Video surveillance system employing video primitives

Patent metadata

Field	Value
Publication number	US-10347101-B2
Application number	US-201816035942-A
Country	US
Kind code	B2
Filing date	Jul 16, 2018
Priority date	Oct 24, 2000
Publication date	Jul 9, 2019
Grant date	Jul 9, 2019

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.

First claim

What is claimed is:

1. A method of video surveillance, comprising:
receiving, by a computer system, a video comprising video images from a video sensor,
the computer system performing the steps of:
analyzing the video to detect stationary objects in the video;
analyzing the video to detect people in the video;
upon detecting a first stationary object in the video, defining a zone as a portion of the video around the first stationary object, defining the zone being responsive to a location of the first stationary object, the zone being defined to be larger than an outer boundary of the first stationary object and smaller than a field of view of the video, a size of the zone allowing detection of multiple non-overlapping objects;
tracking a duration that the first stationary object remains stationary; and
issuing an alert in response to determining that the duration of time the first stationary object has remained stationary exceeds a threshold while no person of interest detected in the video has been inside the zone,
wherein the size of the zone is determined dynamically and is responsive to crowd density.

2. The method of claim 1 , wherein the person of interest comprises any person detected in the video.

3. The method of claim 1 , further comprising detecting a person leaving the first stationary object as the person of interest.

4. The method of claim 1 , wherein the size of the zone is determined prior to the detecting of the first stationary object.

5. The method of claim 1 , wherein the person of interest comprises a person detected as leaving the first stationary object and detected as having been in the zone longer than a first period of time.

6. The method of claim 1 , wherein the size of the zone is defined in an image space that varies as a function of the location of the first stationary object.

7. The method of claim 1 , wherein the zone is defined as a shape in the real-world of the video independent of detecting the first stationary object.

8. The method of claim 1 , wherein the size of the zone is determined by performing an interpolation or an extrapolation of a first shape.

9. The method of claim 1 , further comprising permitting a user to set, via a user interface, at least one parameter selected from the group consisting of: the size of the zone, a shape of the zone, and the duration of time.

10. A method of video surveillance, comprising:
receiving, by a computer system, a video comprising video images from a video sensor,
the computer system performing the steps of:
analyzing the video to detect stationary objects in the video;
analyzing the video to detect people in the video;
upon detecting a first stationary object in the video, defining a zone as a portion of the video around the first stationary object, defining the zone being responsive to a location of the first stationary object, the zone being defined to be larger than an outer boundary of the first stationary object and smaller than a field of view of the video, a size of the zone allowing detection of multiple non-overlapping objects;
tracking a duration that the first stationary object remains stationary; and
issuing an alert in response to the determining that the duration of time the first stationary object has remained stationary exceeds a threshold while at least one of the following occurs:
no person of interest detected in the video has been detected as being in the zone, and
no person of interest detected in the video has been detected as being in the zone longer than a first period of time,
wherein the size of the zone is determined dynamically and is responsive to crowd density.

11. The method of claim 10 , wherein the zone is one of a circle, ellipse or a rectangle.

12. The method of claim 10 , wherein the size of the zone is responsive to a selection by a user.

13. The method of claim 10 , further comprising permitting a user to set, via a user interface, at least one parameter selected from the group consisting of: the size of the zone, a shape of the zone, and the duration of time.

14. A method of video surveillance, comprising:
receiving, by a computer system, a video comprising video images from a video sensor,
the computer system performing the steps of:
analyzing the video to detect stationary objects in the video;
analyzing the video to detect people in the video;
upon detecting a first stationary object in the video, defining a zone as a portion of the video around the first stationary object, defining the zone being responsive to a location of the first stationary object, the zone being defined to be larger than an outer boundary of the first stationary object and smaller than a field of view of the video, a size of the zone allowing detection of multiple non-overlapping objects;
tracking a duration that the first stationary object remains stationary;
issuing an alert in response to determining that the duration of time the first
stationary object has remained stationary exceeds a threshold while no person of interest detected in the video has been inside the zone; and
determining a security threat level,
wherein the size of the zone is responsive to the determined security threat level.

15. A method of video surveillance, comprising:
receiving, by a computer system, a video comprising video images from a video sensor, the computer system performing the steps of:
analyzing the video to detect stationary objects in the video;
analyzing the video to detect people in the video;
upon detecting a first stationary object in the video, defining a zone as a portion of the video around the first stationary object, defining the zone being responsive to a location of the first stationary object, the zone being defined to be larger than an outer boundary of the first stationary object and smaller than a field of view of the video, a size of the zone allowing detection of multiple non-overlapping objects;
tracking a duration that the first stationary object remains stationary;
determining an occurrence of an external event; and
issuing an alert in response to determining that the duration of time the first stationary object has remained stationary exceeds a threshold while no person of interest detected in the video has been inside the zone and the occurrence of the external event,
wherein the size of the zone is responsive to detection of other stationary objects prior to the detecting of the first stationary object.

16. The method of claim 15 , further comprising:
analyzing the video to determine distances between other stationary objects and people putting down a corresponding one of the other stationary objects prior to the detecting of the first stationary object,
wherein the size of the zone is responsive to the analyzing of the video to determine distances between the other stationary objects and the people putting down the corresponding one of the other stationary objects.

17. The method of claim 15 , further comprising:
analyzing the video to determine durations of time people put down other objects prior to the detecting of the first stationary object,
wherein the duration of time is determined in response to the analyzing of the video to determine the durations of time people put down the other objects.

18. The method of claim 15 , further comprising:
tracking a person responsible for leaving behind the first stationary object.

Assignees

• Avigilon Fortress Corp

Inventors

• Venetianer Peter L
• Lipton Alan J
• Hu Yongtong
• Martone Andrew J
• Yin Weihong
• Yu Li
• Zhang Zhong

Classifications

• G06F16/7837

  using objects detected or recognised in the video content · CPC title

• G06F16/7847

  using low-level visual features of the video content · CPC title

• G08B13/196

  using television cameras · CPC title

• G08B29/188

  Data fusion; cooperative systems, e.g. voting among different detectors · CPC title

• G08B13/19604

  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 title