KR-20260066496-A - APPARATUS FOR CONTROLLING A VEHICLE, AND METHOD THEREOF

KR20260066496AKR 20260066496 AKR20260066496 AKR 20260066496AKR-20260066496-A

Abstract

The present invention relates to a vehicle control device and a method thereof. A vehicle control method according to an embodiment of the present invention may include a first camera for acquiring a first image within a first field of view range, a second camera for acquiring a second image within a second field of view range, and a processor for recognizing the first and second images to assist in driving a vehicle. The processor predicts the movement of a reference point belonging to a first image captured at a first timing based on vehicle motion information, determines the estimated position of the reference point at a second timing, determines the slope of the road surface around the vehicle based on the deviation between the estimated position and the detected position of the reference point in the first image captured at the second timing, and if the slope of the road surface is above a certain level, corrects the deviation between the first position coordinates of the reference point in the first image and the second position coordinates of the reference point in the second image.

Inventors

송석범
김득현

Assignees

현대자동차주식회사
기아 주식회사

Dates

Publication Date: 20260512
Application Date: 20241104

Claims (20)

A first camera for acquiring a first image of a first field of view range; A second camera for acquiring a second image of a second field of view range; and A processor for recognizing the first and second images to assist in driving a vehicle; comprising The above processor Based on the motion information of the above vehicle, the movement of a reference point belonging to the first image captured at the first timing is predicted, and the estimated position of the reference point at the second timing is determined. Based on the deviation between the estimated position and the detection position of the reference point in the first image captured at the second timing, the slope of the road surface around the vehicle is determined, and A vehicle control device characterized by correcting the deviation between the first position coordinates of the reference point in the first image and the second position coordinates of the reference point in the second image when the slope of the road surface is above a certain level.
In Article 1, The above processor Convert the above first image into a top-view image, and A vehicle control device characterized by determining an arbitrary coordinate in the above top-view image as the reference point.
In Article 1, The behavior information of the above vehicle A vehicle control device characterized by including the yaw rate of the vehicle and the speed of the vehicle.
In Paragraph 3, The above processor A vehicle control device characterized by determining the estimated position based on the above yaw rate-based rotation matrix and the above speed-based translation matrix.
In Article 1, The above processor Count the number of errors in which the deviation between the estimated position and the detection position of the reference point in the first image acquired at the second timing falls within a certain range, and A vehicle control device characterized by determining the slope of the road surface when the number of errors exceeds a threshold count.
In Article 5, The above processor A vehicle control device characterized by reducing the threshold count as the speed of the vehicle decreases.
In Article 1, The above processor A vehicle control device characterized by determining a discrepancy between the first position coordinate and the second position coordinate based on the difference between the height value of the first position coordinate and the height value of the second position coordinate.
In Article 7, The above processor Based on the above first position coordinates, obtain the first normalized coordinates, and Based on the above second position coordinates, second normalized coordinates are obtained, and A vehicle control device characterized by determining a discrepancy between the first position coordinate and the second position coordinate based on a height error between the first actual height of the first world coordinate obtained by converting the first normalized coordinate and the second actual height of the second world coordinate obtained by converting the second normalized coordinate.
In Article 1, The above processor A vehicle control device characterized by determining the correction coordinates of the reference point based on the distance-weighted average between the first position coordinates and the second position coordinates.
In Article 9, The above processor A vehicle control device characterized by determining the third axis coordinate of the correction coordinate based on the distance deviation between the first position coordinate and the second position coordinate in a plane determined by the first axis and the second axis.
A step of predicting the movement of a reference point belonging to the first image captured by the first camera at the first timing based on vehicle motion information, and determining the estimated position of the reference point at the second timing; A step of determining the slope of the road surface around the vehicle based on the deviation between the estimated position and the detection position of the reference point in the first image taken at the second timing; and If the slope of the road surface is above a certain level, a step of correcting the deviation between the first position coordinate of the reference point in the first image and the second position coordinate of the reference point in the second image captured by the second camera to generate corrected coordinates; A vehicle control method including
In Article 11, The step of determining the estimated position of the reference point at the second timing above A step of converting the first image into a top-view image; and A vehicle control method characterized by including the step of determining an arbitrary coordinate in the above top-view image as the reference point.
In Article 11, The behavior information of the above vehicle A vehicle control method characterized by including the yaw rate of the vehicle and the speed of the vehicle.
In Article 13, The step of determining the estimated position of the reference point at the second timing above A vehicle control method characterized by determining the estimated position based on the above yaw rate-based rotation matrix and the above velocity-based translation matrix.
In Article 11, The step of determining the slope of the road surface above A step of counting the number of errors in which the deviation between the estimated position and the detection position of the reference point in the first image acquired at the second timing falls within a certain range; and A vehicle control method characterized by including a step of determining the slope of the road surface when the number of errors exceeds a threshold count.
In Article 15, The step of counting the number of errors mentioned above A vehicle control method characterized by including a step of reducing the threshold count as the speed of the vehicle slows down.
In Article 11, The step of generating the above correction coordinates A vehicle control method characterized by further including a step of determining a discrepancy between the first position coordinate and the second position coordinate based on the difference between the height value of the first position coordinate and the height value of the second position coordinate.
In Article 17, The step of determining the discrepancy between the first position coordinates and the second position coordinates A step of obtaining a first normalized coordinate based on the first position coordinate above; A step of obtaining a second normalized coordinate based on the second position coordinate; and A vehicle control method characterized by including: a step of determining a discrepancy between the first position coordinate and the second position coordinate based on a height error between the first actual height of the first world coordinate obtained by converting the first normalized coordinate and the second actual height of the second world coordinate obtained by converting the second normalized coordinate.
In Article 11, The step of generating the above correction coordinates A vehicle control method characterized by generating a correction coordinate of the reference point based on a distance-weighted average between the first position coordinate and the second position coordinate.
In Article 19, The step of generating the above correction coordinates A vehicle control method characterized by including a step of determining the third axis coordinate of the correction coordinate based on the distance deviation between the first position coordinate and the second position coordinate in a plane determined by the first axis and the second axis.

