Systems and methods for localization using surface imaging

Patent metadata

Field	Value
Publication number	US-11100673-B2
Application number	US-201615762378-A
Country	US
Kind code	B2
Filing date	Sep 21, 2016
Priority date	Sep 24, 2015
Publication date	Aug 24, 2021
Grant date	Aug 24, 2021

Abstract

Implementations described and claimed herein provide localization systems and methods using surface imaging. In one implementation, a raw image of a target surface is captured using at least one imager. The raw image is encoded into a template using at least one transform. The template specifies a course direction and an intensity gradient at one or more spatial frequencies of a pattern of the target surface. The template is compared to a subset of reference templates selected from a gallery stored in one or more storage media. A location of the target surface is identified when the template matches a reference template in the subset.

First claim

What is claimed is:

1. A method for localization of a vehicle, the method comprising:
capturing a raw image of a surface structural pattern of a target surface using at least one imager;
encoding the raw image into a template using at least one transform, the template specifying a course direction and an intensity gradient at one or more spatial frequencies of the surface structural pattern of the target surface;
comparing the template to a subset of reference templates selected from a gallery stored in one or more storage media, the gallery obtained when the vehicle is charging using a charging station; and
identifying a location of the target surface when the template matches a reference template in the subset, the location of the target surface corresponding to a current location of the vehicle.

2. The method of claim 1 , further comprising:
updating the gallery by storing the template in the one or more storage media.

3. The method of claim 1 , wherein the subset of reference templates is selected from the gallery based on a previous location of the vehicle.

4. The method of claim 3 , wherein the previous location is determined using one or more previously captured raw images.

5. The method of claim 1 , wherein the template is a binary template encoded based on a set of first order log Gabor feature encoders.

6. The method of claim 1 , wherein the template is aligned to the one or more reference templates using registration optimization.

7. The method of claim 6 , wherein the registration optimization includes at least one of a hamming distance minimization or an application of correlation theorem.

8. A system for localization of a vehicle, the system comprising:
at least one imager mounted on the vehicle and configured to capture a raw image of a surface structural pattern of a target surface along a path of travel of the vehicle;
one or more storage media storing a set of reference templates, the set of reference templates obtained when the vehicle is charging using a charging station, each of the reference templates corresponding to a road surface with a known location; and
at least one processor determining a location of the vehicle by matching a template to one of the reference templates, the template generated by encoding the raw image using at least one transform.

9. The system of claim 8 , wherein the one or more storage media include one or more databases accessible over a network.

10. The system of claim 8 , wherein the set of reference templates is retrieved from a gallery stored in one or more databases over a network.

11. The system of claim 8 , wherein the set of reference templates is received from a charging station.

12. The system of claim 11 , wherein each of the road surfaces is located within a radius of the charging station.

13. The system of claim 8 , further comprising at least one light source time synchronized with the at least one imager and configured to illuminate the target surface.

14. One or more tangible non-transitory computer-readable storage media storing computer-executable instructions for performing a computer process on a computing system, the computer process comprising:
receiving a template from a vehicle over a network, the template encoded from a raw image of a surface structural pattern of a target surface using at least one transform, the raw image captured using at least one imager, the template specifying a course direction and an intensity gradient at one or more spatial frequencies of the surface structural pattern of the target surface;
comparing the template to a subset of reference templates selected from a gallery stored in one or more databases; and
identifying a location of the target surface when the template matches a reference template in the subset.

15. The one or more tangible non-transitory computer-readable storage media of claim 14 , wherein the template is compressed.

16. The one or more tangible non-transitory computer-readable storage media of claim 14 , further comprising:
communicating the location of the target surface to at least one processor of a vehicle.

17. The one or more tangible non-transitory computer-readable storage media of claim 14 , wherein the subset is selected from a previous location.

18. The one or more tangible non-transitory computer-readable storage media of claim 17 , wherein the previous location is determined using one or more previously captured raw image.

19. The one or more tangible non-transitory computer-readable storage media of claim 14 , further comprising:
updating the gallery by storing the template correlated to the location of the target surface in the one or more databases.

Assignees

• Apple Inc

Inventors

• Last Matthew E
• Da Silveira Cabral Ricardo
• Potter Daniel E
• Furgale Paul

Classifications

• G06V10/54

  relating to texture · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• H04N23/56

  provided with illuminating means · CPC title

• G06F18/24133

  Distances to prototypes · CPC title

• G06F18/22

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