Shape-based object detection and localization system

• US 8,437,556 B1
• Filed: 10/21/2009
• Issued: 05/07/2013
• Est. Priority Date: 02/26/2008
• Status: Expired due to Fees

• Current Assignee: HRL Laboratories LLC (The Boeing Co.)
• Original Assignee: HRL Laboratories LLC (The Boeing Co.)
• Inventors: Saisan, Payam
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US12/589,483
• Time in Patent Office: 1,294 Days
• Field of Search: 382/103, 382/199, 382/209, 382/224, 382/100
• US Class Current: 382/224
• CPC Class Codes: G06F 18/2135 based on approximation criteria, e.g. principal component analysis
• CPC Class Codes: G06F 18/2433 Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/30112 Baggage; Luggage; Suitcase
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/7715 Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
• CPC Class Codes: G06V 2201/05 Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

Described is a system for identifying a concealed object of interest. The system is initialized by receiving an image in grayscale. The image is processed image to identify feature rich regions, which are identified as a binary mask describing edge pixels and non-edge pixels. A set of edge pixels are then randomly sampled. An object detector function is then used on the set of edge pixels to determine if an object of interest is present in the set of edge pixels.

Claims

1. A computer implemented method for identifying a concealed object of interest, comprising an act of causing a computer having a processor and a memory module encoded with instruction means that are executable by the processor to execute the instruction means and cause the processor to perform acts of:

receiving an image in grayscale;

processing the image to identify feature rich regions which are identified as a binary mask describing edge pixels and non-edge pixels;

randomly sampling a set of edge pixels; and

determining if an object of interest is present in the set of edge pixels.

2. A method as set forth in claim 1, wherein the act of processing the image further comprises acts of:

identifying all edges in the image using an edge detector, which results in a binary image; and

using a threshold to constrain the binary mask to describe edge pixels and non-edge pixels as a binary, two-class classification.

3. A method as set forth in claim 2, wherein the act of determining if an object of interest is present in the set of edge pixels, further comprises acts of:

cropping out a region of interest window centered around a selected edge pixel;

performing an edge preserving non-linear diffusion on the region of interest window to increase saliency of edges of a potential object of interest,

forming a background and a foreground in the region of interest window;

segmenting the background from the foreground;

extracting pixel information for the foreground, the pixel information having dimensional coordinates for each pixel in the foreground;

fitting two best fit ellipsoids to the pixel information, each ellipsoid having a major and minor axis, the two best fit ellipsoids being fit to the pixel information such that there exists an intersection between the major axis of the two ellipsoids;

extracting the two major axes from the two ellipsoids;

aligning the two major axes with the a known two-axis model representing an object of interest;

determining a distance measurement between the two major axes and the known two-axis model; and

identifying the object as an object of interest if the distance measurement is below a predetermined threshold.

4. A method as set forth in claim 1, wherein the act of determining if an object of interest is present in the set of edge pixels, further comprises acts of:

cropping out a region of interest window centered around a selected edge pixel;

performing an edge preserving non-linear diffusion on the region of interest window to increase saliency of edges of a potential object of interest,

forming a background and a foreground in the region of interest window;

segmenting the background from the foreground;

extracting pixel information for the foreground, the pixel information having dimensional coordinates for each pixel in the foreground;

fitting two best fit ellipsoids to the pixel information, each ellipsoid having a major and minor axis, the two best fit ellipsoids being fit to the pixel information such that there exists an intersection between the major axis of the two ellipsoids;

extracting the two major axes from the two ellipsoids;

aligning the two major axes with the a known two-axis model representing, an object of interest;

determining a distance measurement between the two major axes and the known two-axis model; and

identifying the object as an object of interest if the distance measurement is below a predetermined threshold.

5. A computer program product for identifying a concealed object of interest, the computer program product comprising computer-readable instruction means stored on a non-transitory computer-readable medium that are executable by a computer thr causing the computer to perform operations of:

receiving an image in grayscale;

processing the image to identify feature rich regions which are identified as a binary mask describing edge pixels and non-edge pixels;

randomly sampling, a set of edge pixels; and

determining if an object of interest is present in the set of edge pixels.

6. A computer program product as set forth in claim 5, wherein the operation of processing the image further comprises acts of:

identifying all edges in the image using an edge detector, which results in a binary image; and

using a threshold to constrain the binary mask to describe edge pixels and non-edge pixels as a binary, two-class classification.

