METHOD, APPARATUS, AND DEVICE FOR DETERMINING LANE LINE ON ROAD

• US 20190205665A1
• Filed: 12/21/2018
• Published: 07/04/2019
• Est. Priority Date: 12/29/2017
• Status: Active Grant

• Current Assignee: Apollo Intelligent Driving Technology Company Limited
• Original Assignee: Baidu Online Network Technology (Beijing) Co., Ltd (Baidu Incorporated)
• Inventors: Duan, Xiong, Zhou, Wang, Yan, Miao, Zhan, Yifei, Ma, Changjie, Lang, Xianpeng, Jin, Yonggang
• Granted Patent: US 10,885,352 B2
• Time in Patent Office: Days
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

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.

Claims

1. A method for determining a lane line on a road, comprising:

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 a plurality of sets of points in different areas of the road;

iteratively executing following operations for at least one time;

selecting a second set of points from the plurality of sets of points based on the reference curve;

generating a second curve by fitting the second set of points,

determining a fitting degree difference between a first fitting degree associated with the reference curve and a second fitting degree associated with the second curve,

determining whether a convergence condition is met at least partially based on the fitting degree difference, and

setting the second curve as the reference curve, in response to failing to meet the convergence condition; and

determining the lane line of the road based on the second set of points when the convergence condition is met.

2. The method according to claim 1, wherein the selecting the second set of points comprises:

selecting the second set of points based on a distance from the plurality of sets of points to the reference curve, to select points in proximity to the reference curve.

3. The method according to claim 1, wherein the selecting the second set of points from the plurality of sets of points further comprises:

acquiring point cloud data associated with the plurality of sets of points in the different areas on the road;

determining laser reflectivities at locations denoted by points in the plurality of sets based on the point cloud data; and

selecting the second 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:

determining a first 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 a second average laser reflectivity associated with the second curve based on the laser reflectivities at the locations denoted by the points for fitting the second curve;

determining a laser reflectivity difference between the first average laser reflectivity and the second 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 second set of points from the plurality of sets of points further comprises:

acquiring an image of the lane line in the different areas of the road;

establishing mapping from locations denoted by points in the plurality of sets to the image; and

selecting the second 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:

determining confidence levels of the points belonging to the lane line based on the mapping of the locations denoted by the points;

determining a first average confidence level associated with the reference curve based on the confidence levels of the points for fitting the reference curve;

determining a second average confidence level associated with the second curve based on the confidence levels of the points for fitting the second curve;

determining a confidence level difference between the first average confidence level and the second 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:

determining the convergence condition being met, in response to a number of iterations reaching a predetermined threshold.

8. The method according to claim 1, wherein the second fitting degree associated with the second curve is determined based on:

determining distances from the second set of points to the second curve;

determining, from the second set of points, a ratio of points, having distances to the second curve smaller than a predetermined distance, to the points in the second set; and

determining the second 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;

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 a plurality of sets of points in different areas of the road;

iteratively executing following operations for at least one time;

selecting a second set of points from the plurality of sets of points based on the reference curve;

generating a second curve by fitting the second set of points,

determining a fitting degree difference between a first fitting degree associated with the reference curve and a second fitting degree associated with the second curve,

determining whether a convergence condition is met at least partially based on the fitting degree difference, and

setting the second curve as the reference curve, in response to failing to meet the convergence condition; and

a lane line determining module configured for determining the lane line of the road based on the second set of points when the convergence condition is met.

10. The apparatus according to claim 9, wherein the selecting the second set of points comprises:

selecting the second set of points based on a distance from the plurality of sets of points to the reference curve, to select points in proximity to the reference curve.

11. The apparatus according to claim 9, wherein the selecting the second set of points from the plurality of sets of points further comprises:

acquiring point cloud data associated with the plurality of sets of points in the different areas of the road;

determining laser reflectivities at locations denoted by points in the plurality of sets based on the point cloud data; and

selecting the second 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:

determining a first 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 a second average laser reflectivity associated with the second curve based on the laser reflectivities at the locations denoted by the points for fitting the second curve;

determining a laser reflectivity difference between the first average laser reflectivity and the second 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.

13. The apparatus according to claim 9, wherein the selecting the second set of points from the plurality of sets of points further comprises:

acquiring an image of the lane line in the different areas of the road;

establishing mapping from locations denoted by points in the plurality of sets to the image; and

selecting the second 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.

14. The apparatus according to claim 13, wherein the determining whether the convergence condition is met comprises:

determining confidence levels of the points belonging to the lane line based on the mapping of the location denoted by the point;

determining a first average confidence level associated with the reference curve based on the confidence levels of the points for fitting the reference curve;

determining a second average confidence level associated with the second curve based on the confidence levels of the points for fitting the second curve;

determining a confidence level difference between the first average confidence level and the second 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.

15. The apparatus according to claim 9, wherein the determining whether the convergence condition is met comprises:

determining the convergence condition being met, in response to a number of iterations reaching a predetermined threshold.

16. The apparatus according to claim 9, wherein the second fitting degree associated with the second curve is determined based on:

determining distances from the second set of points to the second curve;

determining, from the second set of points, a ratio of points, having distances to the second curve smaller than a predetermined distance, to the points in the second set; and

determining the second fitting degree based on a weighted sum of an average distance of the distances and the ratio.

17. A non-transitory computer storage medium, storing a computer program therein, the program, when executed by a processor, causes the processor to perform operations, the operations comprising:

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 a plurality of sets of points in different areas of the road;

iteratively executing following operations for at least one time;

selecting a second set of points from the plurality of sets of points based on the reference curve;

generating a second curve by fitting the second set of points,

determining a fitting degree difference between a first fitting degree associated with the reference curve and a second fitting degree associated with the second curve,

determining whether a convergence condition is met at least partially based on the fitting degree difference, and

setting the second curve as the reference curve, in response to failing to meet the convergence condition; and

determining the lane line of the road based on the second set of points when the convergence condition is met.