Shape matching automatic recognition methods, systems, and articles of manufacture

• US 8,810,779 B1
• Filed: 08/23/2013
• Issued: 08/19/2014
• Est. Priority Date: 03/25/2013
• Status: Active Grant

• Current Assignee: the united states of america as represented by the secretary of the navy
• Original Assignee: the united states of america as represented by the secretary of the navy
• Inventors: Hilde, Jeffrey Jay
• Primary Examiner(s): RATCLIFFE, LUKE D
• Application Number:
  US13/974,195
• Time in Patent Office: 361 Days
• Field of Search: 356 301- 315, 356 401- 41, 356 501- 515, 356 6- 22, 356/28, 356/28.5
• US Class Current: 356/4.01
• CPC Class Codes: G01C 15/002 Active optical surveying means optical plumbing G01C15/105
• CPC Class Codes: G01S 17/89 for mapping or imaging
• CPC Class Codes: G01S 7/487 Extracting wanted echo signals , e.g. pulse detection
• CPC Class Codes: G06V 20/653 by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces

Abstract

Systems, methods, and articles of manufacture for automatic target recognition. A hypothesis about a target'"'"'s classification, position and orientation relative to a LADAR sensor that generates range image data of a scene including the target is simulated and a synthetic range image is generated. The range image and synthetic range image are then electronically processed to determine whether the hypothesized model and position and orientation are correct. If the score is sufficiently high then the hypothesis is declared correct, otherwise a new hypothesis is formed according to a search strategy.

Claims

1. A method of identifying a target in a sensor range image, comprising:

receiving first target parameter values P₁ for a plurality of target parameters for a first target hypothesis of a plurality of target hypotheses, wherein said plurality of target parameters are selected from the group of parameters describing location and orientation of said target;

wherein said sensor range image is notationally defined as R={(r_ij), i=1, . . . b, j=1 . . . c}, where b represents the number of columns of pixels in said sensor range image, c represents the number of rows of pixels in said sensor range image, and r_ij represents the range between an object at point ij in said sensor range image and said sensor;

receiving a first set of parameter extent values e₁ for a plurality of target search parameters of said plurality of target parameters, where each value of said first set of parameter extent values e₁ describes a search space range of a corresponding of said plurality of target parameters;

electronically generating a first synthetic range image of said scene for said first target hypothesis by rendering a 3-D wire grid model of a plurality of 3-D wire models of targets to be identified at said target parameter values;

wherein one of said plurality of 3-D models has a surface which is a match to a surface of said target, where said first synthetic range image R^s,1 is mathematically defined as R^s,1={r_ij^s,1, i=1, . . . b, j=1 . . . c}, where b represents the number of columns of pixels in said synthetic range image, c represents the number of rows of pixels in said synthetic range image R^s,1, and r_ij^s,1 represents the range between an object at point ij in said first synthetic range image and said sensor;

electronically computing a first matching score C₁ for said first target hypothesis, where said first matching score C₁ is mathematically defined as

2. The method of claim 1, wherein h is selected from the range of values between and including zero and two;

wherein w is selected from the range of values between and including zero and two.

3. The method of claim 1, wherein said generating a synthetic range image step is performed using a graphics processing unit.

4. The method of claim 1, where said sensor is a laser detection and ranging (LADAR) sensor.

5. The method of claim 2, where k=0 and L=3.0.

6. The method of claim 3, where k=7 and L=8.0.

7. A non-transitory computer readable medium having stored thereon a plurality of computer executable instructions that, when executed by a computer including a graphics processing unit, cause the computer to:

receive first target parameter values P₁ for a plurality of target parameters for a first target hypothesis of a plurality of target hypotheses, wherein said plurality of target parameters are selected from the group of parameters describing location and orientation of said target;

wherein said sensor range image is notationally defined as R={(r_ij), i=1, . . . b, j=. . . c}, where b represents the number of columns of pixels in said sensor range image, c represents the number of rows of pixels in said sensor range image, and r_ij represents the range between an object at point ij in said sensor range image and said sensor;

receive a first set of parameter extent values e₁ for a plurality of target search parameters of said plurality of target parameters, where each value of said first set of parameter extent values e₁ describes a search space range of a corresponding of said plurality of target parameters;

electronically generate a first synthetic range image of said scene for said first target hypothesis by rendering a 3-D wire grid model of a plurality of 3-D wire models of targets to be identified at said target parameter values;

wherein one of said plurality of 3-D models has a surface which is a match to a surface of said target, where said first synthetic range image R^s,1 is mathematically defined as R^s,1={r_ij^s,1, i=1, . . . b, j=1 . . . c}, where b represents the number of columns of pixels in said synthetic range image, c represents the number of rows of pixels in said synthetic range image R^s,1, and r_ij^s,1 represents the range between an object at point ij in said first synthetic range image and said sensor;

electronically compute a first matching score C₁ for said first target hypothesis, where said first matching score C₁ is mathematically defined as

8. The medium of claim 7, wherein h is selected from the range of values between and including zero and two;

where w is selected from the range of values between and including zero and two.

9. The medium of claim 7, wherein said generating a synthetic range image step is performed using a graphics processing unit.

10. The medium of claim 7, where said sensor is a laser detection and ranging (LADAR) sensor.

11. The medium of claim 8, where k=0 and L=3.0.

12. The medium of claim 9, where k=7 and L=8.0.