Method and apparatus for detecting objects

• US 6,841,780 B2
• Filed: 01/17/2002
• Issued: 01/11/2005
• Est. Priority Date: 01/19/2001
• Status: Expired due to Term

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Gierczak, Marek, Hamza, Rida M., Cofer, Darren D.
• Primary Examiner(s): Fulton, Christopher W.
• Assistant Examiner(s): Gonzalez, Madeline
• Application Number:
  US10/052,953
• Publication Number:
  US 20020125435A1
• Time in Patent Office: 1,090 Days
• Field of Search: 250/341.1, 250/341.8, 382/107, 382/103, 348/143, 348/152
• US Class Current: 250/341.1
• CPC Class Codes: G01B 11/25 by projecting a pattern, e.g. one or more lines, moiré fringes on the object G01B11/255 takes precedence ; image analysis for depth or shape recovery G06T7/50
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06V 10/145 Illumination specially adapted for pattern recognition, e.g. using gratings
• 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 13/19686 Interfaces masking personal details for privacy, e.g. blurring faces, vehicle license plates

Abstract

An object detection system is provided that projects one or more patterns onto a monitored area, captures one or more live images of the monitored area, and detects objects that enter the monitored area by detecting changes in the one or more patterns in the live images. Such an object detection system may be less susceptible to dynamic lighting conditions, and more sensitive to object motion and/or presence.

Claims

1. A method for detecting an object entering a monitored area, the method comprising the steps of:

projecting a pattern onto the monitored area, the pattern defining one or more lighter regions and one or more darker regions;

capturing a live image of the monitored area, including the pattern; and

detecting an object entering the monitored area when a change is detected in the pattern in the live image.

2. A method according to claim 1 wherein the detecting step detects an object entering the monitored area when the change in the pattern exceeds a predetermined threshold.

3. A method according to claim 1 further comprising the steps of:

capturing a reference image of the monitored area, including the pattern; and

comparing the reference image and the live image to detect a change in the pattern in the live image.

4. A method according to claim 3 wherein the reference image and the live image each have a number of mask windows, and wherein the comparing step compares selected mask windows of the reference image to selected mask windows of the live image.

5. A method according to claim 4 wherein the comparing step compares the selected mask windows of the reference image and the live image using one or more comparing algorithms.

6. A method according to claim 5 wherein the comparing step compares two or more of the selected mask windows using different comparing algorithms.

7. A method according to claim 4 further comprising the step of performing a predefined action if the detecting step detects an object entering one of the selected mask windows.

8. A method according to claim 7 wherein the predefined action is different depending on in which mask window an object is detected.

9. A method according to claim 1 wherein the pattern is a static pattern.

10. A method according to claim 1 wherein the pattern is a dynamic pattern.

11. The method according to claim 1 wherein the pattern includes two or more darker regions, wherein at least selected darker regions are separated from an adjacent darker region by a lighter region.

12. The method according to claim 1 wherein the pattern includes two or more lighter regions and two or more darker regions.

13. A method for detecting an object entering a monitored area, the method comprising the steps of:

illuminating the monitored area with a first pattern;

creating moiré

interference bands by imposing a second pattern shifted relative to the first pattern;

capturing a live image of the monitored area, including the moiré

interference bands; and

detecting an object entering the monitored area when a change is detected in the moiré

interference bands in the live image.

14. A method according to claim 13 wherein the detecting step detects an object entering the monitored area when the change in moiré

the interference bands exceeds a predetermined threshold.

15. A method according to claim 13 further comprising the steps of:

capturing a reference image of the monitored area, including the moiré

interference bands; and

comparing the reference image and the live image to detect a change in the moiré

interference bands in the live image.

16. A method according to claim 15 wherein the comparing step includes subtracting at least part of the live image from at least part of the reference image or visa-versa.

17. A method according to claim 13 wherein the moiré

interference bands are created by illuminating the monitored area with the second pattern.

18. A method according to claim 13 wherein the moiré

interference bands are created by providing a mask or grating having the second pattern between the monitored area and an image capture device.

19. A method according to claim 13 wherein the moiré

interference bands are created by digitally imposing the second pattern on the live image.

20. A method according to claim 13, wherein the reference image of the monitored area and the live image of the monitored area are captured with a sensor.

21. A method according to claim 20, wherein the first pattern is illuminated using light from a specified spectral region and the sensor is attuned to the spectral region.

22. A method according to claim 21, wherein the specified spectral region is near infrared.

23. A method according to claim 13, wherein the first pattern is illuminated using light from a first illumination source, and the second pattern is imposed using a second illumination source.

24. A method for detecting an object entering a monitored area, the method comprising the steps of:

illuminating the monitored area with a first pattern;

creating moiré

interference bands by imposing a second pattern that is different relative to the first pattern;

capturing a reference image of the monitored area;

capturing a live image of the monitored area, including the moiré

interference bands; and

detecting an object in the monitored area when a change is detected in the moiré

interference bands in the live image, and wherein the interference bands of the reference image are compared with the live image using a Radon filter oriented perpendicular relative to the interference bands.

25. A method for detecting an object in a monitored area comprising:

illuminating the monitored area with a specified pattern having bright areas and dark areas, each with a brightness level;

capturing a plurality of reference image mask windows, each mask window covering at least part of the monitored area;

for each reference image mask window, calculating a difference between the brightness levels corresponding to the light areas in the mask window and the brightness levels corresponding to the dark areas in the mask window;

for each reference image mask window, capturing a corresponding live image mask window;

for each live image mask window, calculating a difference between the brightness levels corresponding to the light areas in the mask window and the brightness levels corresponding to the dark areas in the mask window; and

indicating that an object has been detected when, for any mask window, the difference calculated for the live image is different from the corresponding difference calculated for the reference image by at least a specified threshold value.

26. A method according to claim 25 wherein the illuminating step includes illuminating the monitored area with a first specified pattern and a second specified pattern to create one or more moiré

interference bands.