Systems and methods for aligning crowdsourced sparse map data

Patent metadata

Field	Value
Publication number	US-10365658-B2
Application number	US-201715656470-A
Country	US
Kind code	B2
Filing date	Jul 21, 2017
Priority date	Jul 21, 2016
Publication date	Jul 30, 2019
Grant date	Jul 30, 2019

Abstract

Systems and methods are provided for aligning crowdsourced map data. In one implementation, a method of determining a line representation of a road surface feature extending along a road segment may include receiving a first set of drive data including position information associated with the road surface feature, receiving a second set of drive data including position information associated with the road surface feature, segmenting the first set of drive data into first drive patches and segmenting the second set of drive data into second drive patches, longitudinally aligning the first set of drive data with the second set of drive data within corresponding patches, and determining the line representation of the road surface feature based on the longitudinally aligned first and second drive data in the first and second draft patches.

First claim

What is claimed is:

1. A method of determining a line representation of a road surface feature extending along a road segment, the line representation of the road surface feature being configured for use in autonomous vehicle navigation, the method comprising:
receiving, by a server, a first set of drive data including position information associated with the road surface feature, the position information being determined based on analysis of images of the road segment;
receiving, by a server, a second set of drive data including position information associated with the road surface feature, the position information being determined based on analysis of images of the road segment;
segmenting the first set of drive data into first drive patches and segmenting the second set of drive data into second drive patches;
longitudinally aligning the first set of drive data with the second set of drive data within corresponding patches; and
determining the line representation of the road surface feature based on the longitudinally aligned first and second drive data in the first and second draft patches.

2. The method of claim 1 , wherein the road surface feature includes a road edge or a lane marking.

3. The method of claim 1 , wherein determining the line representation includes an alignment of the line representation with global coordinates based on GPS data acquired as part of at least one of the first set of drive data or the second set of drive data.

4. The method of claim 1 , wherein determining the line representation further includes determining and applying a set of average transformations where each of the average transformations is based on transformations determined that link data from the first set of drive data across sequential patches and the link data from the second set of drive data across sequential patches.

5. The method of claim 1 , further including overlaying the line representation of the road surface feature on at least one geographical image.

6. The method of claim 5 , wherein the geographical image is a satellite image.

7. The method of claim 1 , wherein the first set of data and the second set of data further include position information associated with a plurality of landmarks.

8. A system for determining a line representation of a road surface feature extending along a road segment, the line representation of the road surface feature being configured for use in autonomous vehicle navigation, the system comprising:
at least one processing device configured to:
receive a first set of drive data including position information associated with the road surface feature, the position information being determined based on analysis of images of the road segment;
receive a second set of drive data including position information associated with the road surface feature, the position information being determined based on analysis of images of the road segment;
segment the first set of drive data into first drive patches and segment the second set of drive data into second drive patches;
longitudinally align the first set of drive data with the second set of drive data within corresponding patches; and
determine the line representation of the road surface feature based on the longitudinally aligned first and second drive data in the first and second draft patches.

9. The system of claim 8 , wherein the road surface feature includes a road edge or a lane marking.

10. The system of claim 8 , wherein determining the line representation includes an alignment of the line representation with global coordinates based on GPS data acquired as part of at least one of the first set of drive data or the second set of drive data.

11. The system of claim 8 , wherein determining the line representation further includes determining and applying a set of average transformations where each of the average transformations is based on transformations determined that link data from the first set of drive data across sequential patches and the link data from the second set of drive data across sequential patches.

12. The system of claim 8 , further including overlaying the line representation of the road surface feature on at least one geographical image.

13. The system of claim 8 , wherein the first set of data and the second set of data further include position information associated with a plurality of landmarks.

14. A non-transitory, computer-readable medium storing instructions that, when executed by at least one processing device, cause the device to:
receive a first set of drive data including position information associated with the road surface feature, the position information being determined based on analysis of images of the road segment;
receive a second set of drive data including position information associated with the road surface feature, the position information being determined based on analysis of images of the road segment;
segment the first set of drive data into first drive patches and segmenting the second set of drive data into second drive patches;
longitudinally align the first set of drive data with the second set of drive data within corresponding patches; and
determine the line representation of the road surface feature based on the longitudinally aligned first and second drive data in the first and second draft patches.

15. The non-transitory, computer-readable medium of claim 14 , wherein the road surface feature includes a road edge or a lane marking.

16. The non-transitory, computer-readable medium of claim 14 , wherein determining the line representation includes an alignment of the line representation with global coordinates based on GPS data acquired as part of at least one of the first set of drive data or the second set of drive data.

17. The non-transitory, computer-readable medium of claim 14 , wherein determining the line representation further includes determining and applying a set of average transformations where each of the average transformations is based on transformations determined that link data from the first set of drive data across sequential patches and the link data from the second set of drive data across sequential patches.

18. The non-transitory, computer-readable medium of claim 14 , further including overlaying the line representation of the road surface feature on at least one geographical image.

19. The non-transitory, computer-readable medium of claim 18 , wherein the geographical image is a satellite image.

20. The non-transitory, computer-readable medium of claim 14 , wherein the first set of data and the second set of data further include position information associated with a plurality of landmarks.

Assignees

• Mobileye Vision Technologies Ltd

Inventors

• Fridman Ofer

Classifications

• H04N2013/0081

  Depth or disparity estimation from stereoscopic image signals · CPC title

• H04N13/239

  using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance (H04N13/243 takes precedence) · CPC title

• H04N7/18 Primary

  Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast · CPC title

• G01C21/28

  with correlation of data from several navigational instruments · CPC title

• G06T7/12

  Edge-based segmentation · CPC title