Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019032184) ANNOTATION GENERATION FOR AN IMAGE NETWORK
Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

WHAT IS CLAIMED IS:

1. A computer-implemented method of generating annotations in images, the method comprising:

receiving, by a computing system comprising one or more computing devices, image data comprising a plurality of images associated with a plurality of locations, wherein the plurality of images comprises key images comprising one or more key annotations located at one or more key annotation locations in the one or more key images;

selecting, by the computing system, at least one image and a pair of the key images that satisfies one or more annotation criteria based in part on one or more spatial relationships of the plurality of locations associated with the plurality of images;

determining, by the computing system, an annotation location for an annotation in the at least one image based in part on the one or more key annotation locations of the one or more key annotations in the pair of the key images that satisfies the one or more annotation criteria; and

generating, by the computing system, an annotation at the annotation location of the at least one image.

2. The computer-implemented method of claim 1, wherein the one or more spatial relationships comprise one or more threshold distance ranges between the plurality of locations or an adjacency of each of the plurality of locations.

3. The computer-implemented method of any of claims 1 or 2, wherein the determining the annotation location comprises:

determining, by the computing system, epipolar lines associated with the one or more key annotations of the pair of the key images, wherein locations of the epipolar lines are based in part on an optical center of the pair of key images; and

responsive to the epipolar lines satisfying one or more convergence criteria, determining, by the computing system, an epipole for the pair of the key images, the one or more convergence criteria comprising the epipolar lines converging, wherein the annotation location is based in part on the location of the epipole.

4. The computer-implemented method of claim 3, further comprising:

determining, by the computing system, a convergence distance between the epipolar lines; and

responsive to determining that the convergence distance is greater than a threshold convergence distance or that the epipolar lines diverge, determining, by the computing system, that a discontinuity has occurred, wherein at least one of the one or more annotation criteria is based in part on the discontinuity not occurring.

5. The computer-implemented method of any preceding claim, further comprising:

determining, by the computing system, the one or more key images based in part on one or more key image criteria comprising a minimum distance between a set of the plurality of locations or a maximum distance between a set of the plurality of locations.

6. The computer-implemented method of any preceding claim, further comprising:

detecting, by the computing system, one or more visual features in the plurality of images, wherein the one or more visual features comprise a building entranceway, building signage, or a building address marker; and

determining, by the computing system, the one or more key annotation locations of the one or more key annotations based in part on the location of the one or more visual features.

7. The computer-implemented method of any preceding claim, further comprising:

generating, by the computing system, a graph based in part on the plurality of images, the graph comprising a plurality of nodes associated with the plurality of images, locations of the plurality of nodes based in part on the plurality of locations associated with the plurality of images, wherein at least one of the one or more annotation criteria is based in part on a pair of the nodes associated with the pair of the key images being adjacent to a node associated with the at least one image.

8. The computer-implemented method of claim 7, further comprising:

generating, by the computing system, based in part on the graph, a plurality of areas associated with the plurality of nodes, wherein the plurality of areas is separated by one or more partitions based in part on a distance between the plurality of nodes, wherein the one or more spatial relationships are based in part on a shape, size, or relative position of the plurality of areas.

9. The computer-implemented method of claim 8, further comprising:

adding, by the computing system, an additional area to the plurality of areas, wherein the additional area corresponds to an additional image added to the plurality of images, the location of the additional area based in part on an additional location associated with the additional image; and

modifying, by the computing system, the locations of the one or more partitions based in part on a location of the additional location relative to the plurality of locations.

10. The computer-implemented method of any preceding claim, further comprising:

receiving, by the computing system, annotation update data comprising a location for the annotation in the at least one image, wherein the annotation update data is received from a remote computing device or one or more inputs of an input device; and

modifying, by the computing system, the annotation location of the annotation based in part on the annotation update data.

