Systems and methods for sensing occupancy

• US 8,831,287 B2
• Filed: 06/08/2012
• Issued: 09/09/2014
• Est. Priority Date: 06/09/2011
• Status: Expired due to Fees

• Current Assignee: Utah State University
• Original Assignee: Utah State University
• Inventors: Dasu, Aravind, Mathias, Dean, Liu, Chenguang, Christensen, Randy, Christensen, Bruce
• Primary Examiner(s): Thirugnanam, Gandhi
• Application Number:
  US14/124,998
• Publication Number:
  US 20140093130A1
• Time in Patent Office: 823 Days
• Field of Search: 382/103
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/0008 checking presence/absence
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G08B 13/19606 Discriminating between target movement or movement in an area of interest and other non-signicative movements, e.g. target movements induced by camera shake or movements of pets, falling leaves, rotating fan

Abstract

A computer implemented method for sensing occupancy of a workspace includes creating a difference image that represents luminance differences of pixels in past and current images of the workspace resulting from motion in the workspace, determining motion occurring in regions of the workspace based on the difference image, and altering a workspace environment based at least in part on the determined motion. The method also includes determining which pixels in the difference image represent persistent motion that can be ignored and determining which pixels representing motion in the difference image are invalid because the pixels are isolated from other pixels representing motion.

Claims

1. A computer implemented method for sensing occupancy of a workspace, comprising:

creating a difference image that represents luminance differences of pixels between past and current images of the workspace resulting from motion in the workspace;

determining motion occurring in regions of the workspace based on the difference image;

altering a workspace environment based at least in part on the determined motion;

determining which pixels in the difference image represent persistent motion that can be ignored;

determining which pixels representing motion in the difference image are invalid because the pixels are isolated from other pixels representing motion;

determining the number of pixels representing motion in each of a plurality of regions in the workspace and creating a trigger representative of the region having the most pixels representing motion;

evaluating the trigger based on a pre-set priority; and

updating a state machine using a signal representing the evaluated trigger, the state machine controlling the workspace environment.

2. The method of claim 1, wherein creating the difference image includes comparing an absolute value of the difference in luminance between the images to a threshold value, setting a corresponding pixel in the difference image to 1 if the difference is greater than the threshold value, and setting the corresponding pixel in the difference image to 0 if the difference is less than the threshold value.

3. The method of claim 1, further comprising:

comparing every pixel representing motion to immediate neighboring pixels, and if the immediate neighboring pixels are not pixels representing motion, changing a value of the compared pixel representing motion.

4. The method of claim 1, further comprising:

creating a persistence image having a pixel corresponding to each pixel in the difference image, the pixels in the persistence image being incremented in value each time a pixel in the difference image is determined to represent motion.

5. The method of claim 1, further comprising:

creating a motion history image representing how recently motion was detected in each pixel representing motion in the difference image.

6. The method of claim 5, further comprising:

assigning a pixel value to pixels in the motion history image corresponding to pixels in the difference image representing motion, and subtracting from the pixel value each time a pixel in the current image is determined to not represent motion.

7. A computer implemented method for sensing occupancy of a workspace, comprising:

creating a difference image that represents luminance differences of pixels in two sequential images of the workspace resulting from motion in the workspace, the difference image including motion pixels and non-motion pixels;

determining which motion pixels are invalid by comparing the motion pixels to adjacent pixels and changing the motion pixels to non-motion pixels if the adjacent pixels are not also motion pixels;

creating an updated difference image with the pixels changed from motion pixels to non-motion pixels;

altering a workspace environment based at least in part on the updated difference image;

determining the number of motion pixels in each of a plurality of regions in the workspace, and creating a trigger representative of the region which has the most motion pixels; and

updating a state machine using the trigger, the state machine controlling the workspace environment.

8. The method of claim 7, further comprising:

creating a persistence image having a pixel corresponding to each pixel in the difference image, the pixels in the persistence image being incremented in value each time a pixel in the difference image is determined to represent motion.

9. The method of claim 7, further comprising:

creating a motion history image representing how recently motion was detected in each motion pixel.

10. A computer implemented method for sensing occupancy of a workspace, comprising:

creating a difference image that represents luminance differences of pixels in two sequential images of the workspace resulting from motion in the workspace, the difference image including motion pixels and non-motion pixels;

creating a persistence image having pixels corresponding to pixels of the difference image, a value of the pixels in the persistence image being increased each time a corresponding motion pixel is identified in the difference image, the value being decreased when a corresponding non-motion pixel is identified in the difference image, wherein the pixels in the persistence image are ignored when the value exceeds a threshold value; and

altering a workspace environment based at least in part on the persistence and difference images.

11. The method of claim 10, further comprising:

determining motion occurring in regions of the workspace based at least in part on the persistence and difference images.

12. The method of claim 10, further comprising:

creating a motion history image representing how recently motion was detected in each motion pixel.

13. The method of claim 11, further comprising:

determining the number of pixels representing motion in each of the regions in the workspace and creating a trigger representative of the region having the most pixels representing motion.

14. The method of claim 13, further comprising:

evaluating the trigger based on a pre-set priority.

15. The method of claim 13, further comprising:

updating a state machine using a signal representing the trigger, the state machine controlling alterations to the workspace environment.