Video traffic monitor for retail establishments and the like

• US 5,465,115 A
• Filed: 01/10/1995
• Issued: 11/07/1995
• Est. Priority Date: 05/14/1993
• Status: Expired due to Term

• Current Assignee: Shoppertrak RCT Corporation (Johnson Controls International plc)
• Original Assignee: RCT Systems, Inc.
• Inventors: Denenberg, Byron A., Kramerich, George L., Conrad, Gary L.
• Primary Examiner(s): Britton, Howard W.
• Assistant Examiner(s): LEE, RICHARD J
• Application Number:
  US08/370,825
• Time in Patent Office: 301 Days
• Field of Search: 348/150, 348/155, 348/169, 348/170, 348/218
• US Class Current: 348/155
• CPC Class Codes: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G07C 9/00 Individual registration on entry or exit
• 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 traffic monitor and method for counting people using video imaging provides an inexpensive hardware implementation for analyzing real-time video where the operational environment presents a reasonably restricted traffic flow, such as in the entryway of a building. The video traffic monitor utilizes a windowed subsample of an image frame, and the image frame is further subdivided into gates. The video traffic monitor processes this windowed area to highlight the objects moving through the gates. The gates are then analyzed to determine a direction of movement for the people and support the logic for noise elimination and object discrimination. The video traffic monitor counts the detected people and records the count according to the direction of movement of the people.

Claims

1. A method of monitoring and counting retail customers traversing wide zones of a retail mall or store, said method comprising the steps of

positioning an overhead video camera to produce a video image extending across a zone to be monitored for customer movement,

digitizing said video image at repetitive time intervals to produce digital information representing said video image said at repetitive time intervals,

processing said digital information using a linear array of segments of the video image consecutively positioned and fixed in position during processing across the zone to be monitored, with each of said gates having a predetermined size relative to the size of a retail customer for distinguishing retail customers traversing said zone by examining consecutive segments which are occupied to determine whether the number of consecutive segments which are occupied corresponds to an individual retail customer, to determine

(1) the number of retail customers traversing said zone, and

(2) a direction of movement transverse to said linear array of gates through said zone for said retail customers traversing said zone such that said retail customers are counted as entering or exiting said zone.

2. The method of claim 1 wherein the step of processing further comprises the steps of:

obtaining a position for a person within one of said consecutive segments; and

comparing said position with a previous position for said person within said one of said consecutive segments to determine a direction of movement for said person across said zone.

3. The method of claim 1 further comprising the steps of:

storing numbers for directions of movement of said retail customers; and

displaying said numbers and said directions.

4. The method of monitoring and counting retail customers of claim 1 wherein said step of processing further includes the step of:

examining a gap of an unoccupied segment between otherwise consecutive segments which are occupied to determine whether said unoccupied segment is to be considered as occupied.

5. The method of claim 1 wherein said steps following said step of positioning further comprises the step of employing a digital signal processor on a dedicated board.

6. The method of claim 5 wherein said step of digitizing further comprises employing a custom frame-grabber board coupled to said digital signal processor.

7. The method of claim 1 wherein said steps following said step of positioning further comprise the step of employing a personal computer.

8. The method of claim 7 wherein said step of digitizing further comprises employing a conventional frame-grabber board coupled to an I/O port of said personal computer.

9. A video traffic monitor for detecting and counting objects of measurement traversing a traffic zone in different directions, said video traffic monitor, comprising:

a video imager positioned above a traffic zone to be monitored for object movement, said video imager producing an image of said traffic zone in the form of an analog signal;

a signal converter coupled to said video imager for converting said analog signal into digital information representing said image;

an image handler coupled to said signal converter for storing said image represented by said digital information at repetitive time intervals; and

a processor coupled to said image handler for analyzing a window of said image, said window being a subset of said image and positioned and fixed in position during analyzing substantially across said image, said window including a linear array of gates consecutively positioned and fixed in position within said window and within said image during analyzing, each of said gates having a predetermined size relative to the size of an object of measurement, said processor analyzing said gates to determine whether an object of measurement is traversing said window and to determine a direction of movement transverse to said linear array of gates for said object of measurement across said window such that said processor counts said object as entering or exiting said traffic zone, said processor distinguishing objects of measurement traversing said window by examining consecutive gates which are occupied to determine whether the number of consecutive gates which are occupied corresponds to an individual object of measurement.

10. The video traffic monitor of claim 9 wherein said processor being a digital signal processor on a dedicated board.

11. The video traffic monitor of claim 9 wherein said processor is coupled to a personal computer, said personal computer storing and displaying numbers for the directions of movement for said objects.

12. The video traffic monitor of claim 9 wherein said video imager being a monochrome camera.

13. The video traffic monitor of claim 9 wherein said video imager being a color CCD camera.

14. The video traffic monitor of claim 9 wherein said video imager being a infrared camera.

15. The video traffic monitor for detecting and counting objects of measurement traversing a traffic zone of claim 9 wherein said processor examines a gap of an unoccupied gate between otherwise consecutive gates which are occupied to determine whether said unoccupied gate is to be considered as occupied.

16. The video traffic monitor of claim 9 wherein said processor being a conventional personal computer.

17. The video traffic monitor of claim 16 wherein said image handler and said signal converter being a conventional frame-grabber board coupled to an I/O port of personal computer.

