Context-based target recognition
First Claim
Patent Images
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.
1 Assignment
0 Petitions
Accused Products
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.
25 Citations
13 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. - View Dependent Claims (2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13)
-
-
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.
-
Specification