Motion analysis using smart model animations

• US 8,314,840 B1
• Filed: 09/10/2011
• Issued: 11/20/2012
• Est. Priority Date: 09/10/2011
• Status: Expired due to Fees

• Current Assignee: Conley Jack Funk
• Original Assignee: Conley Jack Funk
• Inventors: Funk, Conley Jack
• Primary Examiner(s): Perungavoor, Sath V
• Assistant Examiner(s): PONTIUS, JAMES M
• Application Number:
  US13/229,689
• Time in Patent Office: 437 Days
• Field of Search: 348/157, 382/103, 382/107, 434/247, 434/252, 434/262, 473/222, 482/8
• US Class Current: 348/157
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/1128 using image analysis A61B5/1127 takes precedence
• CPC Class Codes: A61B 5/744 Displaying an avatar, e.g. an animated cartoon character
• CPC Class Codes: A61B 5/7475 User input or interface means, e.g. keyboard, pointing device, joystick
• CPC Class Codes: A63B 2102/32 Golf
• CPC Class Codes: G09B 19/0038 Sports

Abstract

The invention relates to a method and a system for analyzing, teaching and identifying the biomechanics of body motion from a video source. Repeatable body motion activities are analyzed as a series of positions of interest that trigger superimposed smart model animations. The properties of body part images, including location, scale and rotation are determined by a combination of manual and automatic means thereby tailoring the smart models to the underlying video images of the body in motion. Based on the proximity of the subject'"'"'s actual motion to the ideal-or-expected motion defined for the smart models, quantitative characterizations of the motion performance are made.

Claims

1. A computer based method of analyzing a body in motion from a video source, comprising:

displaying at least one image of a plurality of sequential video frames of a subject body in motion;

determining body properties of the subject body in motion for at least one image of the plurality of sequential video frames,

wherein said determined body properties include each of a location property, a scale property, and a rotation property for multiple body parts of the subject body in motion;

displaying at least one image of a smart model animation of an ideal or expected body in motion superimposed on, or beside, the subject body in motion,

wherein said smart model animation includes adjustable model properties, and

wherein the adjustable model properties include each of a location property, a scale property and a rotation property for multiple body parts of the smart model animation;

receiving input from a touch screen or a computer mouse or input of at least one skeletal coordinate from an intelligent video camera that modifies at least one location property, scale property or rotation property of at least one body part of the smart model animation in order to match the at least one modified body part of the smart model animation with at least one body part of the subject body in motion at one or more positions of interest,

wherein whenever one of the adjustable model properties of one body part is modified, one or more of the adjustable model properties of at least one other connected body part is correspondingly modified;

displaying at least one image of the modified smart model animation superimposed on, or beside, the subject body in motion;

displaying subsequent images of the smart model animation when the subject body in motion is determined to be moving beyond, either forward or backward, a position of interest that matches a position of interest of the smart model animation;

if subsequent images of the smart model animation contain a level of divergence between the subject body in motion and the smart model animation, displaying a correction of position animation that transforms at least one body part of the smart model animation to match the at least one transformed body part of the smart model animation with at least one body part of the subject body in motion at one or more positions of interest.

2. The method of claim 1, wherein the transform is a result of input from at least one of a touch-sensitive display screen, a computer mouse, a computer keyboard, a game console, a joystick, or an intelligent video camera.

3. The method of claim 1, wherein the the transform is defined according to at least one of a known standard, an external specification, an instructor, an investigator, a therapist, a researcher or a subject.

4. The method of claim 1, wherein the correction of position animation is displayed superimposed over the subject body in motion, beside the subject body in motion or superimposed over a background image without the subject body in motion present.

5. The method of claim 1, wherein the transform begins with body parts of a matched position of interest and end with body parts of a next position of interest.

6. The method of claim 1, further comprising a duration of animation frame count which determines the number of sequential video frames required to complete a position-of-interest animation.

7. The method of claim 1, wherein, during the transform, whenever one body part of the smart model is transformed, at least one other connected body part of the smart model is correspondingly transformed.

8. The method of claim 1, wherein the determining uses image recognition processing.

9. The method of claim 1, further comprising displaying text descriptions, color-coded markings, gradient filled markings, shadows of markings, on and off flashing of markings or-semi-transparent markings.

10. The method of claim 1, further comprising displaying quantitative ratings according to how well the subject body in motion matches the smart model animation.

11. The method of claim 1, further comprising providing audio responses that indicate how well the subject body in motion matches the smart model animation.

12. The method of claim 1, further comprising displaying actual motion transformations of the subject body in motion.

13. The method of claim 1, further comprising displaying ideal or expected motion transformations.

14. The method of claim 1, further comprising receiving video from a recorded video source or a live video source.

15. The method of claim 1, wherein the matching of the at least one modified body part of the smart model animation with the at least one body part of the subject body in motion at one or more positions of interest occurs independently of the direction of said body in motion.

16. The method of claim 1, wherein the smart model animation originates from a body-model template.

17. The method of claim 16, wherein the body-model template is one still image comprising transformable, graphical body part components.