Automatic image object identification using threshold gradient magnitude based on terrain type

• US 8,135,174 B2
• Filed: 09/24/2010
• Issued: 03/13/2012
• Est. Priority Date: 07/18/2003
• Status: Expired due to Fees

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Wiedemann, Melissa, Phurrough, Larry, Gratsch, Colleen Flynn, Skoblick, Richard, Lee, Harry C.
• Primary Examiner(s): ZARKA, DAVID PETER
• Application Number:
  US12/923,502
• Publication Number:
  US 20110085703A1
• Time in Patent Office: 536 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. Terrain types are identified in the image. A second image is generated identifying areas of the image which border regions of different intensities by identifying a gradient magnitude value for each pixel of the image. A filtered image is generated from the second image, the filtered image identifying potential objects which have a smaller radius than the size of a filter and a different brightness than background pixels surrounding the potential objects. The second image and the filtered image are compared to identify potential objects as an object. A potential object is identified as an object if the potential object has a gradient magnitude greater than a threshold gradient magnitude, and the threshold gradient magnitude is based on the terrain type identified in the portion of the image where the potential object is located.

Claims

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

identifying terrain types in the first image;

generating, in a processor of a computer processing device, a second image identifying areas of the first image which border regions of different intensities by identifying a gradient magnitude value for each pixel of the first image;

generating, in the processor, a filtered image from the second image, the filtered image identifying potential objects which have a smaller radius than the size of a filter and a different brightness than background pixels surrounding the potential objects;

comparing, in the processor, the second image and the filtered image to identify potential objects as an object, a potential object is identified as an object if the potential object has a gradient magnitude greater than a threshold gradient magnitude, and the threshold gradient magnitude is based on the terrain type identified in the portion of the first image where the potential object is located.

2. A method for automatically identifying objects in a first image comprising:

identifying terrain types in the first image;

generating, in a processor of a computer processing device, a second image identifying areas of the first image which border regions of different intensities by identifying a gradient magnitude value for each pixel of the first image;

generating, in the processor, a filtered image from the second image, the filtered image identifying potential objects which have a smaller radius than the size of a filter and a different brightness than background pixels surrounding the potential objects;

comparing, in the processor, the second image and the filtered image to identify potential objects as an object, a potential object is identified as an object if the potential object has a gradient magnitude greater than a threshold gradient magnitude, and the threshold gradient magnitude is based on the terrain type identified in the portion of the first image where the potential object is located; and

generating a mean local gradient magnitude image using the second image, wherein the threshold gradient magnitude is determined using the mean local gradient magnitude image.

3. The method of claim 2, wherein the threshold comprises a first threshold based on the mean local gradient magnitude, and a second threshold based on a maximum histogram value of a local gradient magnitude.

4. A method for automatically identifying objects in a first image comprising:

identifying terrain types in the first image;

generating, in a processor of a computer processing device, a second image identifying areas of the first image which border regions of different intensities by identifying a gradient magnitude value for each pixel of the first image;

generating, in the processor, a filtered image from the second image, the filtered image identifying potential objects which have a smaller radius than the size of a filter and a different brightness than background pixels surrounding the potential objects;

comparing, in the processor, the second image and the filtered image to identify potential objects as an object, a potential object is identified as an object if the potential object has a gradient magnitude greater than a threshold gradient magnitude, and the threshold gradient magnitude is based on the terrain type identified in the portion of the first image where the potential object is located,

wherein the step of generating a filtered image comprises;

performing a series of dilations and erosions of the second image to produce a spatially filtered image; and

subtracting said spatially filtered image from the first image to produce the filtered image.

5. The method of claim 4, further comprising:

performing an intensity histogram of the filtered image to produce a maximum intensity value and a minimum intensity value;

generating a minimum brightness value and a maximum brightness value for each terrain type identified in the first image; and

removing portions of the image which are not greater than the maximum intensity value or less than the minimum intensity value, and which are not greater than the minimum brightness value for a particular terrain type for the portion of the first image or less than the maximum brightness value for a particular terrain type for the portion of the first image.

6. A non-transitory computer-readable recording medium having a computer program recorded thereon that causes a computer to identify objects in a first image, the program causing the computer to perform operations comprising:

identifying terrain types in the first image;

generating a second image identifying areas of the first image which border regions of different intensities by identifying a gradient magnitude value for each pixel of the first image;

generating a filtered image from the second image, the filtered image identifying potential objects which have a smaller radius than the size of a filter and a different brightness than background pixels surrounding the potential objects; and

comparing the second image and the filtered image to identify potential objects as an object, a potential object is identified as an object if the potential object has a gradient magnitude greater than a threshold gradient magnitude, and the threshold gradient magnitude is based on the terrain type identified in the portion of the first image where the potential object is located.

7. A non-transitory computer-readable recording medium having a computer program recorded thereon that causes a computer to identify objects in a first image, the program causing the computer to perform operations comprising:

identifying terrain types in the first image;

generating a second image identifying areas of the first image which border regions of different intensities by identifying a gradient magnitude value for each pixel of the first image;

generating a filtered image from the second image, the filtered image identifying potential objects which have a smaller radius than the size of a filter and a different brightness than background pixels surrounding the potential objects;

comparing the second image and the filtered image to identify potential objects as an object, a potential object is identified as an object if the potential object has a gradient magnitude greater than a threshold gradient magnitude, and the threshold gradient magnitude is based on the terrain type identified in the portion of the first image where the potential object is located; and

generating a mean local gradient magnitude image using the second image, wherein the threshold gradient magnitude is determined using the mean local gradient magnitude image.

8. The computer-readable recording medium of claim 7, wherein the threshold comprises a first threshold based on the mean local gradient magnitude, and a second threshold based on a maximum histogram value of a local gradient magnitude.

9. A non-transitory computer-readable recording medium having a computer program recorded thereon that causes a computer to identify objects in a first image, the program causing the computer to perform operations comprising:

identifying terrain types in the first image;

generating a second image identifying areas of the first image which border regions of different intensities by identifying a gradient magnitude value for each pixel of the first image;

generating a filtered image from the second image, the filtered image identifying potential objects which have a smaller radius than the size of a filter and a different brightness than background pixels surrounding the potential objects; and

comparing the second image and the filtered image to identify potential objects as an object, a potential object is identified as an object if the potential object has a gradient magnitude greater than a threshold gradient magnitude, and the threshold gradient magnitude is based on the terrain type identified in the portion of the first image where the potential object is located,

wherein the operation of generating a filtered image comprises;

performing a series of dilations and erosions of the second image to produce a spatially filtered image; and

subtracting said spatially filtered image from the first image to produce the filtered image.

10. The computer-readable recording medium of claim 9, wherein the operations further comprise:

performing an intensity histogram of the filtered image to produce a maximum intensity value and a minimum intensity value;

generating a minimum brightness value and a maximum brightness value for each terrain type identified in the first image; and

removing portions of the first image which are not greater than the maximum intensity value or less than the minimum intensity value, and which are not greater than the minimum brightness value for a particular terrain type for the portion of the first image or less than the maximum brightness value for a particular terrain type for the portion of the first image.