Method and apparatus for automatic identification of bodies of water

• US 7,738,707 B2
• Filed: 03/10/2008
• Issued: 06/15/2010
• Est. Priority Date: 07/18/2003
• Status: Active Grant

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Skoblick, Richard, Phurrough, Larry, Wiedemann, Melissa, Gratsch, Colleen Flynn, Lee, Harry C.
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): ZARKA, DAVID PETER
• Application Number:
  US12/073,765
• Publication Number:
  US 20080219506A1
• Time in Patent Office: 827 Days
• Field of Search: 382/190
• US Class Current: 382/190
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 30/2504 Coarse or fine approaches, e.g. resolution of ambiguities or multiscale approaches

Abstract

A method and system for processing image data to identify objects in an image. The method and system operate using various resolutions of the image to identify the objects. Information obtained while processing the image at one resolution is employed when processing the image at another resolution. The method and system identify objects in the image based on the information obtained at the various resolutions of the image.

Claims

1. A method for automatically identifying bodies of water in an image, comprising:

receiving a first image at a first resolution, the first image containing physical bodies of water;

transforming the received first image at the first resolution to a second resolution;

processing said first image at the second resolution according to a first algorithm to produce a second image identifying bodies of water in the first image at said second resolution;

transforming the received first image at the first resolution to a third resolution;

processing said first image at the third resolution according to a second algorithm different from the first algorithm to produce a third image identifying bodies of water in the first image at said third resolution; and

automatically identifying the bodies of water contained in the first image using said produced second image and said produced third image.

2. The method of claim 1, wherein said processing steps each comprise:

delineating the identified bodies of water in the second and third produced images, respectively.

3. The method of claim 1, wherein the step of processing said image at said third resolution comprises:

identifying edges in the first image at said third resolution, wherein edges are areas of the first image which border regions of different intensities;

producing an image identifying parallel edges in the image at said third resolution;

producing a dark image and a bright image from said image identifying parallel edges;

processing the dark and bright images; and

combining the processed dark and bright images to produce said third image.

4. The method of claim 1, wherein the step of processing said image at said second resolution comprises:

removing errors in said first image at said second resolution caused by a detector which captured the first image;

determining a variance of intensity of each pixel in the first image at said second resolution from a mean intensity of pixels surrounding each pixel;

removing pixels which have a variance less than a threshold variance;

labeling contiguous pixels as a unique region;

removing unique regions containing less than a predetermined number of pixels;

calculating a set of features for each remaining unique region; and

determining whether each remaining unique region contains bodies of water using said set of features.

5. The method of claim 4, wherein said set of features comprises:

density change, edge change, edge change percent, edge strength and intensity mean.

6. The method of claim 1, wherein the step of receiving the first image comprises receiving the first image from at least one of an imaging device and a photographic device.

7. The method of claim 1, wherein the first resolution is higher than the second resolution, and the second resolution is higher than the third resolution.

8. The method of claim 1, wherein the step of processing said first image at the second resolution comprises selecting the first algorithm from among a plurality of algorithms based on a condition associated with the first image received at the first resolution, and processing the first image at the second resolution according to the selected first algorithm to produce the second image identifying bodies of water in the first image at the second resolution.

9. The method of claim 8, wherein the condition associated with the first image at the first resolution includes at least one of a geographic location, a terrain type, a ground sample distance, weather, a time of day, temperature, a viewing condition, a band frequency of a sensor, a degree of freedom of the sensor, a viewing angle of the sensor, and a positional vector.

10. The method of claim 1, wherein the step of processing said first image at the third resolution comprises selecting the second algorithm from among a plurality of algorithms different than the first algorithm based on a condition associated with the first image received at the first resolution, and processing the first image at the third resolution according to the selected second algorithm to produce the third image identifying bodies of water in the first image at the third resolution.

11. The method of claim 10, wherein the condition associated with the first image at the second resolution includes at least one of a geographic location, a terrain type, a ground sample distance, weather, a time of day, temperature, a viewing condition, a band frequency of a sensor, a degree of freedom of the sensor, a viewing angle of the sensor, and a positional vector.

12. The method of claim 1, comprising:

outputting signals indicative of the bodies of water detected in the first image on a display device.

13. The method of claim 1, wherein at least one of the steps of transforming the received first image at the first resolution to the second resolution, processing said first image at the second resolution, transforming the received first image at the first resolution to the third resolution, processing said first image at the third resolution, and automatically identifying the bodies of water is performed in a computer processing device.

