METHOD, APPARATUS, AND SYSTEM FOR LOCATION CORRECTION BASED ON FEATURE POINT CORRESPONDENCE

• US 20200132472A1
• Filed: 10/26/2018
• Published: 04/30/2020
• Est. Priority Date: 10/26/2018
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: MITTAL, Anish, CHEN, Zhanwei, LAWLOR, David, CHRISTIAN, Peter
• Granted Patent: US 11,215,462 B2
• Time in Patent Office: Days
• CPC Class Codes: G01C 21/005 with correlation of navigation data from several sources, e.g. map or contour matching G01C21/30 takes precedence
• CPC Class Codes: G01C 21/3841 Data obtained from two or more sources, e.g. probe vehicles
• CPC Class Codes: G01C 21/3852 Data derived from aerial or satellite images
• CPC Class Codes: G01C 21/3867 Geometry of map features, e.g. shape points, polygons or for simplified maps
• CPC Class Codes: G01C 21/387 Organisation of map data, e.g. version management or database structures
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 7/74 involving reference images or patches

Abstract

An approach is provided for location correction using feature point correspondences between images or image sources. The approach, for example, involves processing a first image and a second image to identify a feature that is visible in both the first image and the second image. The first image has an image-to-ground correspondence between the feature in the first image and a geographic location. The approach also involves transferring the image-to-ground correspondence from the first image to the second image. The approach further involves using the transferred image-to-ground correspondence to reference the feature in the second image to the geographic location.

Claims

1. A computer-implemented method for location correction of image data comprising:

processing a first image and a second image to identify a feature that is visible in both the first image and the second image, wherein the first image has an image-to-ground correspondence between the feature in the first image and a geographic location;

transferring the image-to-ground correspondence from the first image to the second image; and

using the transferred image-to-ground correspondence to reference the feature in the second image to the geographic location.

2. The method of claim 1, wherein the transferring of the image-to-ground correspondence from the first image to the second image is initiated based on determining that the first image has a location accuracy higher than the second image.

3. The method of claim 1, wherein the first image, the second image, or a combination thereof include top-down imagery, ground-level imagery, or a combination thereof.

4. The method of claim 1, further comprising:

labeling the feature in a plurality of images from a first source of the first image; and

adjusting camera pose information for the first image based on an image-to-image correspondence of the feature among the plurality of images and the image-to-ground correspondence,

wherein the using of the transferred image-to-ground correspondence to reference the feature in the second image to the geographic location is further based on the adjusted camera pose information.

5. The method of claim 4, wherein the feature in the second image is referenced to the geographic location by triangulating the feature in the second image using the adjusted camera pose information.

6. The method of claim 4, further comprising:

labeling the feature in another plurality of images from a second source of the second image; and

adjusting other camera pose information for the second image based another image-to-image correspondence of the feature among the another plurality of images and the transferred image-to-ground correspondence.

7. The method of claim 6, wherein imagery captured using the adjusted other camera pose information is used for vehicle localization, mapping of road features, or a combination thereof.

8. The method of claim 1, wherein the feature is a semantic feature of a road network that is photo-identifiable.

9. The method of claim 1, wherein the semantic feature is a road intersection-related feature.

10. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

process a first image and a second image to identify a feature that is visible in both the first image and the second image, wherein the first image has an image-to-ground correspondence between the feature in the first image and a geographic location;

transfer the image-to-ground correspondence from the first image to the second image; and

use the transferred image-to-ground correspondence to reference the feature in the second image to the geographic location.

11. The apparatus of claim 10, wherein the transferring of the image-to-ground correspondence from the first image to the second image is initiated based on determining that the first image has a location accuracy higher than the second image.

12. The apparatus of claim 10, wherein the first image, the second image, or a combination thereof include top-down imagery, ground-level imagery, or a combination thereof.

13. The apparatus of claim 10, wherein the apparatus is further caused to:

label the feature in a plurality of images from a first source of the first image; and

adjust camera pose information for the first image based on an image-to-image correspondence of the feature among the plurality of images and the image-to-ground correspondence,

wherein the using of the transferred image-to-ground correspondence to reference the feature in the second image to the geographic location is further based on the adjusted camera pose information.

14. The apparatus of claim 13, wherein the feature in the second image is referenced to the geographic location by triangulating the feature in the second image using the adjusted camera pose information.

15. The apparatus of claim 13, wherein the apparatus is further caused to:

label the feature in another plurality of images from a second source of the second image; and

adjust other camera pose information for the second image based another image-to-image correspondence of the feature among the another plurality of images and the transferred image-to-ground correspondence.

16. A non-transitory computer-readable storage medium for determining a ground control point from image data, carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to perform:

processing a first image and a second image to identify a feature that is visible in both the first image and the second image, wherein the first image has an image-to-ground correspondence between the feature in the first image and a geographic location;

transferring the image-to-ground correspondence from the first image to the second image; and

using the transferred image-to-ground correspondence to reference the feature in the second image to the geographic location.

17. The non-transitory computer-readable storage medium of claim 16, wherein the transferring of the image-to-ground correspondence from the first image to the second image is initiated based on determining that the first image has a location accuracy higher than the second image.

18. The non-transitory computer-readable storage medium of claim 16, wherein the first image, the second image, or a combination thereof include top-down imagery, ground-level imagery, or a combination thereof.

19. The non-transitory computer-readable storage medium of claim 16, wherein the apparatus is further caused to perform:

labeling the feature in a plurality of images from a first source of the first image; and

adjusting camera pose information for the first image based on an image-to-image correspondence of the feature among the plurality of images and the image-to-ground correspondence,

wherein the using of the transferred image-to-ground correspondence to reference the feature in the second image to the geographic location is further based on the adjusted camera pose information.

20. The non-transitory computer-readable storage medium of claim 19, wherein the feature in the second image is referenced to the geographic location by triangulating the feature in the second image using the adjusted camera pose information.