Geometric motion analysis

• US 6,816,632 B1
• Filed: 02/17/2000
• Issued: 11/09/2004
• Est. Priority Date: 02/17/2000
• Status: Expired due to Fees

• Current Assignee: Wake Forest University Health Sciences
• Original Assignee: Wake Forest University Health Sciences
• Inventors: Slice, Dennis E.
• Primary Examiner(s): Do, Anh Hong
• Application Number:
  US09/506,463
• Time in Patent Office: 1,727 Days
• Field of Search: 382/294, 382/154, 382/107, 382/236, 382/293, 382/295, 382/291, 703/1, 434/55
• US Class Current: 382/294
• CPC Class Codes: G06F 18/2137 based on criteria of topology preservation, e.g. multidimensional scaling or self-organising maps
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/262 using transform domain methods, e.g. Fourier domain methods
• CPC Class Codes: G06V 10/478 Contour-based spectral representations or scale-space representations, e.g. by Fourier analysis, wavelet analysis or curvature scale-space [CSS]
• CPC Class Codes: G06V 10/752 Contour matching
• CPC Class Codes: G06V 10/76 based on eigen-space representations, e.g. from pose or different illumination conditions; Shape manifolds
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training

Abstract

A method for geometrically analyzing motion having the steps of: choosing a set of points having at least three individual points to define a single realization of a motion; sequentially collecting Cartesian coordinates of the set of points at different times during the motion from a start point to an end point; treating the collection of sets of points as a sample of the motion; and transforming the sets of points at the different times to a common coordinate system thereby defining a trajectory of the motion. In a preferred implementation of the method of the present invention, the method further has the steps of: choosing a set of points having at least three individual points to define a single realization of a motion; sequentially collecting Cartesian coordinates of the set of points at different times during the motion from a start point to an end point; treating the collection of sets of points as a sample of the motion; transforming the sets of points at the different times to a common coordinate system thereby defining a trajectory of the motion; and calculating elliptic Fourier coefficients describing the trajectory of the motion independent of any difference in the spacing of the different times.

Claims

1. A method for geometrically analyzing a motion of an object, the method comprising the steps of:

choosing a set of points on the object characterizing a shape of the object during the motion, the set of points having at least three individual points to define a single realization of the motion;

sequentially collecting Cartesian coordinates of the set of points at different times during the motion from a start point to an end point;

treating the collection of sets of points as a sample of the motion; and

transforming the sets of points at the different times to a common coordinate system thereby defining a trajectory of the motion.

2. The method of claim 1, wherein the common coordinate system is a hemisphere of generalized Procrustes aligned shapes.

3. The method of claim 1, wherein the common coordinate system is a Kendall shape space.

4. The method of claim 1, wherein the transformation to the common coordinate system includes an identity transformation with respect to a prior established, extrinsic coordinate system.

5. The method of claim 1, wherein the common coordinate system is augmented by vectors representing non-spatial variables.

6. A method for geometrically analyzing a motion of an object, the method comprising the steps of:

(a) choosing a set of points on the object characterizing a shape of the object during the motion, the set of points having at least three individual points to define a single realization of the motion;

(b) sequentially collecting Cartesian coordinates of the set of points at different times during the motion from a start point to an end point;

(c) treating the collection of sets of points as a sample of the motion;

(d) transforming the sets of points at the different times to a common coordinate system thereby defining a trajectory of the motion; and

(e) calculating elliptic Fourier coefficients describing the trajectory of the motion independent of any difference in the spacing of the different times.

7. The method of claim 6, further comprising the steps of:

(f) repeating steps (a) through (e) for at least one other realization to form a first sample of realizations together with the single realization; and

(g) performing a statistical analysis on the first sample using the elliptical Fourier coefficients.

8. The method of claim 7, further comprising the steps of:

(h) repeating steps (a) through (f) to form at least a second sample of realizations; and

(i) performing a statistical analysis on the first and second samples using the elliptical Fourier coefficients.

9. The method of claim 6, wherein the elliptical Fourier coefficients are expressed as Cartesian coordinates.

10. The method of claim 6, wherein the elliptical Fourier coefficients are expressed as polar coordinates.

11. The method of claim 6, wherein the common coordinate system is a hemisphere of generalized Procrustes aligned shapes.

12. The method of claim 6, wherein the common coordinate system is a Kendall shape space.

13. The method of claim 6, wherein the transformation to the common coordinate system includes an identity transformation with respect to a prior established, extrinsic coordinate system.

14. The method of claim 6, wherein the common coordinate system is augmented by vectors representing non-spatial variables.