Retraction based three-dimensional tracking of object movements

• US 9,747,691 B2
• Filed: 07/02/2015
• Issued: 08/29/2017
• Est. Priority Date: 01/23/2013
• Status: Active Grant

• Current Assignee: Lmi Liquidating Co., LLC
• Original Assignee: Leap Motion Incorporated (Ultraleap Limited)
• Inventors: Holz, David S., Hall, W. Dale
• Primary Examiner(s): Vu, Kim
• Assistant Examiner(s): Delaney, Molly
• Application Number:
  US14/790,940
• Publication Number:
  US 20150302576A1
• Time in Patent Office: 789 Days
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06T 7/536 from perspective effects, e.g. by using vanishing points
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85

Abstract

The technology disclosed relates to tracking movement of a real world object in three-dimensional (3D) space. In particular, it relates to mapping, to image planes of a camera, projections of observation points on a curved volumetric model of the real world object. The projections are used to calculate a retraction of the observation points at different times during which the real world object has moved. The retraction is then used to determine translational and rotational movement of the real world object between the different times.

Claims

1. A system for tracking movement of an object'"'"'s portion in a three-dimensional (3D) space, the system including:

one or more processors coupled to memory loaded with computer instructions that, when executed on the processors, implement actions including;

selecting five observation points on a sphere model fitted to a portion of a real world object, wherein one of the observation points is at a center of the sphere model and four perimeter observation points are along a perimeter of the sphere model;

capturing at times t0 and t1, projections of at least four perimeter observation points in at least a first image plane of at least one camera, wherein the object moved between t0 and t1;

calculating a retraction of the four perimeter observation points at time t1 to their positions at t0, including using the four perimeter observation points to;

map the projections of at least four perimeter observation points captured at t0 to a first image plane; and

calculate orientation of a second image plane such that the projections of at least four perimeter observation points captured at t1 to the second image plane are collinear with respective projections in the first image plane with respect to a retracted center observation point; and

determining at least translation of the sphere model between the times t0 and t1 using the orientation of the second image plane calculated.

2. The system of claim 1, further configured to:

select a sixth observation point along a perimeter of the sphere model;

capture at times t0 and t1 projections of the sixth observation point in a third image plane of the camera; and

use a difference in position of the sixth observation point in the third image plane combined with the orientation of the second image plane to calculate rotation of the sphere model.

3. The system of claim 1, further configured to calculate the retraction by rescaling positions of at least four perimeter observation points based on distances between the projections of at least one perimeter observation points captured at the times t0 and t1 and corresponding centers of the sphere model at the times t0 and t1.

4. The system of claim 1, further configured to calculate the retraction using projective transformations of a mapping matrix and an inverse mapping matrix, including:

applying a canonical frame to projections of the perimeter observation points at t0 mapped to a first image plane and projections of the perimeter observation points at t1 mapped to a second image plane; and

applying a forward initial transformation of the projections of the perimeter observation points at t0 to an inverse initial transformation projections of the perimeter observation points at t1.

5. The system of claim 4, further configured to construct the mapping matrix by:

mapping captured projections of the perimeter observation points at t0 to captured projections of the perimeter observation points at t1, including;

extending a line connecting a point on the first image plane with a center of the sphere model at time t0; and

intersecting the line extended with the second image plane.

6. The system of claim 4, further configured to construct the inverse mapping matrix by:

mapping captured projections of the perimeter observation points at t1 to captured projections of the perimeter observation points at t0;

extending a line connecting a point on the second image plane; and

intersecting the line extended with the second image plane.

7. The system of claim 4, further configured to determine horizon lines on the first image plane and the second image plane that are mapped to infinity based on the projective transformations of the mapping matrix and inverse mapping matrix.

8. The system of claim 4, further configured to determine positions of centers of the sphere model at the times t0 and t1 by identifying an intersection line between the first image plane and the second image plane and corresponding vanishing planes not mapped to any image plane.

9. The system of claim 8, further configured to identify the intersection line based on geometry of the first image plane and the second image plane and corresponding vanishing planes by:

determining planes lines that include orthogonal projections of a center of the sphere model in the first image plane and the second image plane and are parallel to horizon lines in the first image plane and the second image plane;

extending projection lines that pass through the center of the sphere model and are orthogonal to the plane lines;

responsive to extension of an auxiliary line in a third image plane passing through the center of the sphere model and is parallel to the horizon lines in the first image plane and the second image plane, creating a pair of intersection lines;

wherein the third image plane intersecting with the first image plane and the second image plane; and

responsive to construction of congruent triangles by the pair of intersection lines and the horizon lines in the first image plane and the second image plane, calculating orthogonal distance between the horizon lines in the first image plane and the second image plane and the intersection line between the first image plane and the second image plane.

