Detecting Common Geographic Features in Images Based on Invariant Components

• US 20100328462A1
• Filed: 06/24/2009
• Published: 12/30/2010
• Est. Priority Date: 06/24/2009
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Chen, Xin
• Granted Patent: US 9,129,163 B2
• Time in Patent Office: Days
• US Class Current: 348/148
• CPC Class Codes: G01B 11/022 by means of tv-camera scanning
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01C 21/3815 Road data
• CPC Class Codes: G01C 21/3837 Data obtained from a single source
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06T 17/05 Geographic models
• CPC Class Codes: G06V 20/582 of traffic signs
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

Systems, devices, features, and methods for detecting common geographic features in images, such as, for example, to develop a navigation database are disclosed. For example, a method of detecting a common text pattern, such as for a road or path sign, from collected images includes collecting a plurality of images of geographic areas along a road or path. An image of the plurality of images is selected. Components that correspond to an object about the road or path in the selected image are determined. In one embodiment, the determined components are independent or invariant to scale of the object. The determined components are compared to reference components in a data library. If the determined components substantially match the reference components, the object in the selected image is identified to be a common pattern, such as for a standard road or path sign, corresponding to the reference components in the data library.

Claims

1. A method of detecting a common road sign from collected images to develop a master navigation database, the method comprising:

collecting a plurality of images of geographic areas along a road;

selecting an image of the plurality of images;

determining components that correspond to an object about the road in the selected image, the determined components being independent to scale of the object;

comparing the determined components to reference components in a data library;

if, based on the comparison, the determined components substantially meet a matching threshold with the reference components, identifying the object in the selected image to be a common text pattern of a common road sign corresponding to the reference components in the data library; and

developing a master navigation database based on identifying the object in the selected image to be the common text pattern of the common road sign.

2. The method of claim 1, wherein the common text pattern comprises letters spelling SPEED LIMIT or STOP.

3. The method of claim 1, wherein the determined components are substantially independent to brightness of the object.

4. The method of claim 1, wherein the determined components are substantially independent to rotation of the object.

5. The method of claim 1, further comprising:

identifying a desired common road sign text pattern in a reference image of the plurality of images;

determining the reference components that represent the desired common road sign text pattern in the reference image, the reference components being independent to scale and to rotation of the desired common road sign text pattern; and

storing the reference components in the data library.

6. The method of claim 1, wherein determining the components that correspond to the object about the road comprises using a scale-invariant feature transform.

7. The method of claim 1, wherein determining the components that correspond to the object comprises:

determining components that are independent to scale for the entire selected image;

identifying the determined components that correspond to the object in an area about the road based on clustering; and

filtering out the components not part of the identified cluster.

8. A method of detecting a standard road object in an image, the method comprising:

capturing a plurality of images along roads, the plurality of images captured via a camera mounted on a vehicle;

determining scale-invariant features of each of the plurality of images, the scale-invariant features determined as a function of a scale-invariant feature transform;

comparing the determined scale-invariant features with reference scale-invariant features to determine whether a desired road object is included in at least one of the plurality of images, the reference invariant features corresponding to the desired road object; and

identifying at least one of the plurality of images determined to include the desired road object as a function of the comparison between the determined scale-invariant features and the reference scale-invariant features, the desired road object including a standard label pattern.

9. The method of claim 8, wherein the desired road object comprises a speed limit sign.

10. The method of claim 8, wherein the desired road object comprises a stop sign.

11. The method of claim 8, wherein the reference scale-invariant features correspond to different points along text of the standard label pattern.

12. The method of claim 8, wherein the determined scale-invariant features comprise amplitude extrema points.

13. The method of claim 8, wherein the determined scale-invariant features comprise gradient vectors.

14. The method of claim 8, further comprising:

developing a navigation database based on identifying the at least one of the plurality of images determined to include the desired road object.

15. A computer-readable medium configured to store a computer program that performs a method of identifying a commonly labeled path sign in an image corresponding to a path, the method comprising:

identifying a standard path sign in an image of a path;

determining data components that correspond to the standard path sign, the data components being scale-invariant components representing a text pattern of the standard path sign;

storing the data components that correspond to the standard path sign in a navigation library of a map database developer;

selecting another image representing another path;

determining scale-invariant components of the other image;

comparing the determined scale-invariant components of the other image with the data components stored in the navigation library to determine if the other image includes a path sign substantially similar to the standard path sign.

16. The method of claim 15, wherein the standard path sign comprises a speed limit sign or a stop sign.

17. The method of claim 15, wherein determining the scale-invariant components of the standard path sign comprises determining amplitude extrema in regions of a difference image, the difference image comprising an image generated from a difference between the image of the path and a blurred image of the path.

18. The method of claim 15, wherein the data components being substantially invariant to rotation.

19. The method of claim 15, wherein the data components being substantially invariant to illumination.

20. The method of claim 15, further comprising:

if the determined scale-invariant components substantially match the data components in the navigation library, providing identification of the selected other image to the map database developer.

21. The method of claim 20, wherein providing the identification includes providing a text file.

22. The method of claim 21, wherein the text file includes location information of where the selected other image was taken.