System and method for airport mapping database automatic change detection

• US 20100092045A1
• Filed: 10/15/2008
• Published: 04/15/2010
• Est. Priority Date: 10/15/2008
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Zimmer, Nico, Lugsch, William G., Ravenscroft, Donald L.
• Granted Patent: US 8,144,937 B2
• Time in Patent Office: Days
• US Class Current: 382/113
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06V 20/13 Satellite images

Abstract

A method for automatically updating a graphical information system (GIS) type database using aerial imagery. The method may involve processing a new image to identify at least one target region therewithin; analyzing the target region to determine image invariant moments thereof; using feature vector data to generate a template of a target feature from an old image; analyzing the template to generate image invariant moments thereof; and comparing the image invariant moments of the target region with the image invariant moments of the template to identify a feature change between the target region and the template.

Claims

1. A method for automatically updating a graphical information system (GIS) type database using aerial imagery, the method comprising:

processing a new image to identify at least one target region therewithin;

analyzing said target region to determine image invariant moments thereof;

using feature vector data to generate a template of a target feature from an old image;

analyzing said template to generate image invariant moments thereof; and

comparing said image invariant moments of said target region with said image invariant moments of said template to identify a feature change between said target region and said template.

2. The method of claim 1, wherein said comparing said image invariant moments of said target region with said image invariant moments of said template to identify a feature change comprises identifying a feature vector change, from which a feature raster change between said target region and said template is produced.

3. The method of claim 1, wherein said comparing said image invariant moments of said target region with said image invariant moments of said template to identify said feature vector change between said target region and said template comprises determining a similarity measurement that assists in identifying said feature vector change.

4. The method of claim 3, wherein said determining a similarity measurement comprises determining a Euclidean distance between the two image invariant moments.

5. The method of claim 2, wherein said comparing said image invariant moments of said target region and said image invariant moments of said template comprises applying a rule set to assist in identifying said feature vector change.

6. The method of claim 2, further comprising updating said database to include said identified feature raster change.

7. The method of claim 1, wherein said processing a new image to identify at least one target region therewithin comprises using image invariant moments to describe a shape of said target feature, and separating said target feature from a remainder of said new image.

8. The method of claim 1, wherein:

said processing a new image comprises processing a new satellite image; and

wherein said generating a template of a target feature from an old image comprises generating a template of a target feature from an old satellite image.

9. The method of claim 2, further comprising making a visual inspection of said new and old images to confirm said feature raster change.

10. The method of claim 1, further comprising storing said template in a database prior to comparing said image invariant moments of said template and said target feature.

11. A method for automatically updating an airport mapping database (AMDB) using satellite imagery, the method comprising:

processing a new satellite image to identify at least one target region therewithin;

analyzing said target region to determine image invariant moments thereof;

using feature vector data to generate a template of a target feature from an old image, said template generally corresponding to said target region;

analyzing said template to generate image invariant moments thereof;

comparing said image invariant moments of said target region with said image invariant moments of said template to identify a feature raster change between said target region and said template; and

updating said AMBD with a feature vector change representative of said feature raster change.

12. The method of claim 11, wherein said comparing said image invariant moments of said target region with said image invariant moments of said template to identify a feature raster change between said target region and said template comprises determining a similarity measurement that assists in identifying said feature raster change.

13. The method of claim 12, wherein said determining a similarity measurement comprises determining a Euclidean distance between the two image invariant moments.

14. The method of claim 11, wherein said comparing said image invariant moments of said target region and said image invariant moments of said template comprises applying a rule set to assist in identifying said feature raster change.

15. The method of claim 11, further comprising making a visual inspection of said new and old satellite images to confirm said feature raster change.

16. The method of claim 11, further comprising storing said template in a database prior to comparing said image invariant moments of said template and said target feature.

17. The method of claim 11, wherein said processing a new satellite image to identify at least one target region therewithin comprises processing a new satellite image to separate at least one target region from a background region.

18. A system for automatically updating a graphical information system (GIS) type database using remote sensing imagery, the system comprising:

a database for storing vector data relating to a geographic region and features present within said geographic region;

a pre-processing system for receiving a new image and identifying a target region therewithin;

a processing system for obtaining feature vector data from said database and generating a template from an old image taken previous in time to said new image, said template representing a target feature being generally related in shape to said target region;

an image invariant moment analyzing system for generating image invariant moments of said target region and said template;

a comparison system that compares said image invariant moments of said target region with said image invariant moments of said template and identifies feature changes between said target region and said template.

19. The system of claim 18, wherein said graphical information type database comprises an airport mapping database (AMDB).

20. The system of claim 18, wherein said new and old images each comprise satellite images.