Object detection

• US 7,184,585 B2
• Filed: 01/14/2004
• Issued: 02/27/2007
• Est. Priority Date: 11/17/2000
• Status: Expired due to Term

• Current Assignee: Columbia Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Honeywell International Inc.
• Inventors: Cofer, Darren Duane, Hamza, Ridha M.
• Primary Examiner(s): COUSO, YON JUNG
• Application Number:
  US10/757,674
• Publication Number:
  US 20040146184A1
• Time in Patent Office: 1,140 Days
• Field of Search: 382/103, 382/141, 382/142, 382/143, 382/144, 382/181, 382/282, 382/283, 348/135, 348/136, 348/143, 348/148, 348/149, 348/152
• US Class Current: 382/141
• 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 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 13/19604 involving reference image or background adaptation with time to compensate for changing conditions, e.g. reference image update on detection of light level change
• 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 method for object detection that utilizes a patterned background. Patterned backgrounds are chosen such that each reference image analyzed will have both light and dark pixels. The method calculates the difference between the expected value for the light pixels and the expected value of the dark pixels in the reference image. This difference is used to chose a threshold value. The difference in expected values for the corresponding pixels in a live image is calculated and compared to the threshold value. If the difference in expected values of the live image are less than the threshold value, object detection is indicated.

Claims

1. A method for detecting an object in an area, comprising:

capturing a reference image of the area without the object present, wherein the area includes an intentionally patterned background with both light areas and dark areas, wherein the light areas and dark areas have an intended interrelationship;

capturing a live image; and

determining if the object is present by comparing the reference image and the live image.

2. A method according to claim 1 wherein the area is at least part of a larger area.

3. A method according to claim 1 further comprising at least one other area that at least partially overlaps the area, and the method further includes the step of determining if the object is present in the at least one other area by comparing the reference image and the live image.

4. A method according to claim 2 wherein the larger area at least partially encircles an area to be monitored.

5. A method according to claim 2 wherein the larger area corresponds to an area to be monitored.

6. A method according to claim 1 wherein the area corresponds to a monitored area.

7. A method according to claim 1 wherein the area is a mask window.

8. A method according to claim 1 wherein the patterned background includes an approximately equal amount of light areas and dark areas.

9. A method according to claim 1 wherein the patterned background includes a number of parallel extending light areas and dark areas.

10. A method according to claim 1 wherein the patterned background includes a checkerboard pattern of light areas and dark areas.

11. A method according to claim 1 wherein the light areas and/or dark areas each have a size that is smaller than the object.

12. A method according to claim 1 wherein the determining step comprises the steps of:

determining a difference image by determining a difference in intensity between corresponding locations of the reference image and the live image; and

determining if at least a portion of the difference image includes a complement or inverse image of the object.

13. A method according to claim 1 wherein the determining step comprises the steps of:

determining a difference image by determining a difference in intensity between corresponding locations of the reference image and the live image; and

determining if the intensity of at least part of the difference image exceeds a threshold value.

14. A method for detecting an object in an area, comprising:

providing a patterned background in the area, wherein the patterned background includes both light areas and dark areas with an intended interrelationship;

capturing a reference image of the area without the object present;

capturing a live image of the area; and

determining if the object is present in the area by comparing the reference image and the live image.

15. A method according to claim 14 wherein the area corresponds to an area of a floor, and the patterned background is fixed to the area of the floor.

16. A method according to claim 15 wherein the patterned background is painted on the area of the floor.

17. An object detection system, comprising:

a patterned background fixed to an area, wherein the patterned background includes both light areas and dark areas with an intended interrelationship;

an image capture device for capturing a reference image of the area without the object present, and a live image of the area; and

a processing element for determining if the object is present in the area by comparing the reference image and the live image.

18. An object detection system according to claim 17 wherein the area is at least part of a larger area.

19. An object detection system according to claim 18 wherein the larger area at least partially encircles an area to be monitored.

20. An object detection system according to claim 18 wherein the larger area corresponds to an area to be monitored.

21. An object detection system according to claim 17 wherein the area corresponds to a monitored area.

22. An object detection system according to claim 17 wherein the patterned background includes an approximately equal amount of light areas and dark areas.

23. An object detection system according to claim 17 wherein the patterned background includes a number of parallel extending light areas and dark areas.

24. An object detection system according to claim 17 wherein the patterned background includes a checkerboard pattern of light areas and dark areas.

25. An object detection system according to claim 24 wherein the light areas and/or dark areas each have a size that is smaller than the object.