Systems and Methods for Non-Contact Tracking and Analysis of Physical Activity

• US 20160042529A1
• Filed: 08/11/2015
• Published: 02/11/2016
• Est. Priority Date: 08/11/2014
• Status: Active Grant

• Current Assignee: Arizona Board of Regents (University of Arizona)
• Original Assignee: Nongjian Tao, Yuting Yang
• Inventors: Tao, Nongjian, Yang, Yuting
• Granted Patent: US 10,078,795 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30221 Sports video; Sports image
• 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: G06V 40/23 Recognition of whole body movements, e.g. for sport training

Abstract

Systems and methods for tracking and analysis physical activity is disclosed. In some aspects, a provided method includes receiving a time sequence of images captured while with an individual is performing the physical activity, and generating, using the time sequence of images, at least one map indicating a movement of the individual. The method also includes identifying at least one body portion using the at least one map, and computing at least one index associated with the identified body portions to characterize the physical activity of the individual. The method further includes generating a report using the at least one index.

Claims

1. A system for analyzing a physical activity of an individual without contacting the individual, the system comprising:

an apparatus configured to capture a time sequence of images of an individual performing a physical activity; and

a processor configured to;

receive the captured time sequence of images;

generate, using the time sequence of images, at least one map indicating movement of the individual;

identify at least one body portion of the individual using the at least one map;

compute at least one index associated with the at least one identified body portion to characterize the physical activity;

generate a report using the at least one index.

2. The system of claim 1, wherein the processor is further configured to utilize an optical flow sensing algorithm to generate the at least one map.

3. The system of claim 1, wherein the processor is further configured to determine at least one of a velocity amplitude and a velocity direction for the at least one body portion using the at least one map.

4. The system of claim 1, wherein the processor is further configured to determine a displacement of the at least one body portion.

5. The system of claim 1, wherein the at least one index includes at least one of an energy expenditure and an intensity.

6. The system of claim 1, wherein the processor is further configured to compute the energy expenditure of the physical activity using a weighted sum of a vertical displacement and a velocity amplitude square of at least one body portion averaged over a duration of the physical activity.

7. The system of claim 1, wherein the processor is further configured to determine the at least one index using a hierarchical algorithm.

8. The system of claim 1, wherein the at least one body portion includes at least one of a head of the individual, a neck of the individual, a trunk of the individual, upper arms of the individual, lower arms of the individual, hands of the individual, upper legs of the individual, lower legs of the individual, and feet of the individual.

9. The system of claim 1, wherein the processor is further configured to count repetitions of the physical activity by tracking a boundary associated with the at least one body portion of the individual.

10. The system of claim 1, wherein the processor is further configured to count repetitions of the physical activity based on an amplitude analysis of an optical flow field.

11. The system of claim 1, wherein the processor is further configured to count repetitions of the physical activity based on a template matching of an oriented histogram of an optical flow field.

12. A method for analyzing physical activity performed by an individual comprising:

a) receiving a time sequence of images captured while with an individual is performing the physical activity;

b) generating, using the time sequence of images, at least one map indicating a movement of the individual;

c) identifying at least one body portion using the at least one map;

d) computing at least one index associated with the identified body portions to characterize the physical activity of the individual; and

f) generating a report using the at least one index.

13. The method of claim 12, wherein the method further comprises utilizing an optical flow sensing algorithm to generate the at least one map.

14. The method of claim 12, wherein the method further comprises determining at least one of a velocity amplitude and a velocity direction for the at least one body portion using the at least one map.

15. The method of claim 12, wherein the method further comprises determining a displacement of the at least one body portion.

16. The method of claim 12, wherein the at least one index includes at least one of an energy expenditure and an intensity.

17. The method of claim 12, the wherein the method further comprises computing the energy expenditure of the physical activity using a weighted sum of a vertical displacement and a velocity amplitude square of at least one body portion averaged over a duration of the physical activity.

18. The method of claim 12, wherein the method further comprises determining the at least one index using a hierarchical algorithm.

19. The method of claim 12, wherein the at least one body portion includes at least one of a head of the individual, a neck of the individual, a trunk of the individual, upper arms of the individual, lower arms of the individual, hands of the individual, upper legs of the individual, lower legs of the individual, and feet of the individual.

20. The method of claim 12, wherein the method further comprises counting repetitions of the physical activity by tracking a boundary associated with the at least one body portion of the individual.

21. The method of claim 20, wherein the method further comprises counting repetitions of the physical activity based one of an amplitude analysis of an optical flow field or a template matching of an oriented histogram of the optical flow field.

22. The method of claim 12, wherein the method further comprises quantifying an energy expenditure of the individual using at least one of a calibration curve and a personal profile of the individual.

23. The method of claim 22, wherein the personal profile of the individual includes at least one of a resting energy expenditure of the individual, a gender of the individual, a weight of the individual, relative weights of different body portions of the individual, and a body surface area of the individual.