Method and apparatus for automatic identification of objects in an image

• US 7,676,065 B2
• Filed: 10/31/2007
• Issued: 03/09/2010
• 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:
  US11/980,635
• Publication Number:
  US 20080063238A1
• Time in Patent Office: 860 Days
• Field of Search: 382/103
• US Class Current: 382/103
• 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.

Claims

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

receiving a first image formed by data representing physical objects;

generating a second image identifying areas of the first image which border regions of different intensities;

generating a third image identifying portions of the first image having a respective average gradient magnitude greater than a threshold;

processing the second image to produce a fourth image, the fourth image identifying lines in the first image;

segmenting the first image into a plurality of regions, wherein the segmenting is based on the third image and the fourth image;

determining which of the plurality of segmented regions is a background region not containing said objects;

merging adjacent regions which are not background regions; and

identifying the objects in the merged adjacent regions.

2. The method of claim 1 further comprising:

classifying the identified objects.

3. The method of claim 1, wherein the objects include manmade objects, and the step of identifying objects in the merged adjacent regions comprises identifying the manmade objects.

4. The method of claim 1,

wherein the objects include cloud regions, and

wherein the step of identifying the objects in the merged adjacent regions comprises:

identifying the cloud regions; and

refining the identified cloud regions.

5. The method of claim 1, wherein said step of generating a third image comprises:

dividing the first image into a plurality of portions;

determining an average gradient magnitude for each of the plurality of portions; and

calculating a mean gradient magnitude of the first image using the average gradient magnitudes of each of the plurality of portions, wherein the threshold is the mean gradient magnitude of the first image.

6. The method of claim 1, wherein the lines in the fourth image are identified using the identified areas of the first image which border regions of the first image of different intensities.

7. The method of claim 1, wherein at least one of the steps of generating the second image, generating the third image, processing the second image, segmenting the first image, determining the background region, merging the adjacent regions, and identifying the objects is performed in a computer processing device.

8. The method of claim 1, wherein the step of segmenting the first image is based on the second image, in addition to the third image and the fourth image.

9. 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 containing objects;

generating a second image identifying areas of the first image which border regions of different intensities;

generating a third image identifying portions of the first image having a respective average gradient magnitude greater than a threshold;

processing the second image to produce a fourth image, the fourth image identifying lines in the first image;

segmenting the first image into a plurality of regions, wherein the segmenting is based on the third image and fourth image;

determining which of the plurality of segmented regions is a background region not containing said objects;

merging adjacent regions which are not background regions; and

identifying the objects in the merged adjacent regions.

10. The computer readable medium of claim 9, wherein the program causes the computer to perform an operation of:

classifying the identified objects.

11. The computer readable medium of claim 9, wherein the objects include manmade objects, and the operation of identifying objects in the merged adjacent regions comprises identifying the manmade objects.

12. The computer readable medium of claim 9,

wherein the objects include cloud regions, and

wherein the operation of identifying objects in the merged adjacent regions comprises:

identifying the cloud regions; and

refining the identified cloud regions.

13. The computer readable medium of claim 9, wherein said operation of generating a third image comprises:

dividing the first image into a plurality of portions;

determining an average gradient magnitude for each of the plurality of portions; and

calculating a mean gradient magnitude of the first image using the average gradient magnitudes of each of the plurality of portions, wherein the threshold is the mean gradient magnitude of the first image.

14. The computer readable medium of claim 9, wherein the lines in the fourth image are identified using the identified areas of the first image which border regions of the first image of different intensities.

15. The computer readable medium of claim 9, wherein the operation of segmenting is based on the second image, in addition to the third image and the fourth image.