Gait pattern analysis for predicting falls

Patent metadata

Field	Value
Publication number	US-9801568-B2
Application number	US-201514591561-A
Country	US
Kind code	B2
Filing date	Jan 7, 2015
Priority date	Jan 7, 2014
Publication date	Oct 31, 2017
Grant date	Oct 31, 2017

Abstract

A method for acquiring gait parameters of an individual is disclosed. The method includes capturing calibration images from foot marker placed on feet or shoes of an individual while an individual is standing still, the calibration images are obtained from a camera worn by the individual, capturing subsequent time-varying images from the foot markers while the individual is walking, and comparing the calibration images to the subsequent time-varying images by a processing unit that is coupled to the camera to determine changes between the initial relative image size of the foot markers and the time-varying images of the foot markers as a function of time to analyze gait of the individual.

First claim

What is claimed is:

1. A method for acquiring gait parameters of an individual, comprising:
capturing calibration images from foot markers placed on feet or shoes of an individual while an individual is standing still, the calibration images are obtained from a camera worn by the individual;
capturing subsequent time-varying images from the foot markers while the individual is walking; and
comparing the calibration images to the subsequent time-varying images by a processing unit that is coupled to the camera to determine changes between the initial relative image size of the foot markers and the time-varying images of the foot markers as a function of time to analyze gait of the individual.

2. The method of claim 1 , the camera is an integral part of the processing unit.

3. The method of claim 1 , the camera physically coupled to the processing unit.

4. The method of claim 1 , the camera electronically coupled to the processing unit.

5. The method of claim 4 , the coupling is by a wireless channel.

6. The method of claim 1 , each of the foot markers includes at least one identifiable feature such that the foot marker can be identified in the images.

7. The method of claim 6 , the identifiable feature is a color.

8. The method of claim 7 , the color is a solid color.

9. The method of claim 6 , the identifiable feature is a pattern.

10. The method of claim 9 , the pattern is a checker pattern.

11. A smart gait analysis system, comprising:
a camera worn by an individual;
a processing unit coupled to the camera;
a left foot marker placed on the left shoe or foot of the individual; and
a right foot marker placed on the right shoe or foot of the individual,
the camera is configured to acquire images from the foot markers as the individual is walking,
the processing unit is configured to
capture calibration images from the foot marker while an individual is standing still obtained from the camera,
capture subsequent time-varying images from the foot markers while the individual is walking, and
compare the calibration images to the subsequent time-varying images to determine changes between the initial relative image size of the foot markers and the time-varying images of the foot markers as a function of time to analyze gait of the individual.

12. The gait analysis system of claim 11 , the camera is an integral part of the processing unit.

13. The gait analysis system of claim 11 , the camera physically coupled to the processing unit.

14. The gait analysis system of claim 11 , the camera electronically coupled to the processing unit.

15. The gait analysis system of claim 14 , the coupling is by a wireless channel.

Assignees

• Purdue Research Foundation

Inventors

• Ziaie Babak
• Kim Albert
• Kim Junyoung
• Rietdyk Shirley

Classifications

• A61B5/112 Primary

  Gait analysis · CPC title

• A61B5/6831

  Straps, bands or harnesses · CPC title

• A61B5/1117

  Fall detection · CPC title

• A61B5/1127

  using markers · CPC title

• A61B5/0013

  Medical image data (A61B1/00011, A61B6/56, A61B8/56 take precedence) · CPC title