18. A video traffic analyzer for detecting the flow of objects of measurements across an image of a traffic zone having said objects of measurement traversing said traffic zone, said video traffic analyzer receiving digital information representing said image of said traffic zone and comprising a processor analyzing a window of said image, said window being a subset of said image and positioned and fixed in position during analyzing substantially across said image, said window including a linear array of gates consecutively positioned and fixed in position within said window and within said image during analyzing, each of said gates having a predetermined size relative to the size of an object of measurement, said processor analyzing said gates to determine whether an object of measurement is traversing said window and to determine a direction of movement transverse to said linear array of gates for said object of measurement traversing said window such that said processor counts said object as entering or exiting said traffic zone, said processor distinguishing objects of measurement traversing said window by examining consecutive gates which are occupied to determine whether the number of consecutive gates which are occupied corresponds to an individual object of measurement.

19. The video traffic analyzer of claim 18 wherein said processor being a digital signal processor on a dedicated board.

20. The video traffic analyzer of claim 18 wherein said processor is coupled to a personal computer, said personal computer storing and displaying a number and directions of movement for said objects.

21. The video traffic analyzer of claim 18 wherein said processor being a conventional personal computer.

22. The video traffic analyzer of claim 18 wherein said processor examines a gap of an unoccupied gate between otherwise consecutive gates which are occupied to determine whether said unoccupied gate is to be considered as occupied.

23. A method for detecting the traffic flow of objects of measurement traversing a traffic zone in different directions comprising the steps of:

producing an image of said traffic zone;

storing said image at repetitive time intervals;

analyzing a window of said image being a subset of said image and positioned and fixed in position during said analyzing substantially across said image, said window including a linear array of gates consecutively positioned and fixed in position within said window and within said image during analyzing with each of said gates having a predetermined size relative to the size of an object of measurement;

distinguishing objects of measurement traversing said window by examining consecutive gates which are occupied to determine whether the number of consecutive gates which are occupied corresponds to an individual object of measurement;

determining a direction of movement transverse to said linear array of gates for said object of measurement traversing said window; and

counting said object as entering or exiting said traffic zone.

24. The method of claim 23 further comprising the steps of:

storing a result of said counting and directions of movement for said objects; and

displaying said results and said directions of movement for said objects.

25. The method for detecting the traffic flow of objects of measurement traversing a traffic zone of claim 23 wherein said step of distinguishing further includes the step of:

examining a gap of an unoccupied gate between otherwise consecutive gates which are occupied to determine whether said unoccupied gate is to be considered as occupied.

26. The method of claim 23 wherein said steps following said step of storing further comprise the step of employing a digital signal processor on a dedicated board.

27. The method of claim 26 wherein said step of storing further comprises employing a custom frame-grabber board coupled to said digital signal processor.

28. The method of claim 23 wherein said steps following said step of storing further comprise the step of employing a personal computer.

29. The method of claim 28 wherein said step of storing further comprise employing a conventional frame-grabber board coupled to an I/O port of said personal computer.

30. A method for detecting the flow of objects of measurement across an image of a traffic zone having objects of measurement traversing said traffic zone, comprising the steps of:

analyzing a window of said image being a subset of said image and positioned and fixed in position during said analyzing substantially across said image, said window including a linear array of gates consecutively positioned and fixed in position within said window and within said image during analyzing with each of said gates having a predetermined size relative to the size of an object of measurement;

distinguishing objects of measurement traversing said window by examining consecutive gates which are occupied to determine whether the number of consecutive gates which are occupied corresponds to an individual object of measurement;

determining a direction of movement transverse to said linear array of gates for said object of measurement traversing said window; and

counting said object as entering or exiting said traffic zone.

31. The method of claim 30 further comprising the step of employing a digital signal processor on a dedicated board.

32. The method of claim 30 further comprising the step of employing a personal computer.

33. The method of claim 30 further comprising the steps of:

storing a result of said counting and directions of movement for said objects; and

displaying said results and said directions of movement for said objects.

34. The method for detecting the flow of objects of measurement across an image of a traffic zone of claim 30 wherein said step of distinguishing further includes the step of:

examining a gap of an unoccupied gate between otherwise consecutive gates which are occupied to determine whether said unoccupied gate is to be considered as occupied.

35. A video traffic monitoring system for detecting the flow of objects of measurement across a plurality of traffic zones, comprising:

a plurality of video traffic analyzers, each of said plurality of video traffic analyzers comprising a processor analyzing a window of an image of one of said plurality of traffic zones, said window being a subset of said image and positioned and fixed in position during analyzing substantially across said image, window including a linear array of gates consecutively positioned and fixed in position within said window and within said image during analyzing, each of said gates having a predetermined size relative to the size of an object of measurement, said processor analyzing said gates to determine whether an object of measurement is traversing said window and to determine a direction of movement transverse to said linear array of gates for said object of measurement traversing said window such that said processor counts said object as entering or exiting said one of said plurality of traffic zones, said processor distinguishing objects of measurement traversing said window by examining consecutive gates which are occupied to determine whether the number of consecutive gates which are occupied corresponds to an individual object of measurement; and

a computer coupled to each of said plurality of video traffic analyzers, said computer storing and displaying numbers and directions of movement for said objects in each of said plurality of traffic zones.

36. The video traffic monitoring system for detecting the flow of objects of measurement across a plurality of traffic zones of claim 35 wherein said processor examines a gap of an unoccupied gate between otherwise consecutive gates which are occupied to determine whether said unoccupied gate is to be considered as occupied.