Shape matching automatic recognition methods, systems, and articles of manufacture
First Claim
Patent Images
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={(rij), 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 rij 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 Rs,1 is mathematically defined as Rs,1={rijs,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 Rs,1, and rijs,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
1 Assignment
0 Petitions
Accused Products
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.
-
Citations
12 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={(rij), 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 rij 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 Rs,1 is mathematically defined as Rs,1={rijs,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 Rs,1, and rijs,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 - View Dependent Claims (2, 3, 4, 5, 6)
-
-
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={(rij), 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 rij 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 Rs,1 is mathematically defined as Rs,1={rijs,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 Rs,1, and rijs,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 - View Dependent Claims (8, 9, 10, 11, 12)
-
Specification