Target and method of detecting, identifying, and determining 3-D pose of the target

• US 8,422,777 B2
• Filed: 10/13/2009
• Issued: 04/16/2013
• Est. Priority Date: 10/14/2008
• Status: Active Grant

• Current Assignee: Jolly Seven, Series 70 of Allied Security Trust I (Allied Security Trust)
• Original Assignee: Joshua Victor Aller
• Inventors: Aller, Joshua Victor
• Primary Examiner(s): Alavi, Amir
• Application Number:
  US12/578,543
• Publication Number:
  US 20100092079A1
• Time in Patent Office: 1,281 Days
• Field of Search: 382/162, 382/164, 382/165, 382/168, 382/172, 382270-271, 345/419, 358/465, 358/466, 358/515
• US Class Current: 382/165
• CPC Class Codes: B42D 15/00 Printed matter of special format or style not otherwise provided for
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning

Abstract

We disclose a photogrammetry target that includes a background having a first color and a plurality of ovoid regions located on the background and having a second color contrasting the first color. We further disclose a method and system for detecting the target and processing image data captured from the target to discern therefrom at least one of a distance to the target, identification of the target, or pose of the target.

Claims

1. A target, comprising:

a background including a first intensity; and

a plurality of ovoid regions located on the background, wherein each of the plurality of ovoid regions includes a second intensity contrasting the first intensity;

wherein each of the plurality of ovoid regions is spaced at least a minimum distance from other of the plurality of ovoid regions;

wherein each of the plurality of ovoid regions includes a minor axis having at least the minimum distance;

wherein each of the plurality of ovoid regions is spaced at least the minimum distance from the outer edge of the background; and

wherein a width of a safety region substantially surrounding the background region is at least the minimum distance.

2. The target of claim 1 wherein the safety region includes the second intensity.

3. The target of claim 1 wherein at least two of the ovoid regions are of a different shape.

4. The target of claim 1 wherein the plurality of ovoid regions includes one or more elliptical regions.

5. The target of claim 1 wherein the plurality of ovoid regions is rotationally non-symmetric.

6. The target of claim 1 further comprising:

a medium having reproduced thereon the background and the plurality of ovoid regions; and

wherein the medium includes at least one of metal, paper, stencil mask, plastic, rubber, or laser inscribable medium.

7. The target of claim 1 wherein the medium, background, and the plurality of ovoid regions is capable of detection using a single sensing channel or multiple sensing channels.

8. The target of claim 1

wherein a placement or a shape of each of the plurality of ovoid regions is configured to uniquely define the target;

wherein the shape of each of the plurality of ovoid regions is one of a fixed set of shapes; and

wherein the fixed set of shapes corresponds to one or more shapes grouped according to predetermined areas.

9. The target of claim 1 wherein a placement, shape, or color of each of the plurality of ovoid regions is configured to encode digital information.

10. A non-transitory computer readable medium having computer-executable instructions stored thereon that, if executed by a processor, cause the processor to process image data captured from the target of claim 1 and discern therefrom at least one of a distance to the target, identification of the target, or pose of the target.

11. A method, comprising:

identifying a target including a background region having a first intensity and a plurality of ovoid regions having a second intensity contrasting the first intensity; and

calculating at least one of a distance to the target or a pose of the target responsive to identifying the target;

wherein each of the plurality of ovoid regions is spaced at least a minimum distance from other of the plurality of ovoid regions;

wherein each of the plurality of ovoid regions includes a minor axis having at least the minimum distance;

wherein each of the plurality of ovoid regions is spaced at least the minimum distance from the outer edge of the background; and

wherein a width of a safety region substantially surrounding the background region is at least the minimum distance.

12. The method of claim 11 wherein the identifying the target includes:

generating a plurality of contour loops substantially surrounding a boundary of each of the plurality of ovoid regions wherein the boundary of each of the ovoid regions crosses a predetermined intensity value; and

fitting each of the plurality of contour loops to a corresponding ellipse.

13. The method of claim 12 further comprising selecting the predetermined intensity value based on the boundary of each of the plurality of ovoid regions or a boundary of the background region.

14. The method of claim 11 further comprising:

determining an area of the background region;

calculating an area of the plurality of ovoid regions by summing an area corresponding to each of the plurality of ovoid regions; and

determining an area ratio of the target by dividing the area of the plurality of ovoid regions by the area of the background region.

15. The method of claim 14 further comprising correcting the area ratio of the target responsive to an area ratio of a model.

16. The method of claim 11 further comprising converting the background region and the plurality of ovoid regions to a model metric space that is rotationally invariant.

17. The method of claim 11 further comprising matching each of the plurality of ovoid regions to one or more shapes stored in a database.

18. The method of claim 17 wherein the matching includes:

extracting predetermined metrics from each of the plurality of ovoid regions; and

comparing the predetermined metrics to metrics associated with the one or more shapes stored in the database.

19. The method of claim 11 further comprising:

generating at least two potential poses for the target based at least in part on an orientation associated with each of the plurality of ovoid regions; and

ranking the at least two potential poses.

20. The method of claim 19 further comprising refining the at least two potential poses.