System for automated screening of security cameras

• US 20010033330A1
• Filed: 02/01/2001
• Published: 10/25/2001
• Est. Priority Date: 02/04/2000
• Status: Active Grant

• Current Assignee: CheckVideo, LLC (Kastle Systems International LLC)
• Original Assignee: Cernium Corporation (Kastle Systems International LLC)
• Inventors: Garoutte, Maurice V.
• Granted Patent: US 6,940,998 B2
• Time in Patent Office: Days
• US Class Current: 348/153
• 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: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

The present invention involves a system for automatically screening closed circuit television (CCTV) cameras for large and small scale security systems, as used for example in parking garages. The system includes six primary software elements, each of which performs a unique function within the operation of the security system to provide intelligent camera selection for operators, resulting in a marked decrease of operator fatigue in a CCTV system. Real-time image analysis of video data is performed wherein a single pass of a video frame produces a terrain map which contains parameters indicating the content of the video. Based on the parameters of the terrain map, the system is able to make decisions about which camera an operator should view based on the presence and activity of vehicles and pedestrians, furthermore, discriminating vehicle traffic from pedestrian traffic. The system is compatible with existing CCTV (closed circuit television) systems and is comprised of modular elements to facilitate integration and upgrades.

Claims

1. A method for real-time analysis of video image data, said method comprising the steps of:

(a) performing a single pass through a frame of said video image data; and

(b) generating a terrain map from said pass through said frame of said video image data, said terrain map comprising a plurality of parameters wherein said parameters indicate the content of said video image data.

2. The method according to

claim 1

, wherein said parameters are generated by color space calculations, said color space calculations comprising a color degree parameter which measures how far a color is from gray scale.

3. The method according to

claim 1

, wherein said parameters are generated by color space calculations, said color space calculations comprising a color direction parameter which measures color based on a two-dimensional color analysis.

4. The method according to

claim 1

, wherein said parameters further comprise an average altitude parameter which measures an average value of four pixels in the center of a 2×

2 kernel in said frame of said video image data.

5. The method according to

claim 4

, wherein said parameters further comprise a degree of slope parameter which measures an absolute difference between a highest average value and a lowest average value calculated by said average altitude.

6. The method according to

claim 4

, wherein said parameters further comprise a direction of slope parameter which measures a direction of slope based on a highest average value and a lowest average value calculated by said average altitude.

7. The method according to

claim 1

, wherein said parameters further comprise a horizontal smoothness parameter which measures a consistency of change in horizontal direction from a lowest pixel to a highest pixel in said frame of said video image data.

8. The method according to

claim 1

, wherein said parameters further comprise a vertical smoothness parameter which measures a consistency of change in vertical direction from a lowest pixel to a highest pixel in said frame of said video image data.

9. The method according to

claim 1

, wherein said parameters further comprise a jaggyness parameter which measures an offset in pixels between odd and even fields for a target segmented from said frame of said video image data.

10. The method according to

claim 1

, wherein said real-time analysis discriminates between vehicular traffic and pedestrian traffic.

11. The method according to

claim 10

, wherein said real-time analysis further comprises a maintain background function wherein a background is segregated from a moving target by averaging said video image data which contains no said moving target and said moving target is further analyzed to determine if said moving target is a pedestrian or a vehicle.

12. The method according to

claim 1

, wherein said realtime analysis recognizes at least one event which defines the presence of or change in a target within said video image data.

13. The method according to

claim 12

, wherein said events comprise one or more of the following:

presence of a single person;

presence of multiple people;

fast person;

fallen person;

lurking person;

erratic person;

converging people;

presence of a single vehicle;

presence of multiple vehicles;

fast vehicle;

or

sudden stop vehicle.

14. The method according to

claim 1

, wherein said parameters further comprise:

a color degree parameter which measures how far a color is from gray scale;

a color direction parameter which measures color based on a two-dimensional color analysis;

an average altitude parameter which measures an average value of four pixels in the center of a 2×

2 kernel in said frame of said video image data;

a degree of slope parameter which measures an absolute difference between a highest average value and a lowest average value calculated by said average altitude;

direction of slope parameter which measures a direction of slope based on said highest average value and said lowest average value calculated by said average altitude;

a horizontal smoothness parameter which measures a consistency of change in horizontal direction from a lowest pixel to a highest pixel in said frame of said video image data;

a vertical smoothness parameter which measures a consistency of change in vertical direction from a lowest pixel to a highest pixel in said frame of said video image data; and

a jaggyness parameter which measures an offset in pixels between odd and even fields for a target segmented from said frame of said video image data.

15. The method according to

claim 1

, wherein said parameters further comprise:

an average altitude parameter which measures an average value of four pixels in the center of a 2×

2 kernel in said frame of said video image data;

a degree of slope parameter which measures an absolute difference between a highest average value and a lowest average value calculated by said average altitude;

direction of slope parameter which measures a direction of slope based on said highest average value and said lowest average value calculated by said average altitude;

a horizontal smoothness parameter which measures a consistency of change in horizontal direction from a lowest pixel to a highest pixel in said frame of said video image data;

a vertical smoothness parameter which measures a consistency of change in vertical direction from a lowest pixel to a highest pixel in said frame of said video image data; and

a jaggyness parameter which measures an offset in pixels between odd and even fields for a target segmented from said frame of said video image data.

16. A method for real-time analysis of video image data, said method comprising the steps of:

(a) performing a single pass through a frame of said video image data; and

(b) generating a terrain map from said pass through said frame of said video image data, said terrain map comprising a color space calculation wherein said color space calculation comprises;

a color degree parameter which measures how far a color is from gray scale; and

a color direction parameter which measures color based on a two-dimensional color analysis.

17. A computer system for automated screening of security cameras, said computer system in communication with a plurality of video cameras and comprising real-time image analysis components wherein video image data from said video cameras is analyzed by said image analysis components and said video image data is then selectively presented to an operator for security monitoring.

18. The computer system according to

claim 17

, wherein said computer system further comprises:

at least one video worker, said video worker capturing video image data from said security cameras;

at least one analysis worker, said analysis worker receiving said video data from said video worker and performing image analysis on said video data;

at least one video supervisor, said video supervisor controlling said reception of video data of said analysis worker from said video worker;

at least one node manager, said node manager receiving said video data from said video worker;

a set rules graphical user interface (GUI), said GUI providing an interface to said computer system for required configuration data for said computer system; and

a system arbitrator, said system arbitrator receiving said video data from said node manager and in communication with said set rules GUI,

wherein said arbitrator selectively sends said video data to an operator for security monitoring purposes.

19. The computer system according to

claim 18

, wherein said analysis worker further comprises a library of functions, wherein said functions manipulate said video data.

20. The computer system according to

claim 19

wherein said functions further comprise:

color space calculations, said color space calculations comprising;

a color degree parameter which measures how far a color is from gray scale; and

a color direction parameter which measures color based on a two-dimensional color analysis.

21. The computer system according to

claim 17

, said computer system further comprising:

a pan-tilt-zoom control for manual control of said security cameras by said operator.

22. The computer system according to

claim 17

, said computer system further comprising:

an operator console, said operator console comprising a plurality of video monitors;

a central switch which receives input from said security cameras; and

at least one quad splitter, said quad splitter receiving said video data from said central switch and sending multiple video scenes to one of said video monitors.