Navigating on Images

• US 20110216935A1
• Filed: 03/04/2010
• Published: 09/08/2011
• Est. Priority Date: 03/04/2010
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Mays, Joseph P., Bach, Jeffrey R.
• Granted Patent: US 8,660,316 B2
• Time in Patent Office: Days
• US Class Current: 382/100
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 21/3446 Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
• CPC Class Codes: G01C 21/3602 Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
• CPC Class Codes: G01C 21/3647 Guidance involving output of stored or live camera images or video streams
• CPC Class Codes: G01C 21/3848 Data obtained from both position sensors and additional sensors
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/75 Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries

Abstract

Systems, devices, features, and methods for navigating on images are disclosed. For example, one method includes identifying a point selected on an initial image. An image component, such as a pixel, of the initial image corresponding to the identified point is determined. The image component of the initial image represents an origin. A route from the origin to a destination is generated, and the destination corresponds to another image component, such as another pixel.

Claims

1. A method of routing directly on images, the method comprising:

identifying a point selected on an initial image;

determining an image pixel of the initial image corresponding to the identified point, the image pixel of the initial image representing an origin; and

generating a route from the origin to a destination,

wherein the destination corresponds to another image pixel, and wherein the route comprises a connection between the origin and the destination via intermediate image pixels between the image pixel of the initial image and the other image pixel.

2. The method of claim 1, wherein the other image pixel corresponding to the destination comprises an image pixel of another image.

3. The method of claim 2, wherein the initial image and the other image comprise images of streets or roads.

4. The method of claim 2, wherein the image pixel representing the origin comprises an image pixel corresponding to a ground or floor, and wherein the image pixel representing the destination comprises an image pixel corresponding to a ground or floor.

5. The method of claim 2, wherein the intermediate image pixels correspond to other image pixels in the initial image or the other image.

6. The method of claim 2, wherein at least some of the intermediate image pixels correspond to image pixels of an intermediate image different than the initial image and the other image.

7. The method of claim 2, wherein generating the route comprises determining common geographic features in images from the initial image to the other image to correlate the intermediate image pixels.

8. The method of claim 2, wherein generating the route comprises retrieving correlation data between the origin, destination, and the intermediate image pixels, and wherein the correlation data is obtained based on determining common geographic features in images from the initial image to the other image.

9. The method of claim 8, wherein determining common geographic features includes using scale invariant feature transform.

10. The method of claim 2, further comprising:

identifying a point selected on the other image;

determining an image pixel of the other image corresponding to the identified point of the other image, the image pixel of the other image representing the destination.

11. The method of claim 1, wherein the other image pixel corresponding to the destination comprises another image pixel of the initial image.

12. The method of claim 1, wherein generating the route comprises using a cost factor to determine the intermediate image pixels.

13. The method of claim 1, wherein the intermediate image pixels are designated as navigable pixels.

14. The method of claim 13, wherein the navigable pixels correspond to image pixels associated with a ground or floor.

15. The method of claim 1, wherein the identified point of the initial image is selected via an end user input.

16. A method for developing a navigation system, the method comprising:

identifying image components in a first image, the identified image components in the first image designated as navigable;

identifying image components in a second image, the identified image components in the second image designated as navigable;

generating correlation data associating at least one navigable image component of the first image to at least one navigable image component of the second image; and

storing the correlation data in a hardware medium of the navigation system.

17. The method of claim 16, wherein the identified image components of the first image and the second image correspond to a ground or floor in the respective images.

18. The method of claim 16, further comprising:

comparing the first image and the second image to determine a common geographic feature shared between the first image and the second image, and

wherein generating the correlation data is based on the comparison.

19. The method of claim 16, wherein comparing the first image and the second image to determine the common geographic feature comprises using scale invariant feature transform.

20. The method of claim 16, wherein the first image and the second image comprise street view images.

21. The method of claim 16, wherein the navigation system is configured to provide a route from an origin point associated with a navigable image component on the first image to a destination point via a navigable image component on the second image.

22. A navigation system for routing with images, the system comprising:

an image database including a plurality of images corresponding to geographic areas;

memory including data corresponding to correlations between image pixels of the plurality of images; and

a processor configured to generate a route from an origin point on one of the plurality of images to a destination point on another of the plurality of images based on at least some of the data corresponding to the correlations between the image pixels.

23. A computer-readable medium including computer-executable instructions for performing a method of determining a route between an origin and a destination, the method comprising:

determining a first image pixel corresponding to the origin on a digital image that shows the origin;

determining a second image pixel corresponding to the destination on a digital image that shows the destination; and

determining a route from the origin to a destination via adjacent intermediate image pixels that correspond to a navigable geographic feature shown on a digital image, wherein the navigable geographic feature forms at least part of the route from the origin to the destination.

24. The method of claim 23, wherein the origin and the destination are shown on the same digital image.

25. The method of claim 23, wherein the origin and the destination are shown on different digital images.