7. A computer program product as set forth in claim 6, wherein the operation of determining if an object of interest is present in the set of edge pixels, further comprises operations of:

cropping out a region of interest window centered around a selected edge pixel;

performing an edge preserving non-linear diffusion on the region of interest window to increase saliency of edges of a potential object of interest,

forming a background and a foreground in the region of interest window;

segmenting the background from the foreground;

extracting pixel information for the foreground, the pixel information having dimensional coordinates for each pixel in the foreground;

fitting two best fit ellipsoids to the pixel information, each ellipsoid having a major and minor axis, the two best fit ellipsoids being fit to the pixel information such that there exists an intersection between the major axis of the two ellipsoids;

extracting the two major axes from the two ellipsoids;

aligning the two major axes with the a known two-axis model representing an object of interest;

determining a distance measurement between the two major axes and the known two-axis model; and

identifying the object as an object of interest if the distance measurement is below a predetermined threshold.

8. A computer program product as set forth in claim 5, wherein the operation of determining if an object of interest is present in the set of edge pixels, further comprises operations of:

cropping out a region of interest window centered around a selected edge pixel;

performing an edge preserving non-linear diffusion on the region of interest window to increase saliency of edges of a potential object of interest,

forming a background and a foreground in the region of interest window;

segmenting the background from the foreground;

extracting pixel information for the foreground, the pixel information having dimensional coordinates for each pixel in the foreground;

fitting two best fit ellipsoids to the pixel information, each ellipsoid having a major and minor axis, the two best fit ellipsoids being fit to the pixel information such that there exists an intersection between the major axis of the two ellipsoids;

extracting the two major axes from the two ellipsoids;

aligning the two major axes with the a known two-axis model representing an object of interest;

determining a distance measurement between the two major axes and the known two-axis model; and

identifying the object as an object of interest if the distance measurement is below a predetermined threshold.

9. A system for identifying a concealed object of interest, the system comprising a memory module and a processor, wherein the memory module is encoded with instruction means that are executable by the processor for causing the processor to perform operations of:

receiving an image in grayscale;

processing the image to identify feature rich regions which are identified as a binary mask describing edge pixels and non-edge pixels;

randomly sampling a set of edge pixels; and

determine if an object of interest is present in the set of edge pixels.

10. A system as set forth in claim 9, wherein the operation of processing the image further comprises acts of:

identifying all edges in the image using an edge detector, which results in a binary image; and

using a threshold to constrain the binary mask to describe edge pixels and non-edge pixels as a binary, two-class classification.

11. A system as set forth in claim 10, wherein the operation of determining if an object of interest is present in the set of edge pixels, further comprises operations of:

cropping out a region of interest window centered around a selected edge pixel;

performing an edge preserving non-linear diffusion on the region of interest window to increase saliency of edges of a potential object of interest,

forming a background and a foreground in the region of interest window;

segmenting the background from the foreground;

extracting pixel information for the foreground, the pixel information having dimensional coordinates for each pixel in the foreground;

fitting two best fit ellipsoids to the pixel information, each ellipsoid having a major and minor axis, the two best fit ellipsoids being fit to the pixel information such that there exists an intersection between the major axis of the two ellipsoids;

extracting the two major axes from the two ellipsoids;

aligning the two major axes with the a known two-axis model representing an object of interest;

determining a distance measurement between the two major axes and the known two-axis model; and

identifying the object as an object of interest if the distance measurement is below a predetermined threshold.

12. A system as set forth in claim 9, wherein the operation of determining if an object of interest is present in the set of edge pixels, further comprises operations of:

cropping out a region of interest window centered around a selected edge pixel;

performing an edge preserving non-linear diffusion on the region of interest window to increase saliency of edges of a potential object of interest,

forming, a background and a foreground in the region of interest window;

segmenting the background from the foreground;

extracting pixel information for the foreground, the pixel information having dimensional coordinates for each pixel in the foreground;

fitting two best fit ellipsoids to the pixel information, each ellipsoid having a major and minor axis, the two best fit ellipsoids being fit to the pixel information such that there exists an intersection between the major axis of the two ellipsoids;

extracting the two major axes from the two ellipsoids;

aligning the two major axes with the a known two-axis model representing an object of interest;

determining, a distance measurement between the two major axes and the known two-axis model; and

identifying the object as an object of interest if the distance measurement is below a predetermined threshold.