Video surveillance system employing video primitives

• US 20080100704A1
• Filed: 12/15/2005
• Published: 05/01/2008
• Est. Priority Date: 10/24/2000
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: ObjectVideo Incorporated (Alarm.com Holdings, Inc.)
• Inventors: Martone, Andrew J., Yu, Li, Zhang, Zhong, Venetianer, Peter L., Lipton, Alan J., Yin, Weihong, Hu, Yongtong
• Granted Patent: US 8,711,217 B2
• Time in Patent Office: Days
• US Class Current: 348/143
• CPC Class Codes: G06F 16/7837 using objects detected or recognised in the video content
• CPC Class Codes: G06F 16/7847 using low-level visual features of the video content
• CPC Class Codes: G06F 16/7854 using shape G06F16/7837 takes precedence
• CPC Class Codes: G06F 16/786 using motion, e.g. object motion or camera motion
• 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: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion
• CPC Class Codes: G08B 13/196 using television cameras
• 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 13/19615 wherein said pattern is defined by the user
• CPC Class Codes: G08B 13/19697 Arrangements wherein non-video detectors generate an alarm themselves
• CPC Class Codes: G08B 21/0476 Cameras to detect unsafe condition, e.g. video cameras
• CPC Class Codes: G08B 29/188 Data fusion; cooperative systems, e.g. voting among different detectors
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

A video surveillance system is set up, calibrated, tasked, and operated. The system extracts video primitives and extracts event occurrences from the video primitives using event discriminators. The system can undertake a response, such as an alarm, based on extracted event occurrences.

Claims

1. A method of video surveillance comprising:

detecting at least one stationary object in video; and

using at least one video or non-video primitive derived from said video to determine if the at least one stationary object meets at least one predetermined criterion for generating an alert.

2. The method of claim 1, wherein said at least one video or non-video primitive comprises at least one condition based on an exclusion zone around said at least one stationary object.

3. The method of claim 2, further comprising:

permitting a user to set at least one exclusion zone parameter selected from the group consisting of;

a size of the exclusion zone, a shape of the exclusion zone, and a duration of time associated with the exclusion zone.

4. The method of claim 3, wherein said permitting includes permitting the user to enter a radius for the exclusion zone.

5. The method of claim 3, wherein said permitting comprises:

permitting a user to determine at least one exclusion zone parameter for a near-field exclusion zone and at least one exclusion zone parameter for a far-field exclusion zone.

6. The method of claim 5, further comprising at least one of the operations selected from the group consisting of:

interpolating between the exclusion zone parameter for a near-field exclusion zone and the exclusion zone parameter for a far-field exclusion zone to determine said exclusion zone parameter in a region between the near-field exclusion zone and the far-field exclusion zone; and

extrapolating from the exclusion zone parameter for a near-field exclusion zone and the exclusion zone parameter for a far-field exclusion zone to determine said exclusion zone parameter in a region outside of the region between the near-field exclusion zone and the far-field exclusion zone.

7. The method of claim 3, wherein said duration of time associated with the exclusion zone comprises a duration of time that a non-stationary object may leave the exclusion zone without generating an alert.

8. The method of claim 2, further comprising:

learning at least one parameter of the exclusion zone based on said video.

9. The method of claim 2, further comprising:

dynamically adjusting at least one parameter of the exclusion zone based on said video.

10. The method of claim 1, wherein said using comprises:

performing activity inferencing on the at least one video or non-video primitive.

11. The method of claim 10, wherein said performing activity inferencing comprises:

using a modified “

and”

operator to combine a stationary target activity detector and an are of interest inside activity detector with spatial and temporal modifiers.

12. The method of claim 10, wherein said performing activity inferencing comprises:

tracking a person responsible for leaving behind the at least one stationary object.

13. A computer-readable medium containing machine-executable code that, when executed by a processor, causes the processor to execute the method of claim 1.

14. A video surveillance system comprising application-specific hardware to implement the method of claim 1.

15. The method of claim 1, wherein said video or non-video primitive comprises at least one condition based on a duration of time for which some predetermined action occurs.

16. The method of claim 1, wherein said video or non-video primitive comprises at least one condition based on the occurrence of an event external to said at least one stationary object.

17. The method of claim 16, further comprising:

representing said at least one condition as a non-video primitive; and

storing said non-video primitive in a primitive storage facility.

18. The method of claim 1, wherein said at least one predetermined criterion comprises a query comprising at least two sub-queries and at least one combinator.

19. The method of claim 18, wherein at least one of said sub-queries includes a modifier.

20. The method of claim 19, wherein said modifier is selected from the group consisting of:

a modifier to address how a sub-query is stored;

a modifier to address whether a sub-query is stored;

a modifier to address how a sub-query is to be used in detecting one or more events; and

a modifier to address how many events a sub-query may be used to detect.