Context-based target recognition

• US 9,086,484 B2
• Filed: 06/30/2011
• Issued: 07/21/2015
• Est. Priority Date: 06/30/2011
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Medasani, Swarup S., Korchev, Dmitriy, Molineros, Jose M., Owechko, Yuri
• Primary Examiner(s): Koziol, Stephen R
• Assistant Examiner(s): Conner, Sean
• Application Number:
  US13/173,891
• Publication Number:
  US 20130004017A1
• Time in Patent Office: 1,482 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G01S 13/9027 Pattern recognition for feature extraction
• CPC Class Codes: G01S 7/412 based on a comparison between measured values and known or stored values
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: G06V 10/768 using context analysis, e.g. recognition aided by known co-occurring patterns

Abstract

A method and apparatus for identifying a target object. A group of objects is identified in an image. The group of objects provides a context for identifying the target object in the image. The target object is searched for in the image using the context provided by the group of objects.

Claims

1. A method for identifying a target object comprising at least one of a road and a building from an image taken using synthetic aperture radar (SAR) data, the method comprising:

generating a mask by;

selecting, using the processor, a first threshold and a second threshold of a plurality of thresholds based on a cumulative histogram for the image, wherein the cumulative histogram plots a level of intensity versus a cumulative percentage of pixels in the image;

selecting, using the processor, a percentage using the cumulative histogram, the percentage being the percentage of pixels that are to be included in a process for identifying a set of bright areas and a number of shadow areas;

using an area detector, executed by the processor, to identify the set of bright areas and the number of shadow areas in the image using the plurality of thresholds, including the first threshold and the second threshold;

identifying bright areas by applying the plurality of thresholds, including the first threshold, to the image to identify a number of binary images in which each pixel in a given binary image has a first set of two values, either a first value indicating that a first intensity for that pixel is less than the first threshold or a second value that indicates that a second intensity for that pixel is greater than the first threshold, wherein the bright areas are pixels that are above the first threshold;

identifying number shadow areas by applying the plurality of thresholds, including the second threshold in the plurality of thresholds, to the image to identify a second number of binary images in which each pixel in a given binary image has a second set of two values, either a third value indicating that the first intensity for that pixel is less than the second threshold or a fourth value that indicates that the second intensity for that pixel is greater than the second threshold, wherein the shadow areas are pixels that are below the second threshold, and wherein the first threshold is greater than the second threshold;

wherein generating the mask is performed by processing the bright areas and the shadow areas to identify which objects in the image may be the target object;

searching, by the processor and using the mask, for the target object within the number of regions.

2. The method of claim 1, wherein searching for the target object in the image further comprises:

responsive to identifying a particular object in the image as the target object, determining whether the particular object is the target object based on a location of the particular object to a group of objects.

3. The method of claim 2, wherein searching for the target further comprises:

searching for the target object in the image using a context provided by the group of objects with a number of agents, wherein an agent in the number of agents is configured to search for the target object within a window for the agent.

4. The method of claim 3, wherein searching for the target object in the image using the context provided by the group of objects comprises:

searching for the target object in the image in a number of regions in the image using a particle-swarm optimization process, wherein the number of regions is identified using the context provided by the group of objects.

5. The method of claim 1, wherein generating the mask further comprises:

identifying a set of lines in the image and processing the set of lines along with the bright areas and the shadow areas.

6. The method of claim 1 wherein generating the mask further comprises:

prior to selecting the first and second thresholds, processing the SAR data to reduce noise present in the image.

8. The method of claim 1 further comprising:

prior to identifying the group of objects, preprocessing the image to reduce noise in the image.

9. The method of claim 1, wherein the context further includes additional information obtained from sources other than the image.

10. The method of claim 9, wherein the additional information is selected from the group consisting of:

intelligence information, mission details, and weather data.

11. The method of claim 1, wherein the number of masks is selected from the group consisting of a building mask, a vegetation mask, and a road mask.

12. The method of claim 11, wherein the number of masks comprises all of the building mask, the vegetation mask, and the road mask.

13. The method of claim 1, wherein the plurality of thresholds is a plurality of thresholds, and wherein other thresholds within the plurality of thresholds are selected by substantially equally dividing an interval between the first threshold and a highest level of intensity in the image by a total of the plurality of thresholds.

7. An apparatus for identifying a target object comprising at least one of a road and a building from an image taken using synthetic aperture radar (SAR) data, the apparatus comprising:

a processor configured to generate a mask, the processor being specifically configured to;

select, using the processor, a first threshold and a second threshold of a plurality of thresholds based on a cumulative histogram for the image, wherein the cumulative histogram plots a level of intensity versus a cumulative percentage of pixels in the image;

select, using the processor, a percentage using the cumulative histogram, the percentage being the percentage of pixels that are to be included in a process for identifying a set of bright areas and a number of shadow areas;

use an area detector, executed by the processor, to identify the set of bright areas and the number of shadow areas in the image using the plurality of thresholds, including the first threshold and the second threshold;

identify bright areas by applying the plurality of thresholds, including the first threshold, to the image to identify a number of binary images in which each pixel in a given binary image has a first set of two values, either a first value indicating that a first intensity for that pixel is less than the first threshold or a second value that indicates that a second intensity for that pixel is greater than the first threshold, wherein the bright areas are pixels that are above the first threshold;

identify number shadow areas by applying the plurality of thresholds, including the second threshold in the plurality of thresholds, to the image to identify a second number of binary images in which each pixel in a given binary image has a second set of two values, either a third value indicating that the first intensity for that pixel is less than the second threshold or a fourth value that indicates that the second intensity for that pixel is greater than the second threshold, wherein the shadow areas are pixels that are below the second threshold, and wherein the first threshold is greater than the second threshold;

wherein generating the mask is performed by processing the bright areas and the shadow areas to identify which objects in the image may be the target object;

the processor further configured to search, using the mask, for the target object within the number of regions.