METHOD AND SYSTEM FOR BACKGROUND ESTIMATION IN LOCALIZATION AND TRACKING OF OBJECTS IN A SMART VIDEO CAMERA

• US 20080285797A1
• Filed: 05/15/2007
• Published: 11/20/2008
• Est. Priority Date: 05/15/2007
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Digisensory Technologies Pty., Ltd.
• Inventors: Hammadou, Tarik
• Granted Patent: US 7,961,946 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 10/422 for representing the structure of the pattern or shape of an object therefor
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

Aspects of a method and system for change detection in localization and tracking of objects in a smart video camera are provided. A programmable surveillance video camera comprises processors for detecting objects in a video signal based on an object mask. The processors may generate a textual representation of the video signal by utilizing a description language to indicate characteristics of the detected objects, such as shape, texture, color, and/or motion, for example. The object mask may be based on a detection field value generated for each pixel in the video signal by comparing a first observation field and a second observation field associated with each of the pixels. The first observation field may be based on a difference between an input video signal value and an estimated background value while the second observation field may be based on a temporal difference between first observation fields.

Claims

1. A method for image processing, the method comprising:

detecting within a programmable surveillance video camera one or more objects in a video signal based on an object mask generated from said video signal; and

generating within said programmable surveillance video camera a textual representation of at least a portion of said video signal by utilizing a description definition language (DDL) to indicate characteristics of said detected one or more objects.

2. The method according to claim 1, comprising generating said object mask based on a detection field value generated for each pixel in at least a portion of said video signal by comparing a first observation field and a second observation field associated with each of said pixels.

3. The method according to claim 2, wherein said detection field value for each of said pixels is a Boolean value.

4. The method according to claim 2, comprising generating said second observation field associated with each of said pixels based on a temporal difference between a previous value of said first observation field and a factored (N) current value of said first observation field for each of said pixels.

5. The method according to claim 2, comprising generating an estimated background value for each of said pixels.

6. The method according to claim 5, comprising generating said first observation field associated with each of said pixels based on a difference between an input video signal value and said generated estimated background value for each of said pixels.

7. The method according to claim 1, wherein said characteristics of said one or more objects comprise one or more of the following:

shape, texture, color, motion, sequence name, location, links, and alarm type.

8. A machine-readable storage having stored thereon, a computer program having at least one code section for image processing, the at least one code section being executable by a machine for causing the machine to perform steps comprising:

detecting within a programmable surveillance video camera one or more objects in a video signal based on an object mask generated from said video signal; and

generating within said programmable surveillance video camera a textual representation of at least a portion of said video signal by utilizing a description definition language (DDL) to indicate characteristics of said detected one or more objects.

9. The machine-readable storage according to claim 8, comprising code for generating said object mask based on a detection field value generated for each pixel in at least a portion of said video signal by comparing a first observation field and a second observation field associated with each of said pixels.

10. The machine-readable storage according to claim 9, wherein said detection field value for each of said pixels is a Boolean value.

11. The machine-readable storage according to claim 9, comprising code for generating said second observation field associated with each of said pixels based on a temporal difference between a previous value of said first observation field and a factored (N) current value of said first observation field for each of said pixels.

12. The machine-readable storage according to claim 9, comprising code generating an estimated background value for each of said pixels.

13. The machine-readable storage according to claim 12, comprising code for generating said first observation field associated with each of said pixels based on a difference between an input video signal value and said generated estimated background value for each of said pixels.

14. The machine-readable storage according to claim 8, wherein said characteristics of said one or more objects comprise one or more of the following:

shape, texture, color, motion, sequence name, location, links, and alarm type.

15. A system for image processing, the system comprising:

one or more processors within a programmable surveillance video camera that enable detecting one or more objects in a video signal based on an object mask generated from said video signal; and

said one or more processors enable generating a textual representation of at least a portion of said video signal by utilizing a description definition language (DDL) to indicate characteristics of said detected one or more objects.

16. The system according to claim 15, wherein said one or more processors enable generating said object mask based on a detection field value generated for each pixel in at least a portion of said video signal by comparing a first observation field and a second observation field associated with each of said pixels.

17. The system according to claim 16, wherein said detection field value for each of said pixels is a Boolean value.

18. The system according to claim 16, wherein said one or more processors enable generating said second observation field associated with each of said pixels based on a temporal difference between a previous value of said first observation field and a factored (N) current value of said first observation field for each of said pixels.

19. The system according to claim 16, wherein said one or more processors enable generating an estimated background value for each of said pixels.

20. The system according to claim 19, wherein said one or more processors enable generating said first observation field associated with each of said pixels based on a difference between an input video signal value and said generated estimated background value for each of said pixels.

21. The system according to claim 15, wherein said characteristics of said one or more objects comprise one or more of the following:

shape, texture, color, motion, sequence name, location, links, and alarm type.