Method, device and storage medium for road slope predicating

Patent metadata

Field	Value
Publication number	US-12299928-B2
Application number	US-202117543978-A
Country	US
Kind code	B2
Filing date	Dec 7, 2021
Priority date	Feb 7, 2021
Publication date	May 13, 2025
Grant date	May 13, 2025

Abstract

A road slope predicting method, a device, and a storage medium are disclosed. The road slope predicting method includes obtaining a road image of a road by a camera, detecting a first image lane line and a second image lane line of the road from the road image, setting a number of road image segmentation points along a road image center line of the first image lane line and the second image lane line respectively by means of the corresponding road image segmentation points, determining the pitch angle of the camera with respect to the road plane at each road space segmentation point; based on the internal and external parameters of the camera and the pitch angle, a space coordinate of each road space segmentation points is calculated in a recursive man. A road model of the road is constructed based on each space coordinate.

First claim

What is claimed is:

1. A road slope predicting method, comprising:
obtaining a road image of a road by a camera installed on or in a vehicle that is currently in motion;
detecting a first image lane line and a second image lane line of the road from the obtained road image by a processor in a device installed on or in the vehicle for road slope, and forming three-dimensional lane lines corresponding to the first image lane line and the second image lane line as the first spatial lane line and the second spatial lane line;
using the processor to set a plurality of road image segmentation points along a road image center line of the first image lane line and the second image lane line and the second image lane line, and divide the road into multiple segments by the road image segmentation points;
using the processor to determine a pitch angle of the camera with respect to the road plane at each road space segmentation point by the road image segmentation points, respectively, each of a plurality of three-dimensional space segmentation points corresponding to these road image segmentation points is referred to as a road space segmentation point, and the pitch angle which is used to indicate the angle between the optical axis of the camera and the road space centerline of the first and second road space lane lines at the road space segmentation point on the road plane;
using the processor to calculate spatial coordinates of each road space segmentation points in a recursive manner based on internal parameters, external parameters and pitch angle of the camera; and
using the processor to construct a road model of the road based on each of the spatial coordinates and obtain a slope angle of the road at an arbitrary position or a corresponding road depth by the road model;
controlling the vehicle to provide assisted driving based on the road model.

2. The method of claim 1 , wherein the step of determining the pitch angle of the camera with respect to the road plane at each road space segmentation point by the road image segmentation points, respectively further comprises:
fitting portions of the first image lane line and the second image lane line within a neighborhood interval of the road image segmentation points into a first straight line and a second straight line, respectively;
determining an intersection of the first straight line and the second straight line as an image vanishing point of the road; and
calculating the pitch angle of the camera with respect to the road plane at the road space division point based on the image coordinates of the image vanishing point.

3. The method of claim 2 , wherein the step of fitting portions of the first image lane line and the second image lane line within a neighborhood interval of the road image segmentation points into the first straight line and the second straight line, respectively comprises:
fitting portions of the first image lane line and the second image lane line within the neighborhood interval of the road image segmentation points into the first straight line and the second straight line, respectively by using a least square method or a random sampling consensus algorithm.

4. The method of claim 2 , wherein the step of calculating the pitch angle of the camera with respect to the road plane at the road space division point based on the image coordinates of the image vanishing point comprises calculating the pitch angle using the following formula:

tan
⁢
θ

=

v
-

c
y

f
y

wherein, θ is the pitch angle to be calculated, (u, v) is the image coordinate of the current image vanishing point, f x , f y , c x , c y are the camera internal parameters.

5. The method of claim 1 , wherein the step of constructing a road model of the road based on each of the spatial coordinates comprises:
an equation for representing a road spatial center line of the road is fitted using a curve fitting method as the road model based on each of spatial coordinates.

6. The method of claim 5 , wherein the curve fitting method comprises polynomial curve fitting or spline curve fitting.

7. The method of claim 1 , wherein the step of calculating spatial coordinates of each road space segmentation points in the recursive manner based on internal parameters, external parameters and pitch angle of the camera comprises solving spatial coordinates of each road spatial segmentation points based on the following equations:

[

u

v

1

]

=

1

z
c

·

[

f
x

0

c
x

0

0

f
y

c
y

0

0

0

1

0

]

·

[

R

T

0

1

]

·

Assignees

• Black Sesame Technologies Inc

Inventors

• Tang Zhiyong
• Peng Jiang
• Zhang Tao

Classifications

• G06T2207/30256

  Lane; Road marking · CPC title

• G06T2207/30244

  Camera pose · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G06T7/536

  from perspective effects, e.g. by using vanishing points · CPC title

• Y02A30/60

  Planning or developing urban green infrastructure · CPC title