Cooperative camera network

• US 7,149,325 B2
• Filed: 06/21/2002
• Issued: 12/12/2006
• Est. Priority Date: 04/19/2001
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Morellas, Vassilios, Pavlidis, Ioannis
• Primary Examiner(s): Tran, Phuoc
• Application Number:
  US10/177,688
• Publication Number:
  US 20030040815A1
• Time in Patent Office: 1,635 Days
• Field of Search: 382/103, 382/165, 382/170, 382/270, 348/154
• US Class Current: 382/103
• CPC Class Codes: G06F 3/005 Input arrangements through a video camera
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• CPC Class Codes: G06V 10/28 Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
• CPC Class Codes: G06V 10/62 relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
• 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: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

A cooperative camera network involving segmenting an image of an object and extracting a color signature from it. The color signature may be matched with the other signatures in an attempt to identify the object. There also can be combining and fusing the tracking of people and objects with image processing and the identification of the people and objects being tracked in an area or facility.

Claims

1. A cooperative camera network station comprising:

at least one camera;

an initialization component connected to said at least one camera;

a differencing component connected to said at least one camera; and

a color signature extraction component connected to said differencing component.

2. The cooperative camera network of claim 1, further comprising a thresholding component connected to said differencing component.

3. The network of claim 2, further comprising:

a database component connected to said color signature extraction component; and

a color signature matching component connected to said database component.

4. The network of claim 2, further comprising:

a display function connected to said color signature matching component; and

a distributed database component connected to said database component.

5. A method for identifying an object comprising:

obtaining a first image of a scene;

obtaining a second image of the scene;

differencing the first and second images into a segmented image having substantially dissimilar regions of the first and second images retained;

thresholding regions that have a set threshold level of dissimilarity and adding them to the segmented image; and

extracting a color signature from the segmented image; and

matching the color signature with a color signature in a database.

6. The method of claim 5, wherein said extracting the color signature comprises attaining a histogram of the segmented image.

7. The method of clam 6, wherein the histogram comprises the number of pixels in the segmented image for each color value of a range of color values for a first color.

8. The method of claim 7, further comprising matching the histogram with a histogram of the color signature in the database.

10. The method of claim 9, further comprising repeating the method of claims 8 and 9 for any other color signature in the database.

9. A method for identifying an object comprising:

obtaining a first image of a scene;

obtaining a second image of the scene;

differencing the first and second images into a segmented image having substantially dissimilar regions of the first and second images retained;

thresholding regions that have a set threshold level of dissimilarity and adding them to the segmented image; and

extracting a color signature from the segmented image by attaining a histogram of the segmented image, wherein the histogram comprises the number of pixels in the segmented image for each color value of a range of color values for a first color;

matching the color signature with a color signature in a database; and

matching the histogram with a histogram of the color signature in the database by

selecting color values that have pixels in both histograms;

noting the smaller number of pixels of the two numbers for each selected color value;

adding the smaller numbers of pixels of all of the selected color values to a first sum;

adding up the numbers of pixels for all of the color values of the histogram of the segmented image to a second sum;

dividing the first sum by the second sum to attain a value of a match of the color signature in the database with the color signature of the segmented image, for the first color.

11. The method of claim 9, further comprising repeating the method of claim 9 for a second color.

12. The method of claim 11, further comprising repeating the method of claim 9 for a third color.

13. An identification system comprising:

means for imaging;

means for initializing connected to said means for imaging;

means for storing data connected to said means for imaging;

means for segmenting connected to said means for storing data; and

means for identifying connected to said means for storing data, wherein said means for identifying comprises;

means for determining a color signature of an image; and

means for comparing the color signature with at least another color signature.

14. The identification system of claim 13, wherein said means for identifying further comprises means for selecting color signatures from said means for storing data that match to a selected level the color signature of the image.

15. The identification system of claim 14, wherein said means for determining a color signature measures a color value of each pixel of the image for one color.

16. The identification system of claim 15, wherein said means for determining a color signature measures a color value of each pixel of the image for each of three colors.