Non-motion detection

• US 20050036658A1
• Filed: 11/21/2002
• Published: 02/17/2005
• Est. Priority Date: 11/21/2001
• Status: Active Grant

• Current Assignee: iOmniscient Pty Ltd.
• Original Assignee: iOmniscient Pty Ltd.
• Inventors: Brooks, Michael J., Gibbins, Daniel, Newsam, Garry
• Granted Patent: US 7,688,997 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• 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
• 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
• CPC Class Codes: G08B 13/19682 Graphic User Interface [GUI] presenting system data to the user, e.g. information on a screen helping a user interacting with an alarm system
• CPC Class Codes: G08B 13/19693 using multiple video sources viewed on a single or compound screen

Abstract

An image sequence derived from area surveillance is considered as a collection of independent time series, each of which describes an image feature that summarises a small neighbourhood of the image. These time series are regarded as samples from some underlying distribution, and statistical techniques are used to identify the density function of this distribution. The background can then be identified as a feature of this distribution, moreover the distribution of features in subsequent image frames can be monitored to see if it deviates sufficiently from the current distributions to indicate a change in the background.

Claims

1. A method of detecting background changes in a visual scene, the method comprising the steps of:

capturing images of the scene into which objects enter and from which objects leave;

generating a first probabilistic measure of the scene indicative of a relatively static background of the scene;

generating a second probabilistic measure of the scene indicative of a relatively dynamic transient objects entering and leaving the scene; and

detecting whether the second probabilistic measure deviates from the first probabilistic measure, indicating that an object entering the scene has not left the scene.

2. The method as claimed in claim 1, wherein respective first and second probability measures are generated for multiple regions of the scene.

3. The method as claimed in claim 1, wherein the first probabilistic measure comprises a mode of a probability density function of pixel values.

4. The method as claimed in claim 3, wherein the probability density function is constructed as a histogram of pixel values.

5. The method as claimed in claim 1, wherein the second probabilistic measure comprises a mode of a probability density function of pixel values.

6. The method as claimed in claim 5, wherein the probability density function is constructed as a histogram of pixel values.

7. The method as claimed in claim 1, wherein the first probabilistic measure is based upon a first, relatively long time period indicative of the static nature of the background of the scene.

8. The method as claimed in claim 1, wherein the second probabilistic measure is based upon a second relatively short time period indicative of the dynamic nature of the transient objects entering and leaving the scene.

9. The method as claimed in claim 1, further comprising the step of alerting an operator to the detected object.

10. The method as claimed in claim 1, further comprising the step of pre-processing the captured images to improve detection of objects.

11. The method as claimed in claim 1, further comprising the step of detecting regions of motion in the scene and removing such regions from further consideration.

12. The method as claimed in claim 1, further comprising the step of checking whether detected objects satisfy a predetermined object recognition criterion.

13. Computer software, recorded on a medium and operable on a computer system, for detecting background changes in a visual scene, the computer software comprising:

software code means for receiving image data for a scene into which objects enter and from which objects leave;

software code means for generating a first probabilistic measure of the scene indicative of a relatively static background of the scene;

software code means for generating a second probabilistic measure of the scene indicative of a relatively dynamic transient objects entering and leaving the scene; and

software code means for detecting whether the second probabilistic measure deviates from the first probabilistic measure, indicating that an object entering the scene has not left the scene.

14. A computer system for detecting background changes in a visual scene, the apparatus comprising:

an input port for accepting images of the scene into which objects enter and from which objects leave;

process means for;

(i) generating a first probabilistic measure of the scene indicative of a relatively static background of the scene,

(ii) generating a second probabilistic measure of the scene indicative of a relatively dynamic transient objects entering and leaving the scene, and

(iii) detecting whether the second probabilistic measure deviates from the first probabilistic measure, indicating that an object entering the scene has not left the scene; and

an interface for alerting an operator to the detected object.