least one second pixel being selected such that they are assigned to a same object point of the object in the captured environment, and
determining object coordinates of the assigned object point from first image coordinates of the at least one first pixel and from second image coordinates of the at least one second pixel by triangulation, assuming a base length between the two positions of the camera;
wherein said changing the position of the at least one camera from the first position to the second position is brought about by controlling an active actuator system in the vehicle, wherein the active actuator system adjusts the at least one camera by an adjustment distance without changing a driving condition of the vehicle in all operating conditions of the vehicle including movement and non-movement of the vehicle, wherein an active air suspension system with air springs or a chassis adjustment system is controlled as the active actuator system, wherein by controlling the active air suspension system or the chassis adjustment system, a vehicle body is adjusted in height by the adjustment distance so that the at least one camera fixed to the vehicle body is adjusted indirectly by the adjustment distance to change the position of the at least one camera, and wherein said changing the position of the at least one camera is performed while the vehicle is moving.

2 . The method of claim 1 , wherein the base length between the first position and the second position of the camera is determined from odometry data of the vehicle; and, the odometry data are generated at least depending on the adjustment distance and the odometry data characterize an adjustment of the camera between the first position and the second position.

3 . The method of claim 1 , wherein a camera adjustment system is controlled as the active actuator system; the active actuator system comprises at least one of actuating motors, pneumatic cylinders, hydraulic cylinders, and electric servo cylinders; and, the at least one camera is fixed directly to the camera adjustment system so that when the camera adjustment system is controlled the at least one camera is adjusted by the adjustment distance to change the position of the at least one camera.

4 . The method of claim 1 , wherein a component adjustment system is controlled as the active actuator system, wherein by controlling the component adjustment system, a component of the vehicle is adjusted by the adjustment distance so that the at least one camera attached to this component is adjusted indirectly by the adjustment distance to change the position of the at least one camera.

5 . The method of claim 4 , wherein the component is at least one of a driver's cab and an aerodynamic component.

6 . The method of claim 1 , wherein, when the active actuator system is controlled, the vehicle is in the driving condition in which the vehicle has a vehicle speed which is lower than a threshold speed, or the vehicle is at a standstill.

7 . The method of claim 1 , wherein the object coordinates for a plurality of object points are determined from the first image and the second image by triangulation; and, at least one of an object contour and an object form is determined from the plurality of object points.

8 . The method of claim 7 , wherein the object is divided into object classes via at least one of the object contour and the object form.

9 . The method of claim 1 , wherein a plurality of cameras are provided and object information relating to the object is determined via each camera by adjusting by the corresponding adjustment distance independently of one another.

10 . The method of claim 9 , further comprising plausibility checking the object information determined by the plurality of cameras.

11 . The method of claim 1 , wherein more than two images are acquired at different positions and, from each acquired image, pixels are selected which are assigned to the same object point of the object in the captured environment, wherein the object coordinates of the assigned object point are determined from image coordinates of the selected pixels by triangulation assuming a base length between respective positions of the camera.

12 . The method of claim 1 , wherein a bundle adjustment is carried out via the first image and the second image.

13 . The method of claim 1 , wherein a plurality of first pixels in the first image are combined into a first feature point and a plurality of second pixels in the second image are combined into a second feature point, the first feature point and the second feature point being selected such that they are assigned to a same feature of the object in the captured environment; and,
wherein the object coordinates of the assigned feature are determined from first image coordinates of the first feature point and from second image coordinates of the second feature point by triangulation, assuming a base length between the first position and the second position of the camera.

14 . The method of claim 1 further comprising plausibility checking the determined object information, which follows from an adjustment of the camera by the adjustment distance via the active actuator system with object information which follows from odometry data of the vehicle, wherein the odometry data includes at least one of a wheel speed signal, a vehicle speed, a steering angle, and bending angle.

15 . The method of claim 1 , wherein, when the active actuator system is controlled, the vehicle is in the driving condition in which the vehicle is moving.

16 . A control unit for determining object information of an object in an environment of a vehicle having a camera, the control unit comprising:
a processor; a non-transitory computer readable storage medium having program code stored thereon; said program code being configured to capture the environment with said camera from a first position and, in dependence thereon, generate a first image having first pixels; said program code being configured to change the position of the camera and to capture the environment via the camera from a second position and, in dependence thereon, generate a second image having second pixels; said program code being configured to determine the object information in the captured environment by
selecting at least one first pixel in the first image and at least one second pixel in the second image, the at least one first pixel and the at least one second pixel being selected such that they are assigned to a same object point of the object in the captured environment, and
determining object coordinates of the assigned object point from first image coordinates of the at least one first pixel and from second image coordinates of the at least one second pixel by triangulation assuming a base le

Assignees

• Zf Cv Systems Global Gmbh

Inventors

• Dieckmann Thomas
• Klinger Tobias
• Ricke Janik

Classifications

• G06V2201/07

  Target detection · CPC title

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• G06V10/771

  Feature selection, e.g. selecting representative features from a multi-dimensional feature space · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title