Description

Apparatus for controlling a vehicle, and method thereof The present invention relates to a vehicle control device and a method thereof, and more specifically, to a technology for determining the slope of a road surface based on an image acquired by a vehicle. An autonomous vehicle refers to a vehicle capable of operating on its own without manipulation by a driver or passengers, while an automated vehicle and highway system refers to a system that monitors and controls such autonomous vehicles to enable them to operate autonomously. Furthermore, technologies are being proposed to assist the driver by monitoring the vehicle's exterior and operating various driving assistance measures based on the monitored external environment. Autonomous vehicles or vehicles equipped with driver assistance systems sometimes utilize methods of learning images of the vehicle's exterior through artificial intelligence as a means of monitoring the vehicle's exterior. For example, images of the vehicle's exterior are acquired using cameras mounted on the vehicle, and the acquired images are used for artificial intelligence learning. Depending on the purpose, the artificial intelligence networks used to learn the images may perform object detection, semantic segmentation, depth map estimation, lane detection, etc. Vehicles sometimes utilize two or more cameras to minimize blind spots when acquiring images of the external environment. During this process, overlapping areas may occur where the field of view of different cameras overlaps. Within these overlapping areas, identical objects should be determined to correspond to the same coordinates; however, if the road surface is sloped, they may be represented by different coordinates from each camera. As such, if the coordinate values acquired by different cameras differ from one another, the accuracy of image recognition is reduced, and errors may occur in autonomous driving or driver assistance systems based on image recognition. FIG. 1 is a diagram showing the configuration of a vehicle control device according to an embodiment of the present invention. Figure 2 is a drawing illustrating an example of camera mounting. FIG. 3 is a flowchart for explaining a vehicle control method according to an embodiment of the present invention. FIG. 4 is a drawing for explaining a method of recognizing a parking space according to an embodiment of the present invention. FIG. 5 is a diagram illustrating the coordinate system used in an embodiment of the present invention. FIG. 6 is a drawing for explaining a method for correcting the location of a parking space according to an embodiment of the present invention. FIG. 7 is a drawing for explaining a method for detecting road surface slope according to an embodiment of the present invention. Figure 8 is a diagram illustrating the procedure for aligning images acquired by cameras. FIG. 9 is a drawing showing a computing system according to one embodiment of the present invention. Hereinafter, embodiments of the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. In describing the embodiments of the present disclosure, detailed descriptions of known configurations or functions are omitted if it is determined that such descriptions could obscure the essence of the present disclosure. Additionally, parts of the drawings unrelated to the description of the present disclosure have been omitted, and similar parts are denoted by similar reference numerals. In the present disclosure, when a component is described as being "connected," "combined," or "joined" with another component, this may include not only a direct connection but also an indirect connection in which another component exists in between. Furthermore, when a component is described as "comprising" or "having" another component, this means that, unless specifically stated otherwise, it does not exclude the other component but may include the other component. In the present disclosure, terms such as first, second, etc. are used solely for the purpose of distinguishing one component from another component and do not limit the order or importance of the components unless specifically stated otherwise. Accordingly, within the scope of the present disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and likewise, a second component in one embodiment may be referred to as a first component in another embodiment. In the present disclosure, distinct components are intended only to clearly describe their respective features and do not imply that the components are separate. That is, multiple components may be integrated to form a single hardware or software unit, or a single component may be distributed to form multiple hard