Crowd counting and monitoring

• US 20080118106A1
• Filed: 11/22/2006
• Published: 05/22/2008
• Est. Priority Date: 11/22/2006
• Status: Active Grant

• Current Assignee: Regents of The University of Minnesota (University of Minnesota)
• Original Assignee: Regents of The University of Minnesota (University of Minnesota)
• Inventors: Masoud, Osama T., Kilambi, Prahlad, Papanikolopoulos, Nikolaos
• Granted Patent: US 8,116,564 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06M 11/00 Counting of objects distributed at random, e.g. on a surface
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

This document discusses, among other things, methods and systems for determining the number of members in a group as well as changes over a period of time. Using an image of the scene, an overlap area is calculated by projecting portions of the image onto spaced apart and parallel planes. A filter correlates the overlap area to the number of members.

Claims

1. A method comprising:

receiving an image from a camera, the image including a foreground region;

projecting the region onto a first reference plane and onto a second reference plane; and

computing an intersected area using a difference between an area on the first reference plane and an area on the second reference plane.

2. The method of claim 1 further including receiving calibration data for the camera, and wherein computing the intersected area includes calibrating the camera using the calibration data.

3. The method of claim 1 wherein the first reference plane corresponds to a ground plane.

4. The method of claim 1 wherein the second reference plane corresponds to a plane at a predetermined height above the first reference plane.

5. The method of claim 1 wherein the second reference plane corresponds to a height approximately that of a human.

6. The method of claim 1 further including:

receiving an average area corresponding to an individual; and

calculating a count using a quotient of the intersected area and the average area.

7. The method of claim 1 further including identifying at least one ellipse corresponding to the intersected area.

8. The method of claim 7 wherein identifying the at least one ellipse includes calculating an eigenvector using the intersected area.

9. The method of claim 7 wherein identifying the at least one ellipse includes minimizing a cost function using the intersected area.

10. The method of claim 7 further including:

determining an area for an average individual; and

determining a count using the area for the average individual and the at least one ellipse.

11. The method of claim 10 further including storing the count as a function of time.

12. The method of claim 11 further including, for a predetermined period of time, calculating at least one of a mode, a median and an average.

13. A medium including instructions executable in a processor for carrying out a method comprising:

receiving an image having a foreground region and a background, the foreground region including a depiction of at least one person;

generating a shape using an intersected area, the intersected area corresponding to projections of the depiction of the at least one person onto both a ground plane and an elevated plane, the elevated plane disposed parallel to the ground plane and at a predetermined height relative to the ground plane; and

determining a count corresponding to the at least one person using a ratio of an area of the generated shape and an area of a modeled person.

14. The medium of claim 13 wherein the predetermined height corresponds to a height approximately that of a human.

15. The medium of claim 13 further including identifying at least one ellipse corresponding to the shape.

16. The medium of claim 15 wherein identifying the at least one ellipse includes calculating an eigenvector using the intersected area.

17. The medium of claim 15 wherein identifying the at least one ellipse includes minimizing a cost function using the intersected area.

18. The medium of claim 13 further including storing the count as a function of time.

19. The medium of claim 18 further including, for a predetermined period of time, calculating at least one of a mode, a median and an average.

20. A system for counting people in a crowd, the system comprising:

an image capture module for receiving image data including a background and a foreground, the foreground having a depiction of at least one person;

a processor for determining an intersected area based on a projection of the depiction onto both a ground plane and an elevated plane, the elevated plane disposed parallel to the ground plane and at a predetermined height relative to the ground plane, and for producing a count corresponding to the depiction, the count based on a ratio of the intersected area and a unit measure, the unit measure corresponding to an area of a person.

21. The system of claim 20 further including an input device coupled to the preprocessor and wherein the input device includes at least one of a keyboard, a mouse, and a removable storage device.

22. The system of claim 20 further including an output device coupled to the processor and wherein the output device includes at least one of a display, a printer, a transducer, a memory device, a controller, and a transmitter.

23. Apparatus for counting members of a group, the apparatus comprising:

an image receiver for receiving a two dimensional representation of a three dimensional environment, the environment including a background and a foreground, the foreground including a depiction of at least one member;

a processor for calculating an intersected area using a projection of the depiction onto both a ground plane and onto an elevated plane, the elevated plane disposed parallel to the ground plane and at a predetermined height relative to the ground plane, and for determining a count of members in the environment using a ratio of the intersected area and a unit area corresponding to the at least one member.

24. The apparatus of claim 23 wherein the processor is adapted to determine an area of at least one ellipse corresponding to the intersected area.

25. The apparatus of claim 23 wherein the processor executes an algorithm to minimize a cost function.

26. The apparatus of claim 23 further including a tracking register to store the count as a function of time and wherein the image receiver is configured to receive a plurality of environments in time sequence.

27. The apparatus of claim 23 wherein the image receiver includes a camera.

28. The apparatus of claim 23 wherein the processor executes an algorithm to implement a filter.

29. The apparatus of claim 28 wherein the filter includes a non-linear filter.