Video surveillance system

• US 8,605,155 B2
• Filed: 08/07/2007
• Issued: 12/10/2013
• Est. Priority Date: 06/04/2003
• Status: Active Grant

• Current Assignee: Model Software Corporation
• Original Assignee: Model Software Corporation
• Inventors: Kelly, John J III, Miller, J. Matthew III
• Primary Examiner(s): WONG, ALLEN C
• Application Number:
  US11/890,509
• Publication Number:
  US 20080030579A1
• Time in Patent Office: 2,317 Days
• Field of Search: 348/143, 348151-155, 348/169
• US Class Current: 348/154
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30241 Trajectory
• 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 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: G08B 13/19645 Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

Viewing a three dimensional area from numerous camera angles at different exposures using intensity and chromaticity data at the different exposures to create a pixel model for each pixel. A current image is compared with the background model to find pixels that have changed from their pixel model. These novel pixels are processed using contiguous region detection and grouped into foreground figures. For each camera, software extracts features from each foreground figure. A central processor maintains an object model for each foreground figure. A graphical user interface displays the relative location of foreground figures in a world model. The location and identification of the foreground figures is checked against a table of permissions so as to selectively generate an alert. If a figure leaves or is about the leave a cell, the invention accounts for its approximate position and notifies adjacent cells of the expected arrival of the foreground figure.

Claims

1. A video surveillance system, comprising:

a plurality of surveillance cells in a cellular format in which the plurality of surveillance cells operate independently while maintaining a unified global identification system,

wherein each surveillance cell includes at least one video surveillance station and at least one data processor, and each video surveillance station includes at least one video surveillance camera, said surveillance cell maintaining a local object identification assigned to an object in said surveillance cell, said object also having an associated global object identification assigned to the object in all surveillance cells comprising said video surveillance system, and

each surveillance cell receiving information from at least one adjacent surveillance cell to identify adjacent surveillance cells, and wherein said surveillance cells communicate with adjacent surveillance cells, and

wherein said surveillance cell maintains local and global object identifications in a data structure of a computer memory that contains associations between local and global identifications, and processes new objects when a new object enters a cell from outside a coverage of the cell, assigns a local identification comparing the new object to characteristics of an object having a local identification associated with an adjacent cell and a global identification, and determines whether the features from a new object of a surveillance cell exceed a threshold of similar features to, and determines whether the new object of the surveillance cell is within an estimated position of, an object that has left or is leaving an adjacent surveillance cell, and when determination is made that the features from the new object of the surveillance cell exceed the threshold of similar features, and determination is made that the new object is within the estimated position of the object that has left or is leaving the adjacent surveillance cell, the object is given the same global identification with which the object was associated in the adjacent surveillance cell.

2. A system according to claim 1, wherein a first video surveillance station in a first surveillance cell calculates the first position estimate based upon a first vector in real space and a second video surveillance station in an adjacent cell calculates the second position estimate based upon a second vector in real space, and said first and second vectors are compared to determine whether the new object is within the estimated position of an object leaving or having left an adjacent surveillance cell.

3. A system according to claim 1, a control unit interconnected to said surveillance cells for graphically displaying an icon on a video interface based upon a position of the object.

4. A system according to claim 1, a control unit checks the position of the object against a table of permissions.

5. A system according to claim 4, the control unit generating an alarm based upon the position of the object when the check against the table of permission indicates the object is not authorized to be in the object'"'"'s current position.

6. A system in accordance with claim 1, a first region of a surveillance cell being a closed area entry point, the surveillance cell assigning the object an old global identification and an old local identification when features of the object match those of an object associated with the old global identification.

7. A system in accordance with claim 1, a control unit initially assigning the figure a second local identification, the second local identification corresponding to the object in a second region of said surveillance cell until determination is made that the object is the same object as associated with an old local identification of said surveillance cell.

8. A system according to claim 1, wherein when an object leaves a closed area having only one exit, an adjacent surveillance cell to said one exit is notified to expect the object.

9. A system in accordance with claim 1, wherein when an object enters an open area having multiple entrances, the object that enters the open area is assigned a new local and global identification and, if the features extracted from the object are determined to be that of a previously known object, the two objects are connected and given the same global identification.

10. A system in accordance with claim 1, wherein the local object identification includes information that identifies the object as existing within a particular surveillance cell.

11. A system in accordance with claim 1, wherein each surveillance cell queries a server to find out which surveillance cells are nearby.

12. A system in accordance with claim 1, wherein a file that is run at startup of the video surveillance system includes information that identifies which surveillance cells are nearby said surveillance cell.

13. A system in accordance with claim 1, wherein each surveillance cell is configured to communicate with nearby cells by broadcasting each surveillance cell'"'"'s current state.

14. A system in accordance with claim 13, wherein when a surveillance cell communicates with nearby cells, the surveillance cell opens a socket-based-client-server connection with the nearby cells.

15. A system in accordance with claim 1, wherein when a surveillance cells needs information, nearby cells are polled to obtain the needed information.