Extracting performance metrics from images

• US 7,561,989 B2
• Filed: 04/03/2007
• Issued: 07/14/2009
• Est. Priority Date: 04/04/2006
• Status: Expired due to Fees

• Current Assignee: Procise
• Original Assignee: Procise
• Inventors: Moon, Ed, Banks, Gordon
• Primary Examiner(s): Feliciano; Eliseo Ramos
• Assistant Examiner(s): Suarez; Felix E
• Application Number:
  US11/732,498
• Publication Number:
  US 20070282563A1
• Time in Patent Office: 833 Days
• Field of Search: 702/85, 702/94, 702/141, 702/143, 702/156, 702/159, 702/181, 702/179, 702/183, 702/190, 702/191, 250/208.1, 342/357.07, 375/240.16, 345/473, 345/474, 348169-172
• US Class Current: 702/191
• CPC Class Codes: A61B 2503/10 Athletes
• CPC Class Codes: A61B 2560/0223 of calibration, e.g. protocols for calibrating sensors
• CPC Class Codes: A61B 5/1038 Measuring plantar pressure during gait
• CPC Class Codes: A61B 5/1113 Local tracking of patients, e.g. in a hospital or private home
• CPC Class Codes: A61B 5/1128 using image analysis A61B5/1127 takes precedence
• CPC Class Codes: A61B 5/7435 Displaying user selection data, e.g. icons in a graphical user interface
• CPC Class Codes: A63B 2024/0025 Tracking the path or location of one or more users, e.g. players of a game
• CPC Class Codes: A63B 2220/05 Image processing for measuring physical parameters
• CPC Class Codes: A63B 2220/13 Relative positions
• CPC Class Codes: A63B 2220/30 Speed
• CPC Class Codes: A63B 2220/40 Acceleration
• CPC Class Codes: A63B 2220/806 Video cameras
• CPC Class Codes: A63B 24/0003 Analysing the course of a movement or motion sequences during an exercise or trainings sequence, e.g. swing for golf or tennis
• CPC Class Codes: A63B 24/0021 Tracking a path or terminating locations
• CPC Class Codes: G01P 3/50 for measuring linear speed G01P3/56 takes precedence
• CPC Class Codes: G01P 3/806 in devices of the type to be classified in G01P3/68
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30248 Vehicle exterior or interior
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments

Abstract

Through the use of image processing and set-up calibration techniques, an accurate position of an object may be determined. Embodiments of the present disclosure measure a change in position over a known time interval. Accordingly, the change in position aids in measuring the object'"'"'s metrics such as, for example, position, velocity, acceleration, maximum velocity, maximum acceleration and/or maximum deceleration. The object can be, for example, any person, individual body part, a group of body parts, a vehicle, or any other movable object.

Claims

1. A method of extracting performance metrics comprising:

inputting data for a digital video of at least one moving object into a computer readable medium, the digital video including a plurality of frames corresponding to a pixel space through which pixel data for the object moves;

selecting a portion of the object;

processing pixel data corresponding to the selected portion of the object according to a user-defined set of calibration factors;

correlating pixel locations for the selected portion of the object within the pixel space in at least two of the frames to determine movement of the selected portion of the object through the pixel space based upon changes in the pixel locations for the selected portion of the object relative to pixel data not corresponding to the selected object; and

outputting metric information to the computer readable medium regarding movement of the selected portion of the object within the pixel space according to the correlated pixel locations.

2. The method according to claim 1, wherein the metric information comprises an acceleration of the object, the acceleration determined by examining movement of the selected portion of the object within the pixel space in the plurality of frames over a period of time, the time determined by a known frame rate of the digital video.

3. The method according to claim 2, wherein the acceleration of the object is determined for a specific point in time.

4. The method according to claim 1, wherein the metric information comprises a velocity of the object, the velocity determined by examining movement of the selected portion of the object within the pixel space in the plurality of frames over a period of time, the time determined by a known frame rate of the digital video.

5. The method according to claim 2, wherein the metric information comprises a maximum acceleration of the object.

6. The method according to claim 4, wherein the metric information comprises a maximum velocity of the object.

7. The method according to claim 1 further comprising:

scaling the image of the object to a second object, the second object having a known size.

8. The method according to claim 1 further comprising:

storing the metric information in a memory; and

comparing a second set of metric information to the stored metric information.

9. The method according to claim 8 further comprising:

outputting a report describing a relationship between the metric information and the second set of metric information.

10. A system to extract performance metrics comprising:

a digital video recorded on a computer readable medium, the digital video including a plurality of frames corresponding to a pixel space through which pixel data for the object moves; and

a processor operable to;

input the digital video of at least one moving object;

select a portion of the object;

process pixel data corresponding to the selected portion of the object according to a user-defined set of calibration factors;

correlate pixel locations for the selected portion of the object within the pixel space in at least two of the frames to determine movement of the selected portion of the object through the pixel space based upon changes in the pixel locations for the selected portion of the object relative to pixel data not corresponding to the selected object; and

output metric information regarding movement of the selected portion of the object within the pixel space according to the correlated pixel locations.

11. The system according to claim 10, wherein the metric information comprises an acceleration of the object, the acceleration determined by examining movement of the selected portion of the object within the pixel space in the plurality of frames over a period of time, the time determined by a known frame rate of the digital video.

12. The system according to claim 11, wherein the acceleration of the object is determined for a specific point in time.

13. The system according to claim 10, wherein the metric information comprises a velocity of the object, the velocity determined by examining movement of the selected portion of the object within the pixel space in the plurality of frames over a period of time, the time determined by a known frame rate of the digital video.

14. The system according to claim 11, wherein the metric information comprises a maximum acceleration of the object.

15. The system according to claim 13, wherein the metric information comprises a maximum velocity of the object.

16. The system according to claim 10 the processor scales the image of the object to a second object, the second object having a known size.

17. The system according to claim 10 further comprising:

a memory to store the metric information in a memory.

18. The system according to claim 17, wherein the processor compares a second set of metric information to the stored metric information.

19. The system according to claim 18, wherein the processor outputs a report describing a relationship between the metric information and the second set of metric information.

20. A computer program embodied on a computer readable medium and operable to be executed by a processor, the computer program comprising computer readable program code, the code comprising:

inputting a digital video of at least one moving object, the digital video including a plurality of frames corresponding to a pixel space through which pixel data for the object moves;

selecting a portion of the object;

processing pixel data corresponding to the selected portion of the object according to a user-defined set of calibration factors;

correlating pixel locations for the selected portion of the object within the pixel space in at least two of the frames to determine movement of the selected portion of the object through the pixel space based upon changes in the pixel locations for the selected portion of the object relative to pixel data not corresponding to the selected object; and

outputting metric information regarding movement of the selected portion of the object within the pixel space according to the correlated pixel locations.