Method and apparatus for maintaining a background image model in a background subtraction system using accumulated motion

• US 20070177800A1
• Filed: 02/02/2006
• Published: 08/02/2007
• Est. Priority Date: 02/02/2006
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Connell, Jonathan
• Application Number:
  US11/345,854
• Publication Number:
  US 20070177800A1
• Time in Patent Office: Days
• US Class Current: 382/181
• CPC Class Codes: G06V 10/28 Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

Methods and apparatus are provided for maintaining a background image model in a background subtraction system using accumulated motion. A background image model is maintained by obtaining a map of accumulated motion; and adjusting the background image model based on the map of accumulated motion. The map of accumulated motion may be obtained, for example, based on one or more of motion field images; stability maps; frame differences; or information from a background subtraction system. Objects can be added to or removed from the background model or the background model can be otherwise updated. One or more pixels from an image are added to the background image model if a stability measure for the one or more pixels satisfies a predefined criteria. A portion of the background image model can be invalidated in regions where the map of accumulated motion exceeds a predefined threshold.

Claims

1. A method for maintaining a background image model, comprising:

obtaining a map of accumulated motion; and

adjusting said background image model based on said map of accumulated motion.

2. The method of claim 1, wherein said step of obtaining a map of accumulated motion further comprises the step of obtaining one or more motion field images.

3. The method of claim 1, wherein said step of obtaining a map of accumulated motion further comprises the step of obtaining one or more stability maps.

4. The method of claim 1, wherein said step of obtaining a map of accumulated motion further comprises the step of maintaining a counter indicating a degree of motion in a portion of a sequence of images.

5. The method of claim 1, wherein said map of accumulated motion is obtained based on frame differences.

6. The method of claim 1, wherein said map of accumulated motion is obtained based on information from a background subtraction system.

7. The method of claim 1, wherein said adjusting step further comprises the step of adding an object to said background model.

8. The method of claim 1, wherein said adjusting step further comprises the step of removing an object from said background model.

9. The method of claim 1, wherein said adjusting step further comprises the updating said background model.

10. The method of claim 1, wherein said adjusting step further comprises the updating said background model on a pixel-by-pixel basis.

11. The method of claim 1, wherein said adjusting step further comprises the updating said background model on an object level.

12. The method of claim 1, further comprising the step of adding one or more pixels from an image to said background image model if a stability measure for said one or more pixels satisfies a predefined criteria.

13. The method of claim 1, wherein said adjusting step further comprises the step of invalidating a portion of said background image model in regions where said map of accumulated motion exceeds a predefined threshold.

14. The method of claim 1, wherein said adjusting step further comprises the step of copying a portion of an image to said background image model if a stability measure satisfies a predefined criteria.

15. The method of claim 1, wherein said adjusting step further comprises the step of updating said background image model over time if a stability measure satisfies a predefined criteria.

16. The method of claim 1, further comprising the step of determining whether an object has been added to or deleted from an image by examining edge information associated with an object.

17. The method of claim 16, wherein an added object has a detectable intensity boundary and a removed object exposes an underlying homogeneous region in an environment.

18. A system for maintaining a background image model, comprising:

a memory; and

at least one processor, coupled to the memory, operative to;

obtain a map of accumulated motion; and

adjust said background image model based on said map of accumulated motion.

19. The system of claim 18, wherein said processor is further configured to obtain one or more of motion field images and stability maps.

20. The system of claim 18, wherein said processor is further configured to maintain a counter indicating a degree of motion in a portion of a sequence of images.

21. The system of claim 18, wherein said map of accumulated motion is obtained based on one or more of frame differences;

or information from a background subtraction system.

22. The system of claim 18, wherein said processor is further configured to add an object to said background model, remove an object from said background model or update said background model.

23. The system of claim 18, wherein said processor is further configured to add one or more pixels from an image to said background image model if a stability measure for said one or more pixels satisfies a predefined criteria.

24. The system of claim 18, wherein said processor is further configured to invalidate a portion of said background image model in regions where said map of accumulated motion exceeds a predefined threshold.

25. The system of claim 18, wherein said processor is further configured to copy a portion of an image to said background image model if a stability measure satisfies a predefined criteria.

26. The system of claim 18, wherein said processor is further configured to update said background image model over time if a stability measure satisfies a predefined criteria.

27. An article of manufacture for maintaining a background image model, comprising a machine readable medium containing one or more programs which when executed implement the steps of:

obtaining a map of accumulated motion; and

adjusting said background image model based on said map of accumulated motion.