Pose tracking

• US 8,837,778 B1
• Filed: 06/01/2012
• Issued: 09/16/2014
• Est. Priority Date: 06/01/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Rawles, LLC (Amazon.com, Inc.)
• Inventors: Chang, Samuel Henry, Yao, Ning
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): HARANDI, SIAMAK
• Application Number:
  US13/486,664
• Time in Patent Office: 837 Days
• Field of Search: None
• US Class Current: 382/103
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06T 7/75 involving models

Abstract

Techniques are described for tracking the pose of a surface based on a point set representing the surface. Sequential observed poses of the surface are used as the basis for creating a mathematical model of the motion of the surface. Future motion of the surface may be predicted based on the mathematical model.

Claims

1. A system comprising:

one or more processors;

a projector;

an imaging sensor; and

one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising;

capturing images using the imaging sensor;

based at least in part on the captured images, determining sequential observed locations of a display medium upon which content is to be projected;

based at least in part on the sequential observed locations, estimating motion parameters for a motion model;

predicting future location motion of the display medium based at least in part on the motion parameters and the motion model; and

projecting the content on the display medium from the projector based at least in part on the predicted future motion of the display medium.

2. The system of claim 1, the acts further comprising comparing the predicted future motion of the display medium with subsequently observed locations of the display medium to determine stability of the predicted future motion.

3. The system of claim 1, wherein the motion model comprises one or more state equations.

4. The system of claim 1, wherein estimating the motion parameters comprises recursive least squares parameter identification.

5. The system of claim 1, wherein the predicted future motion of the display medium is specified in three dimensional coordinates.

6. The system of claim 1, wherein the predicted future motion of the display medium is specified as sets of corner locations.

7. The system of claim 1, wherein the display medium is polygonal.

8. A method of projecting content onto an object, comprising:

determining sequential observed locations of the object;

repeatedly predicting future motion of the object based at least in part on the sequential observed locations; and

projecting the content onto the display medium based at least in part on the predicted future motion of the object.

9. The method of claim 8, further comprising comparing the predicted future motion of the object with subsequently observed locations of the object to determine stability of the predicted future motion.

10. The method of claim 8, wherein predicting the future motion of the object comprises dynamically estimating parameters of a motion model.

11. The method of claim 8, wherein predicting the future motion of the object comprises dynamically estimating parameters of a motion model, and wherein estimating the parameters comprises recursive least squares parameter identification.

12. The method of claim 8, wherein the object is polygonal.

13. One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform acts comprising:

obtaining point sets representing at least a portion of a display medium at sequential times;

calculating observed poses of the display medium based at least in part on the point sets;

based at least in part on the observed poses, estimating motion parameters of a motion model; and

predicting future motion of the display medium based at least in part on the motion parameters and the motion model.

14. The one or more non-transitory computer-readable media of claim 13, the acts further comprising comparing the predicted future motion of the display medium with the observed poses of the display medium to determine stability of the predicted future motion.

15. The one or more non-transitory computer-readable media of claim 13, wherein estimating the motion parameters comprises recursive least squares parameter identification.

16. The one or more non-transitory computer-readable media of claim 13, the acts further comprising identifying corners of the display medium based at least in part on the point set, wherein calculating the observed poses is based at least in part on the identified corners.

17. The one or more non-transitory computer-readable media of claim 13, wherein the display medium is polygonal.

18. The one or more non-transitory computer-readable media of claim 13, wherein the motion model comprises one or more state equations.

19. The one or more non-transitory computer-readable media of claim 13, wherein the predicted future motion of the display medium is specified in three dimensional coordinates.

20. The one or more non-transitory computer-readable media of claim 13, wherein the acts further comprising causing content to be projected on the display medium from a projector based at least in part on the predicted future motion of the display medium.