Virtual fence

• US 8,390,685 B2
• Filed: 02/06/2008
• Issued: 03/05/2013
• Est. Priority Date: 02/06/2008
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Connell, Jonathan H. II
• Primary Examiner(s): Backer, Firmin
• Assistant Examiner(s): ALGIBHAH, HAMZA N
• Application Number:
  US12/026,698
• Publication Number:
  US 20090195654A1
• Time in Patent Office: 1,854 Days
• Field of Search: 348/154
• US Class Current: 348/154
• 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 13/19641 Multiple cameras having overlapping views on a single scene
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

The present invention is directed to a virtual fence provided using a plurality of video cameras. A method for providing a virtual fence in accordance with an embodiment includes: positioning a plurality of video cameras about a perimeter to be monitored, the perimeter comprising a plurality of designated areas; for each of the designated areas: capturing video data of the designated area using at least one video camera; analyzing the captured video data to detect an event; and sending at least one of image or video data to a central facility only in response to the detection of the event.

Claims

1. A method for providing a virtual fence, comprising:

positioning a plurality of video cameras about a perimeter to be monitored, the perimeter comprising a plurality of designated areas and completely encircling an area, wherein positioning a plurality of video cameras comprises;

providing a series of poles about the perimeter to be monitored, wherein each designated area comprises an area between a respective pair of the poles;

mounting a pair of video cameras on each of the poles, wherein a first of each pair of video cameras mounted on each pole is directed toward a previous pole in the series of poles, and a second of each pair of video cameras mounted on each pole is directed toward a next pole in the series of poles, such that an overlap in coverage between the video data of the first and second video cameras of each pair of video cameras is provided in each designated area;

for each of the designated areas;

capturing video data in a thin strip in the designated area using a pair of the video cameras on two adjacent poles;

analyzing the captured video data to detect an event; and

sending at least one of an alarm, image data, or video data to a central facility only in response to the detection of the event.

2. The method of claim 1, wherein analyzing the captured video data to detect an event further comprises:

performing moving object detection on the captured video data.

3. The method of claim 2, wherein detecting an event further comprises:

detecting when a track of an object crosses into or out of the encircled area of the perimeter via the designated area.

4. The method of claim 2, wherein detecting an event further comprises:

detecting a size of an object crossing the designated area; and

limiting the detection of an event to an object having at least a predetermined size.

5. The method of claim 1, further comprising:

associating a processing unit with each pole for analyzing the captured video.

6. A virtual fence, comprising:

a plurality of video cameras positioned about a perimeter to be monitored, the perimeter comprising a plurality of designated areas and completely encircling an area, wherein the plurality of video cameras are positioned on a series of poles about the perimeter to be monitored, wherein each designated area comprises an area between a respective pair of the poles, wherein a pair of video cameras are mounted on each of the poles, wherein a first of each pair of video cameras mounted on each pole is directed toward a previous pole in the series of poles, and a second of each pair of video cameras mounted on each pole is directed toward a next pole in the series of poles, such that an overlap in coverage between the video data of the first and second video cameras of each pair of video cameras is provided in each designated area;

for each of the designated areas;

a pair of the video camera cameras on two adjacent poles for capturing video data in a thin strip in the designated area;

a system for analyzing the captured video data to detect an event; and

a system for sending at least one of an alarm, image data, or video data to a central facility only in response to the detection of the event.

7. The virtual fence of claim 6, wherein the system for analyzing the captured video data to detect an event further comprises:

a system for performing moving object detection on the captured video data.

8. The virtual fence of claim 7, wherein the system for analyzing the captured video data to detect an event further comprises:

a system for detecting when a track of an object crosses into or out of the encircled area of the perimeter via the designated area.

9. The virtual fence of claim 7, wherein the system for analyzing the captured video data to detect an event further comprises:

a system for detecting a size of an object crossing the designated area; and

a system for limiting the detection of an event to an object having at least a predetermined size.

10. The virtual fence of claim 6, further comprising:

a processing unit associated with each pole for analyzing the captured video.

11. A program product stored on a non-transitory computer readable medium, which when executed, provides a virtual fence, the computer readable medium comprising program code for:

capturing video data using a plurality of video cameras positioned about a perimeter to be monitored, the perimeter comprising a plurality of designated areas and completely encircling an area, wherein a series of poles are provided about the perimeter to be monitored, wherein each designated area comprises an area between a respective pair of the poles, wherein a pair of video cameras are mounted on each of the poles, wherein a first of each pair of video cameras mounted on each pole is directed toward a previous pole in the series of poles, and a second of each pair of video cameras mounted on each pole is directed toward a next pole in the series of poles, such that an overlap in coverage between the video data of the first and second video cameras of each pair of video cameras is provided in each designated area;

monitoring the video data using background subtraction in a thin strip in each designated area to detect an event; and

sending at least one of an alarm, image data, or video data to a central facility only in response to the detection of the event.

12. A method for deploying an application for providing a virtual fence, comprising:

providing a computer infrastructure being operable to;

capture video data using a plurality of video cameras positioned about a perimeter to be monitored, the perimeter comprising a plurality of designated areas and completely encircling an area, wherein a series of poles are provided about the perimeter to be monitored, wherein each designated area comprises an area between a respective pair of the poles, wherein a pair of video cameras are mounted on each of the poles, wherein a first of each pair of video cameras mounted on each pole is directed toward a previous pole in the series of poles, and a second of each pair of video cameras mounted on each pole is directed toward a next pole in the series of poles, such that an overlap in coverage between the video data of the first and second video cameras of each pair of video cameras is provided in each designated area;

monitor the video data using background subtraction in a thin strip in each designated area to detect an event; and

send at least one of an alarm, image data, or video data to a central facility only in response to the detection of the event.