Scalable method for rapidly detecting potential ground vehicle under cover using visualization of total occlusion footprint in point cloud population

• US 8,294,712 B2
• Filed: 07/10/2007
• Issued: 10/23/2012
• Est. Priority Date: 09/19/2003
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Nelson, James M.
• Primary Examiner(s): HAJNIK, DANIEL F
• Application Number:
  US11/775,430
• Publication Number:
  US 20080123961A1
• Time in Patent Office: 1,932 Days
• Field of Search: None
• US Class Current: 345/421
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes

Abstract

Techniques for facilitating detection of an object in a point cloud of three-dimensional imaging data representing an area of study where the object potentially is obscured by intervening obstacles are provided. The imaging data is processed to identify elements in the point cloud having substantially common attributes signifying that the identified elements correspond to a feature in the area of study. An isosurface is generated associating the elements having substantially common attributes. A reversed orientation visualization model for a region of interest is generated. The reversed orientation visual model areas of total occlusion that potentially signify presence of the object.

Claims

1. A computer implemented method to detect a presence in an area of study of a ground-level object, the method comprising:

gathering, in a processing device, a point cloud of three-dimensional imaging data representing the area of study from an aerial position where an intervening obstacle impedes a line of sight between the aerial position and a ground-level object;

processing, in the processing device, the three-dimensional imaging data to identify elements in the point cloud having common attributes signifying that the identified elements correspond to a feature in the area of study that is at least partially obscured by the intervening obstacle;

generating, in the processing device, at least one implied geometrical representation which represents data points having equivalent scalar values as calculated from the collected data;

generating, in the processing device, at least one isosurface associating the elements having common attributes;

selecting, in the processing device, a region of interest from the area of study;

generating, in the processing device, from the imaging data gathered from the aerial position an up from underground oriented visualization model of the region of interest; and

displaying, on a display module coupled to the processing device, the up from underground oriented visualization model to expose the feature in the area of study that is at least partially obscured by the intervening obstacle in the line of sight between the aerial position and the ground-level object.

2. The computer implemented method of claim 1, wherein the three-dimensional imaging data of the area of study is gathered using ladar.

3. The computer implemented method of claim 1, wherein imaging data is processed using a population function computed on a sampling mesh by a Fast Binning Method (FBM).

4. The computer implemented method of claim 1, wherein the isosurface of the population function is computed using a marching cubes method.

5. The computer implemented method of claim 1, further comprising allowing an operator to manually select the region of interest from the area of study.

6. The computer implemented method of claim 1, wherein the up from underground oriented visualization model exposes areas of total ground occlusion.

7. The computer implemented method of claim 1, further comprising regenerating the up from underground oriented visualization model using interactive user input from a slider resolution control.

8. The computer implemented method of claim 7, wherein the slider resolution control dynamically regenerates the up from underground oriented visualization model when a user changes the slider resolution control position.

9. The computer implemented method of claim 1, wherein the up from underground oriented visual model disambiguates areas of total ground occlusion from porous ground occluders.

10. A computer implemented method, comprising:

gathering, in the computer, a point cloud of three-dimensional imaging data representing the area of study from an aerial position where an intervening obstacle impedes a line of sight between the aerial position and a ground-level object;

processing, in the computer, the three-dimensional imaging data to identify elements in the point cloud having common attributes signifying that the identified elements correspond to a feature in the area of study that is at least partially obscured by the intervening obstacle;

generating, in the computer, at least one implied geometrical representation which represents data points having equivalent scalar values as calculated from the collected data;

viewing, on a display coupled to a processing device, a reversed orientation visualization model of an isosurface generated from the three-dimensional imaging data;

selecting, on the display, a region of interest from the reversed orientation visualization model;

viewing, on the display, the region of interest of the isosurface as a top-down orientation visualization model;

selectively varying the point resolution of the region of interest on the display to adjust the isosurface sampling resolution; and

identifying an object within the isosurface.

11. The computer implemented method of claim 10, wherein the isosurface includes an area of partial ground occlusion and an area of total ground occlusion, the area of total ground occlusion depicted as a cavity within the isosurface when viewed in the revered orientation visualization model.

12. The computer implemented method of claim 10, wherein selecting the region of interest includes selecting a cavity with the isosurface.

13. The computer implemented method of claim 10, wherein selectively varying the point resolution includes user interaction with a slider control.

14. The computer implemented method of claim 10, wherein identifying an object within the isosurface includes identifying a target that is at least partially obscured in a top-down image.

15. The computer implemented method of claim 10, wherein the isosurface is generated from a point cloud population generated from ladar.

16. A computer based system to detect a presence, in an area of study, of an object, the system comprising:

a data gathering device to gather a point cloud of three-dimensional imaging data representing the area of study from an aerial position;

an image processor to identify one or more data elements in the point cloud of three dimensional imaging data which have substantially common attributes and to generate at least one implied geometrical representation which represents data points having equivalent scalar values as calculated from the collected data;

an isosurface generator to generate at least one isosurface associating a subset of the one or more data elements having substantially common attributes which indicate that the identified elements correspond to a feature in the area of study that is at least partially obscured by an intervening obstacle;

a region of interest selector to enable a user to select a region of interest from the area of study;

a visualization model generator to generate, from the three-dimensional imaging data gathered from the aerial position, an up from underground oriented visualization model of the region of interest; and

a display module to display the up from underground oriented visualization model to expose the feature in the area of study that is at least partially obscured by an intervening obstacle in a line of sight between the data gathering device and the object.

17. The system of claim 16 wherein the data gathering device comprises a ladar.

18. The system of claim 16, wherein:

the image processor uses a population function computed on a sampling mesh by a Fast Binning Method (FBM); and

the isosurface generator uses a marching cubes method to determine an isosurface.

19. The system of claim 16, wherein the up from underground oriented visualization model exposes areas of total ground occlusion.