AUTOMATED SCORING SYSTEM FOR ATHLETICS

• US 20090220124A1
• Filed: 03/02/2009
• Published: 09/03/2009
• Est. Priority Date: 02/29/2008
• Status: Active Grant

• Current Assignee: Fred Siegel
• Original Assignee: Fred Siegel
• Inventors: SIEGEL, Fred
• Granted Patent: US 8,175,326 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 2207/30221 Sports video; Sports image
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training

Abstract

Disclosed are methods and systems for utilizing motion capture techniques, for example, video based motion capture techniques, for capturing and modeling the captured 3D movement of an athlete through a defined space. The model is then compared with an intended motion pattern in order to identify deviations and/or form breaks that, in turn, may be used in combination with a scoring algorithm to quantify the athlete'"'"'s execution of the intended motion pattern to produce an objective score. It is anticipated that these methods and systems will be particularly useful for training and judging in those sports that have struggled with the vagaries introduced by the subjective nature of human scoring.

Claims

1. A method of evaluating a subject'"'"'s performance comprising:

receiving a sequence of images as the subject moves through a defined space;

processing, by a processing device, the sequence of images to generate a performance model corresponding to the movement of the subject through the defined space;

comparing, by the processing device, the performance model with a comparison model;

identifying, by the processing device, deviation between the performance model and the comparison model; and

outputting, by the processing device, the identified deviation in a human or machine readable format.

2. The method of evaluating a subject'"'"'s performance according to claim 1, further comprising:

applying, by the processing device, a scoring method to the identified deviation to obtain a score reflecting the subject'"'"'s performance; and

outputting, by the processing device, the score in a human or machine readable format.

3. The method of evaluating a subject'"'"'s performance according to claim 2, wherein:

the subject is a diver;

the subject moves through the defined space in executing a dive; and

the scoring method produces a score of from 0 to 10.

4. The method of evaluating a subject'"'"'s performance according to claim 2, further comprising:

applying, by the processing device, a first adjustment method for improving a correlation between the performance model and the subject'"'"'s performance.

5. The method of evaluating a subject'"'"'s performance according to claim 4, wherein:

utilizing subject-specific biomorphic data in the first adjustment method for modifying the performance model.

6. The method of evaluating a subject'"'"'s performance according to claim 5, further comprising:

collecting the subject-specific biomorphic data at a time generally contemporaneous with the performance.

7. The method of evaluating a subject'"'"'s performance according to claim 4, further comprising:

applying, by the processing device, a second adjustment method for improving a correlation between the performance model and the comparison model.

8. A system for evaluating a subject'"'"'s performance comprising:

a camera array arranged and configured for capturing a plurality of image sequences of the subject in a defined space;

a processor arranged and configured for

converting the captured images sequences into a performance model corresponding to the subject'"'"'s motion through the defined space;

identifying a deviation between the performance model and a comparison model; and

assigning a deviation value to the deviation.

9. The system for evaluating a subject'"'"'s performance according to claim 8, wherein the processor is also arranged and configured for:

applying a scoring method to the deviation value to generate scoring data.

10. The system for evaluating a subject'"'"'s performance according to claim 8, wherein:

the processor is arranged and configured for executing a first adjustment method for improving a correlation between the performance model and the subject'"'"'s performance.

11. The system for evaluating a subject'"'"'s performance according to claim 10, wherein:

the adjustment method utilizes subject-specific biomorphic data to modify the performance model.

12. The system for evaluating a subject'"'"'s performance according to claim 11, wherein:

the camera array collects subject-specific biomorphic data at a time generally contemporaneous with the performance.

13. The system for evaluating a subject'"'"'s performance according to claim 10, wherein:

the processor is arranged and configured for executing a second adjustment method for improving a correlation between the performance model and the comparison model.