14. A computer-readable recording medium having a computer program recorded thereon that causes a computer to automatically identify bodies of water in an image, the program causing the computer to perform operations comprising:

receiving a first image at a first resolution, the first image containing bodies of water;

transforming the received first image at the first resolution to a second resolution;

processing the first image at the second resolution according to a first algorithm to produce a second image identifying bodies of water in the first image at the second resolution;

transforming the received first image at the first resolution to a third resolution;

processing the first image at the third resolution according to a second algorithm different from the first algorithm to produce a third image identifying bodies of water in the first image at the third resolution; and

automatically identifying the bodies of water contained in the first image using the produced second image and the produced third image.

15. The computer-readable recording medium of claim 14, wherein the operation of processing the first image at the second resolution comprises delineating the identified bodies of water in the second produced image, and

the operation of processing the first image at the third resolution comprises delineating the identified bodies of water in the third produced image.

16. The computer-readable recording medium of claim 14, wherein the operation of processing the image at the third resolution comprises:

identifying edges in the first image at the third resolution, wherein edges are areas of the first image which border regions of different intensities;

producing an image identifying parallel edges in the image at the third resolution;

producing a dark image and a bright image from the image identifying parallel edges;

processing the dark and bright images; and

combining the processed dark and bright images to produce the third image.

17. The computer-readable recording medium of claim 14, wherein the operation of processing the image at the second resolution comprises:

removing errors in the first image at the second resolution caused by a detector which captured the first image;

determining a variance of intensity of each pixel in the first image at the second resolution from a mean intensity of pixels surrounding each pixel;

removing pixels which have a variance less than a threshold variance;

labeling contiguous pixels as a unique region;

removing unique regions containing less than a predetermined number of pixels;

calculating a set of features for each remaining unique region; and

determining whether each remaining unique region contains bodies of water using the set of features.

18. The computer-readable recording medium of claim 17, wherein the set of features comprises:

density change, edge change, edge change percent;

edge strength and intensity mean.

19. The computer-readable recording medium of claim 14, wherein the operation of receiving the first image comprises receiving the first image from at least one of an imaging device and a photographic device.

20. The computer-readable recording medium of claim 14, wherein the first resolution is higher than the second resolution, and the second resolution is higher than the third resolution.

21. The computer-readable recording medium of claim 14, wherein the operation of processing said first image at the second resolution comprises selecting the first algorithm from among a plurality of algorithms based on a condition associated with the first image received at the first resolution, and processing the first image at the second resolution according to the selected first algorithm to produce the second image identifying bodies of water in the first image at the second resolution.

22. The computer-readable recording medium of claim 21, wherein the condition associated with the first image at the first resolution includes at least one of a geographic location, a terrain type, a ground sample distance, weather, a time of day, temperature, a viewing condition, a band frequency of a sensor, a degree of freedom of the sensor, a viewing angle of the sensor, and a positional vector.

23. The computer-readable recording medium of claim 14, wherein the operation of processing the first image at the third resolution comprises selecting the second algorithm from among a plurality of algorithms different than the first algorithm based on a condition associated with the first image received at the first resolution, and processing the first image at the third resolution according to the selected second algorithm to produce the third image identifying bodies of water in the first image at the third resolution.

24. The computer-readable recording medium of claim 23, wherein the condition associated with the first image at the second resolution includes at least one of a geographic location, a terrain type, a ground sample distance, weather, a time of day, temperature, a viewing condition, a band frequency of a sensor, a degree of freedom of the sensor, a viewing angle of the sensor, and a positional vector.

25. The computer-readable recording medium of claim 14, wherein the program causes the computer to perform an operation of outputting signals indicative of the bodies of water detected in the first image on a display device communicatively connected to the computer.

26. A method for automatically identifying objects in an image, comprising:

receiving a first image at a first resolution, the first image containing objects;

transforming, by a computer processing device, the received first image at the first resolution to a second resolution;

processing, by the computer processing device, said first image at the second resolution according to a first algorithm to produce a second image identifying objects in the first image at said second resolution;

transforming, by the computer processing device, the received first image at the first resolution to a third resolution;

processing, by the computer processing device, said first image at the third resolution according to a second algorithm different from the first algorithm to produce a third image identifying objects in the first image at said third resolution; and

automatically identifying, by the computer processing device, the objects contained in the first image using said produced second image and said produced third image.

27. A computer-readable recording medium having a computer program recorded thereon that causes a computer to automatically identify objects in an image, the program causing the computer to perform operations comprising:

receiving a first image at a first resolution, the first image containing objects;

transforming the received first image at the first resolution to a second resolution;

processing the first image at the second resolution according to a first algorithm to produce a second image identifying objects in the first image at the second resolution;

transforming the received first image at the first resolution to a third resolution;

processing the first image at the third resolution according to a second algorithm different from the first algorithm to produce a third image identifying objects in the first image at the third resolution; and

automatically identifying the objects contained in the first image using the produced second image and the produced third image.