Object instance identification using template textured 3-D model matching

• US 9,128,188 B1
• Filed: 07/15/2013
• Issued: 09/08/2015
• Est. Priority Date: 07/13/2012
• 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): BHATNAGAR, ANAND P
• Application Number:
  US13/942,234
• Time in Patent Office: 785 Days
• US Class Current: 1/1
• CPC Class Codes: G01S 17/894 3D imaging with simultaneous measurement of time-of-flight at a 2D array of receiver pixels, e.g. time-of-flight cameras or flash lidar
• CPC Class Codes: G01S 7/4802 using analysis of echo signal for target characterisation; Target signature; Target cross-section
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/30212 Military
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 20/00 Scenes; Scene-specific elements control of digital cameras H04N23/60
• CPC Class Codes: G06V 20/64 Three-dimensional objects

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 scene, comprising:

receiving target parameter values for a plurality of target parameters for a target hypothesis, wherein said plurality of target parameters are selected from the group of parameters describing location and orientation of said target in a range image of said scene, wherein said range image R is mathematically 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 a range sensor;

providing intensity imagery of said scene generated by an intensity imaging sensor;

electronically generating a synthetic range image of said scene for said 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 synthetic range image R^s is mathematically defined as R^s={r_ij^s, 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^s represents the range between an object at point ij in said synthetic range image and said range sensor;

electronically computing a geometrical matching score C for said target hypothesis, where said geometrical matching score C 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 2, where k=0 and L=3.0.

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

5. The method of claim 4, where k=7 and L=8.0.

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