Security video system using customer regions for monitoring point of sale areas

Patent metadata

Field	Value
Publication number	US-9602778-B2
Application number	US-201213712591-A
Country	US
Kind code	B2
Filing date	Dec 12, 2012
Priority date	Dec 12, 2012
Publication date	Mar 21, 2017
Grant date	Mar 21, 2017

Abstract

A system and method for determining proximity of individuals to specific regions of interest such as Point of Sale (“POS”) terminals within a POS monitored area of a scene of video data captured from security cameras as part of a networked security system, when the security cameras are located outside the POS monitored area, mounted on a ceiling or other high location and pointed at the POS monitored area. With the help of customer regions drawn in an abstract layer whose areas coincide with expected locations of individuals near POS terminals in the video data, and video analytics elements such as bounding boxes generated around individuals in the video data, the system can perform live and forensic analysis of the video data to infer information such as the proximity of individuals to POS terminals and the relative height of an individual compared to their expected height within the scene of video data.

First claim

What is claimed is:

1. A security video system for monitoring individuals at a Point Of Sale (“POS”) area, the security video system comprising:
at least one security camera generating image data of the POS area, wherein the security camera is positioned outside the POS area; and
a security video analytics system for analyzing the image data to determine whether the individuals are within the POS area by reference to one or more customer regions, which are areas overlaid on the image data, the individuals being analyzed relative to the customer regions,
wherein the customer re ions are trapezoidal-shaped, and the customer regions correspond to vertically oriented planes in a three-dimensional space of scenes captured in the image data; and
wherein the security video analytics system determines whether the individuals are within the POS area based on lowest visible areas of their bodies relative to bottom edges of the customer regions and based on highest visible areas of their bodies relative to top edges of the customer regions.

2. The security video system of claim 1 , further comprising a security system workstation enabling specification of the customer regions for the image data of the POS area.

3. The security video system of claim 2 , wherein the security system workstation comprises:
a display;
one or more user input devices; and
a customer region drawing tool for defining the customer regions within the image data of the POS area, drawn by an operator over the image data.

4. The security video system of claim 1 , wherein the customer regions are areas of pixels with vertical edges parallel to the y-axis of the image data.

5. The security video system of claim 1 , wherein the field of view of the security camera captures at least a POS terminal of the POS area and the customer regions.

6. The security video system of claim 1 , wherein the security video analytics system generates bounding boxes around individuals in the image data and compares the bounding boxes relative to the customer regions to infer proximity of the individuals to the POS area.

7. The security video system of claim 6 , wherein the security video analytics system compares the bounding boxes relative to the customer regions to infer proximity of the individuals to the PUS area.

8. The security video system of claim 6 , wherein the security video analytics system analyzes the bounding boxes relative to the customer regions and determines distances between the tops and/or bottoms of the bounding boxes and tops and bottoms of the customer regions to conclude whether the individuals are within the POS area.

9. The security video system of claim 1 , wherein the security video system performs forensic analysis on stored image data to determine proximity of the individuals to the PUS area.

10. The security video system of claim 1 , wherein the security video system performs live analysis on current image data to determine proximity of the individuals to the PUS area.

11. The security video system of claim 1 , wherein the security video analytics system computes L, the expected height of the individuals in pixels relative to the customer regions, and then computes HA, the distance in pixels between intersection of the highest visible areas of their bodies relative to the top edges of the customer regions, and computes FB, the distance in pixels between the lowest visible areas of their bodies relative to bottom edges of the customer regions and the bottom of bounding box and bottom of Customer Regions.

12. The security video system of claim 11 , wherein the security video analytics system compares the distances AH and BF to a percentage of expected height L of the individuals to determine if the individuals are in a vicinity of the POS area.

13. A method for monitoring individuals at a Point Of Sale (“PUS”) area, the method comprising:
positioning a security camera outside the PUS area;
generating image data of the PUS area with the security camera; and
analyzing the image data to determine whether the individuals are within the POS area by reference to one or more customer regions, which are areas overlaid on the image data, by analyzing the individuals relative to the customer regions, the customer regions being trapezoidal-shape areas of pixels corresponding to vertically oriented planes in a three-dimensional space of scenes captured in the image data, the determination of whether the individuals are within the POS area being based on lowest visible areas of their bodies relative to bottom edges of the customer regions and based on highest visible areas of their bodies relative to top edges of the customer regions.

14. The method of claim 13 , further comprising enabling specification of the customer regions for the image data of the POS area by enabling an operator to draw the customer regions on the image data of the POS area.

15. The method of claim 13 , further comprising representing the customer regions as areas of pixels with vertical edges parallel to the y-axis of the image data, and saving the areas of pixels comprising each of the customer regions to video data metadata.

16. The method of claim 13 , further comprising capturing at least a POS terminal of the POS area and the customer regions within the image data.

17. The method of claim 13 , further comprising generating bounding boxes around the individuals in the image data and comparing the bounding boxes relative to the customer regions to infer proximity of the individuals to the POS area.

18. The method of claim 17 , further comprising analyzing the bounding boxes relative to the customer regions and determining distances between the tops and/or bottoms of the bounding boxes and tops and bottoms of the customer regions to conclude whether the individuals are within the POS area.

19. The method of claim 18 , wherein analyzing the bounding boxes relative to the customer regions includes drawing a center line bisecting each bounding box and determining intersection between one or more edges of the customer regions.

20. The method of claim 13 , further comprising performing forensic analysis on stored image data to determine proximity of the individuals to the POS area.

21. The method of claim 13 , further comprising performing live analysis on current image data to determine proximity of the individuals to the POS area.

22. A method for determining the presence of individuals at a Point Of Sale (“POS”) area in a video security system, comprising:
generating image data of the POS area from at least one security camera;
generating bounding boxes around individuals in the image data by a security video analytics system;
representing customer regions as areas of pixels overlaid on the image data, the customer re ions being trapezoidal-shaped, and the customer regions corresponding to vertically oriented planes in a three-dimensional space of scenes captured in the image data; and
analyzing the bounding boxes relative to the customer regions to infer whether the individuals are within the POS area based on distances between the tops and bottoms of the bounding boxes and tops and bottoms, respectively, of the customer regions.

23. The method of claim 22 , wherein analyzing the bounding boxes relative to the customer regions includes drawing a center line bisecting each bounding box and determining intersection between one or more customer regions.

24. A security video system for monitoring individuals

Assignees

• Sensormatic Electronics Llc

Inventors

• Ristivojevic Mirko
• Westmacott Ian Christopher

Classifications

• G08B13/19682 Primary

  Graphic User Interface [GUI] presenting system data to the user, e.g. information on a screen helping a user interacting with an alarm system · CPC title

• G07G3/003

  Anti-theft control (theft alarms G08B13/00) · CPC title

• H04N7/18 Primary

  Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast · CPC title

• G08B13/19613

  Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion · CPC title

• G06Q20/20

  Point-of-sale [POS] network systems · CPC title