10. The system of claim 2, further configured to determine a range of values of an angle between the first image plane and the second image plane based on the sixth observation point along the perimeter of the sphere model.

11. The system of claim 8, wherein determining positions of centers of sphere model at the times t0 and t1 further includes:

constructing two axes that intersect at two points and also intersect the intersection line based on the mapping matrix and inverse mapping matrix, geometry of the first image plane and the second image plane and corresponding vanishing planes, and a range of values for an angle between the first image plane and the second image plane.

12. The system of claim 10, further configured to determine a relative rotational angle of the sphere model from t0 to t1 based on the projections of at least four perimeter observation points captured at times t0 and t1 and positions of centers of the sphere model for the range of values of the angle between the first image plane and the second image plane.

13. The system of claim 10, further configured to:

calculate a mapping error for the range of values of the angle by comparing new sphere models constructed based on the determined positions of the centers of the sphere model with the observation points along the perimeter of the sphere model; and

select a particular new sphere model with minimum mapping error.

14. The system of claim 13, further configured to calculate positions of the observation points by normalizing, to a unit length, radii directed from corresponding centers of the new sphere models to projections of the observations points.

15. A system for tracking movement of an object'"'"'s portion in a three-dimensional (3D) space, the system including:

one or more processors coupled to memory loaded with computer instructions that, when executed on the processors, implement actions including;

capturing at times t0 and t1 projections of at least four perimeter observation points on a sphere model fitted to a portion of a real world object;

calculating a retraction of the four perimeter observation points at time t1 to their positions at t0 by;

using projective transformations of a mapping matrix and an inverse mapping matrix based on a first image plane to which projections of the perimeter observation points at t0 are mapped and a second image plane to which projections of the perimeter observation points at t1 are mapped;

determining horizon lines on the first image plane and the second image plane that are mapped to infinity based on the projective transformations of the mapping matrix and inverse mapping matrix;

determining positions of centers of the sphere model at the times t0 and t1 by identifying an intersection line between the first image plane and the second image plane and corresponding vanishing planes not mapped to any image plane;

determining a range of values of an angle between the first image plane and the second image plane based on a sixth observation point along a perimeter of the sphere model;

determining positions of centers of the sphere model at the times t0 and t1 by constructing two axes that intersect at two points and also intersect the intersection line based on the mapping matrix and inverse mapping matrix, geometry of the first image plane and the second image plane and corresponding vanishing planes, and the range of values of the angle between the first and second image planes; and

determining a relative rotational angle of the sphere model from t0 to t1 based on the projections of the perimeter observation points captured at the times t0 and t1 and positions of centers of the sphere model for the range of values of the angle between the first and second image planes.

16. The system of claim 15, further configured to:

calculate a mapping error for the range of values of the angle by comparing new sphere models constructed based on the determined positions of the centers of the sphere model with the four perimeter observation points along the perimeter of the sphere model; and

select a particular new sphere model with minimum mapping error.

17. The system of claim 15, further configured to calculate positions of the four perimeter observation points by normalizing, to a unit length, radii directed from corresponding centers of new sphere models to projections of the four perimeter observations points.

18. A non-transitory computer readable medium, storing a plurality of instructions for programming one or more processors to track movement of an object'"'"'s portion in a three-dimensional (3D) space, the instructions, when executed on the processors, implementing actions including:

selecting five observation points on a sphere model fitted to a portion of a real world object, wherein one of the observation points is at a center of the sphere model and four perimeter observation points are along a perimeter of the sphere model;

capturing at times t0 and t1, projections of at least four perimeter observation points in at least a first image plane of at least one camera, wherein the object moved between t0 and t1;

calculating a retraction of the four perimeter observation points at time t1 to their positions at t0, including using the four perimeter observation points to;

map the projections of at least four perimeter observation points captured at t0 to a first image plane; and

calculate orientation of a second image plane such that the projections of at least four perimeter observation points captured at t1 to the second image plane are collinear with respective projections in the first image plane with respect to a retracted center observation point; and

determining at least translation of the sphere model between the times t0 and t1 using the orientation of the second image plane calculated.

19. The non-transitory computer readable medium of claim 18, further configured to:

select a sixth observation point along a perimeter of the sphere model;

capture at the times t0 and t1 projections of the sixth observation point in a third image plane of the camera; and

use a difference in position of the sixth observation point in the third image plane combined with the orientation of the second image plane to calculate rotation of the sphere model.

20. The non-transitory computer readable medium of claim 18, further configured to calculate the refraction using projective transformations of a mapping matrix and an inverse mapping matrix, including:

applying a canonical frame to projections of the perimeter observation points at t0 mapped to a first image plane and projections of the perimeter observation points at t1 mapped to a second image plane; and

applying a forward initial transformation of the projections of the perimeter observation points at t0 to an inverse initial transformation projections of the perimeter observation points at t1.