METHOD, SYSTEM, AND COMPUTER PROGRAM FOR DETECTING AND CHARACTERIZING MOTION

• US 20090147991A1
• Filed: 12/07/2007
• Published: 06/11/2009
• Est. Priority Date: 12/07/2007
• Status: Active Grant

• Current Assignee: Tom Chau
• Original Assignee: Tom Chau
• Inventors: Chau, Tom
• Granted Patent: US 8,165,345 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: A61F 4/00 Methods or devices enabling patients or disabled persons to operate an apparatus or a device not forming part of the body operating or control means for prostheses A61F2/48, A61F2/68
• CPC Class Codes: G06F 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training

Abstract

A method for motion detection/characterization is provided including the steps of (a) capturing a series of time lapsed images of the target, wherein the target moves between at least two of such images; (b) generating a motion distribution in relation to the target across the series of images; and (c) identifying motion of the target based on analysis of the motion distribution. In a further aspect of motion detection/characterization in accordance with the invention, motion is detected/characterized based on calculation of a color distribution for a series of images. A system and computer program for presenting an augmented environment based on the motion detection/characterization is also provided. An interface means based on the motion detection/characterization is also provided.

Claims

1. A method for detection and/or characterization of motion of a target comprising the steps of:

a. capturing a series of time lapsed images of the target, wherein the target moves as between at least two of such images;

b. generating a motion distribution in relation to the target across the series of images; and

c. identifying motion of the target based on analysis of the motion distribution.

2. The method of claim 1 comprising the further steps of optionally generating a color distribution for the target based on the series of images, and further identifying the motion based on analysis of the color distribution.

3. The method of claim 2 wherein the analysis of the color distribution provides greater specificity to the motion detection and/or characterization.

4. The method of claim 1 wherein the motion distribution is generated based on a probability distribution of differences as between the at least two such images signifying motion in the target.

5. The method of claim 1 wherein the motion distribution is generated by:

a. defining a region of interest for each of the at least two images that corresponds to the target, or movement of the target;

b. comparing the region for each of the at least two images to establish the difference therebetween;

c. estimating the level of activity associated within the region for each of the at least two images; and

d. based on the level of activity determining whether the level of activity connotes motion within the region, or motion having particular characteristics within the region.

6. The method of claim 5 comprising the further step of determining an area within the region where motion is occurring.

7. The method of claim 5 comprising the further step of defining a motion sensitivity level.

8. The method of claim 7 wherein the level of activity is analyzed to determine whether it meets or exceeds the motion sensitivity level.

9. The method of claim 8 wherein the motion sensitivity level is adjustable.

10. The method of claim 8 wherein the motion sensitivity level is defined automatically.

11. The method of claim 2 wherein the color distribution is generated by:

a. defining a region of interest from a plurality of images that correspond to the target, so as to define a first image sample, and a second image sample, each of the first image sample and second image sample including one or more images;

b. calculating the average value of each pixel over the first image sample;

c. establishing the intensity of each image in the second image sample, subtracting the intensity of each such image from the average pixel value in the first image sample, and creating an image model based on such calculations, the image model defining the color distribution.

12. The method of claim 2 wherein the method is operable to adapt to a change in a background scene of the at least two images.

13. The method of claim 5 comprising the further step of ignoring certain of the identified motions by:

a. obtaining the region of interest of each of the at least two images to a first plurality of greyscale representations, or converting the region of interest to the first plurality of greyscale representations;

b. generating a greyscale baseline by averaging, for each pixel in the region of interest, the pixel value of the first plurality of greyscale representations;

c. obtaining a second plurality of greyscale representations of the region of interest of subsequent images, or converting the region of interest of subsequent images to the second plurality of greyscale representations;

d. generating a plurality of averages by averaging, for each pixel in the region of interest, the pixel value of the second plurality of greyscale representations;

e. generating a plurality of fluctuation values by subtracting, for each pixel in the region of interest, the pixel value of the plurality of averages from the pixel value of the greyscale baseline;

f. generating an upper boundary value and a lower boundary value based on a mean and a standard deviation from a statistical distribution of the plurality of fluctuation values;

g. obtaining a single greyscale representation of the region of interest of a further subsequent image, or converting the region of interest of the further subsequent image to the single greyscale representation;

h. generating an average of the sample values generated by subtracting, for each pixel in the region of interest, the pixel value of the single greyscale representations from the pixel value of the greyscale baseline;

i. ignoring detected motion if the average falls between the lower boundary value and the upper boundary value.

14. The method of claim 13 wherein the first plurality of greyscale representations, the second plurality of greyscale representations, and the sample values are buffered.

15. The method of claim 13 wherein the method is operable to adapt to a change in a background scene of the at least two images.

16. An augmented environment system comprising:

a. a computer;

b. an image capture utility linked to or loaded on the computer;

c. optionally, a display linked to the computer;

d. a motion detection/characterization utility linked to the computer or loaded on the computer, the motion detection/characterization utility being operable to;

i. capture a series of time lapsed images of the target, wherein the target moves between at least two of such images;

ii. generate a motion distribution in relation to the target across the series of images; and

iii. identify motion of the target based on analysis of the motion distribution.

17. The system of claim 16 further including an aural output means.

18. The system of claim 16 wherein the system is operable to respond to particular movements of an individual with predetermined sounds.

19. The system of claim 16 wherein the system is operable to function as an input means to the computer or a remote computer linked to the computer.

20. The system of claim 16 wherein the system is operable to function as an input means overlaid on a display.

21. A computer program comprising computer instructions which when made available to a computer are operable to define in relation to the computer a motion detection/characterization utility that is operable to:

a. capture a series of time lapsed images of the target, wherein the target moves between at least two of such images;

b. generate a motion distribution in relation to the target across the series of images; and

c. identify motion of the target based on analysis of the motion distribution.

22. The computer program of claim 21 wherein the motion detection/characterization utility enables a user to interface with a computer program.

23. The computer program of claim 22 wherein the computer program is a computer game.