11. One or more tangible non-transitory computer-readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations comprising:

receiving image data comprising a plurality of images associated with a plurality of locations, wherein the plurality of images comprises key images comprising one or more key annotations located at one or more key annotation locations in the one or more key images; selecting at least one image and a pair of the key images that satisfies one or more annotation criteria based in part on one or more spatial relationships of the plurality of locations associated with the plurality of images;

determining an annotation location for an annotation in the at least one image based in part on the one or more key annotation locations of the one or more key annotations in the pair of the key images that satisfies the one or more annotation criteria; and

generating an annotation at the annotation location of the at least one image.

12. The one or more tangible non-transitory computer-readable media of claim 11, wherein the one or more spatial relationships comprise one or more threshold distance ranges between the plurality of locations or an adjacency of each of the plurality of locations.

13. The one or more tangible non-transitory computer-readable media of any of claims 11 or 12, wherein the determining the annotation location comprises:

determining epipolar lines associated with the one or more key annotations of the pair of the key images, wherein locations of the epipolar lines are based in part on an optical center of the pair of key images; and

responsive to the epipolar lines satisfying one or more convergence criteria, determining an epipole for the pair of the key images, the one or more convergence criteria comprising the epipolar lines converging, wherein the annotation location is based in part on the location of the epipole.

14. The one or more tangible non-transitory computer-readable media of claim 13, further comprising:

determining a convergence distance between the epipolar lines; and

responsive to determining that the convergence distance is greater than a threshold convergence distance or that the epipolar lines diverge, determining, that a discontinuity has occurred, wherein at least one of the one or more annotation criteria is based in part on the discontinuity not occurring.

15. The one or more tangible non-transitory computer-readable media of any of claims 11 to 14, further comprising:

determining the one or more key images based in part on one or more key image criteria comprising a minimum distance between a set of the plurality of locations or a maximum distance between a set of the plurality of locations.

16. A computing system comprising:

one or more processors;

one or more non-transitory computer-readable media storing instructions that when executed by the one or more processors cause the one or more processors to perform operations comprising:

receiving image data comprising a plurality of images associated with a plurality of locations, wherein the plurality of images comprises key images comprising one or more key annotations located at one or more key annotation locations in the one or more key images;

selecting at least one image and a pair of the key images that satisfies one or more annotation criteria based in part on one or more spatial relationships of the plurality of locations associated with the plurality of images;

determining an annotation location for an annotation in the at least one image based in part on the one or more key annotation locations of the one or more key annotations in the pair of the key images that satisfies the one or more annotation criteria; and

generating an annotation at the annotation location of the at least one image.

17. The computing system of claim 16, wherein the one or more spatial relationships comprise one or more threshold distance ranges between the plurality of locations or an adjacency of each of the plurality of locations.

18. The computing system of any of claims 16 or 17, wherein the determining the annotation location comprises:

determining epipolar lines associated with the one or more key annotations of the pair of the key images, wherein locations of the epipolar lines are based in part on an optical center of the pair of key images; and

responsive to the epipolar lines satisfying one or more convergence criteria, determining an epipole for the pair of the key images, the one or more convergence criteria comprising the epipolar lines converging, wherein the annotation location is based in part on the location of the epipole.

19. The computing system of claim 18, further comprising:

determining a convergence distance between the epipolar lines; and

responsive to determining that the convergence distance is greater than a threshold convergence distance or that the epipolar lines diverge, determining, that a discontinuity has occurred, wherein at least one of the one or more annotation criteria is based in part on the discontinuity not occurring.

20. The computing system of any of claims 16 to 19, further comprising:

determining the one or more key images based in part on one or more key image criteria comprising a minimum distance between a set of the plurality of locations or a maximum distance between a set of the plurality of locations.

21. A computer program comprising machine-readable instructions which when executed by computing apparatus causes the computing apparatus to perform the method of any of claims 1 to 10.

22. A computing system comprising:

one or more processors;

one or more non-transitory computer-readable media storing instructions that when executed by the one or more processors cause the one or more processors to perform the method of any of claims 1 to 10.