Method, apparatus, and device for determining lane line on road

Patent metadata

Field	Value
Publication number	US-10885352-B2
Application number	US-201816231015-A
Country	US
Kind code	B2
Filing date	Dec 21, 2018
Priority date	Dec 29, 2017
Publication date	Jan 5, 2021
Grant date	Jan 5, 2021

Abstract

The disclosure relates to a method, apparatus, device, and computer readable storage medium for determining a lane line on a road. The method includes: acquiring a first curve as a reference curve, the first curve being obtained by fitting a first set of points selected from sets of points in different areas of the road; iteratively executing operations: selecting a second set of points from the sets of points based on the reference curve; generating a second curve by fitting the second set of points, determining a difference between a fitting degree associated with the reference curve and a fitting degree associated with the second curve, determining whether a convergence condition is met based on the difference, and setting the second curve as the reference curve if not met and determining the lane line of the road based on the second set of points if met.

First claim

What is claimed is:

1. A method for determining a lane line on a road, comprising the steps of:
acquiring a first curve, and using the first curve as a reference curve, the first curve being obtained by fitting a first set of points, and the first set of points being selected from points in different areas of the road;
setting a value of i as 2;
executing following steps a) to d):
step a): selecting an i th set of points from the points in the different areas of the road based on the reference curve,
step b): generating an i th curve by fitting the i th set of points,
step c): determining a fitting degree difference between an (i−1) th fitting degree associated with the reference curve and an i th fitting degree associated with the i th curve,
step d) determining whether a convergence condition is met at least partially based on the fitting degree difference;

in response to failing to meet the convergence condition: setting the generated i th curve as the reference curve, increasing i by 1, and executing steps a) to d); and
determining the lane line of the road based on the i th set of points when the convergence condition is met.

2. The method according to claim 1 , wherein the selecting the i th set of points comprises:
selecting the i th set of points based on a distance from the points in the different areas of the road to the reference curve, to select points in proximity to the reference curve.

3. The method according to claim 1 , wherein the selecting the i th set of points from the points in the different areas of the road further comprises:
acquiring point cloud data associated with the points in the different areas on the road;
determining laser reflectivities at locations denoted by the points in the different areas of the road based on the point cloud data; and
selecting the i th set of points based on the laser reflectivities and the reference curve, to select points in proximity to the reference curve and having high laser reflectivities.

4. The method according to claim 3 , wherein the determining whether the convergence condition is met comprises the steps of:
determining an (i−1) th average laser reflectivity associated with the reference curve based on the laser reflectivities at the locations denoted by the points for fitting the reference curve;
determining an i th average laser reflectivity associated with the i th curve based on the laser reflectivities at the locations denoted by the points for fitting the i th curve;
determining a laser reflectivity difference between the (i−1) th average laser reflectivity and the i th average laser reflectivity; and
determining the convergence condition being met, in response to a weighted sum of the laser reflectivity difference and the fitting degree difference being smaller than a predetermined threshold.

5. The method according to claim 1 , wherein the selecting the i th set of points from the plurality of sets of points further comprises the steps of:
acquiring an image of the lane line in the different areas of the road;
establishing mapping from locations denoted by the points in the different areas of the road to the image; and
selecting the i th set of points based on the mapping and the reference curve, to select points in proximity to the reference curve and corresponding to locations in proximity to or on the lane line in the image.

6. The method according to claim 5 , wherein the determining whether the convergence condition is met comprises the steps of:
determining confidence levels of the points belonging to the lane line based on the mapping of the locations denoted by the points in the different areas of the road;
determining an (i−1) th average confidence level associated with the reference curve based on the confidence levels of the points for fitting the reference curve;
determining an i th average confidence level associated with the i th curve based on the confidence levels of the points for fitting the i th curve;
determining a confidence level difference between the (i−1) th average confidence level and the i th average confidence level; and
determining the convergence condition being met, in response to a weighted sum of the confidence level difference and the fitting degree difference being smaller than a predetermined threshold.

7. The method according to claim 1 , wherein the determining whether the convergence condition is met comprises the steps of:
determining the convergence condition being met, in response to i being greater than a predetermined threshold.

8. The method according to claim 1 , wherein the i th fitting degree associated with the i th curve is determined based on:
determining distances from the i th set of points to the i th curve;
determining, from the i th set of points, a ratio of points, having distances to the i th curve smaller than a predetermined distance, to the points in the i th set; and
determining the i th fitting degree based on a weighted sum of an average distance of the distances and the ratio.

9. An apparatus for determining a lane line on a road, comprising:
at least one processor; and
a memory storing instructions, wherein the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising the steps of:
acquiring a first curve, and using the first curve as a reference curve, the first curve being obtained by fitting a first set of points, and the first set of points being selected from points in different areas of the road;
setting a value of i as 2;
executing following steps a) to d):
step a): selecting an i th set of points from the points in different areas of the road based on the reference curve,
step b): generating an i th curve by fitting the i th set of points,
step c): determining a fitting degree difference between an (i−1) th fitting degree associated with the reference curve and an i th fitting degree associated with the i th curve, and
step d): determining whether a convergence condition is met at least partially based on the fitting degree difference;

in response to failing to meet the convergence condition: setting the generated i th curve as the reference curve, increasing i by l, and executing steps a) to d); and
determining the lane line of the road based on the i th set of points when the convergence condition is met.

10. The apparatus according to claim 9 , wherein the selecting the i th set of points comprises:
selecting the i th set of points based on a distance from the points in the different areas of the road to the reference curve, to select points in proximity to the reference curve.

11. The apparatus according to claim 9 , wherein the selecting the i th set of points from the points in the different areas of the road further comprises the steps of:
acquiring point cloud data associated with the points in the different areas of the road;
determining laser reflectivities at locations denoted by the points in the different areas of the road based on the point cloud data; and
selecting the i th set of points based on the laser reflectivities and the reference curve, to select points in proximity to the reference curve and having high laser reflectivities.

12. The apparatus according to claim 11 , wherein the determining whether the convergence condition is met comprises the steps of:
determining an (i−1) th average laser reflectivity associated with the reference curve based on the laser reflectivities at the locations denoted by the points for fitting the reference curve;
determining an i th average laser reflectivity associated with t

Assignees

• Baidu online network technology beijing co ltd

Inventors

• Duan Xiong
• Zhou Wang
• Yan Miao
• Zhan Yifei
• Ma Changjie
• Lang Xianpeng
• Jin Yonggang

Classifications

• G06V20/588 Primary

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G01S17/88

  Lidar systems specially adapted for specific applications · CPC title

• G06T2207/30256

  Lane; Road marking · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title