METHODS AND APPARATUS TO COUNT PERSONS IN A MONITORED ENVIRONMENT

• US 20100195865A1
• Filed: 08/07/2009
• Published: 08/05/2010
• Est. Priority Date: 08/08/2008
• Status: Active Grant

• Current Assignee: Nielsen Company (US) LLC (RR Donnelley & Sons Company)
• Original Assignee: Nielsen Company (US) LLC (RR Donnelley & Sons Company)
• Inventors: Luff, Robert A.
• Granted Patent: US 8,411,963 B2
• Time in Patent Office: Days
• US Class Current: 382/100
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20224 Image subtraction
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06V 10/421 by analysing segments intersecting the pattern
• 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: H04H 60/33 Arrangements for monitoring the users' behaviour or opinions

Abstract

Methods and apparatus to count persons in a monitored environment are disclosed. An example apparatus to count the number of people in a monitored environment is described, which includes an image sensor having a plurality of pixels, a pseudorandom number generator to generate pseudorandom coordinates, a reader to read first pixel data generated by a first pixel of the image sensor at a first time, the first pixel corresponding to the pseudorandom coordinates, a comparator to compare the first pixel data with second pixel data generated by the first pixel at a second time different from the first time to generate a change value, and a counter configured to generate a count of persons based at least on the change value.

Claims

1. An apparatus to count a number of persons in a monitored environment, comprising:

an image sensor having a plurality of pixels;

a pseudorandom number generator configured to generate pseudorandom coordinates;

a reader configured to read first pixel data generated by a first pixel of the image sensor at a first time, the first pixel corresponding to the pseudorandom coordinates;

a comparator configured to compare the first pixel data with second pixel data generated by the first pixel at a second time different from the first time to generate a change value; and

a counter configured to generate a count of persons based on the change value.

2. An apparatus as defined in claim 1, further comprising a storage device to store the change value and the coordinates corresponding to the first pixel.

3. An apparatus as defined in claim 2, wherein the storage device is configured to store one or more counts of audience members.

4. An apparatus as defined in claim 1, wherein the counter is to map the change value to facilitate detection of motion indicative of a person.

6. An apparatus as defined in claim 4, wherein the counter comprises a map interpolator to a second change value based on a plurality of change values.

7. An apparatus as defined in claim 6, wherein the map interpolator is to generate the second change value by interpolating the plurality of change values.

8. An apparatus as defined in claim 1, wherein the counter comprises a blob discriminator to determine one or more blobs based on one or more change values.

9. An apparatus as defined in claim 8, wherein the blob discriminator is to determine whether at least one of the blobs is indicative of a plurality of persons.

10. An apparatus as defined in claim 8, wherein the counter further comprises a non-human filter to determine whether the one or more blobs does not represent a person.

11. An apparatus as defined in claim 1, wherein the counter comprises a high-motion filter to determine whether the change value is indicative of a high-motion event.

12. An apparatus as defined in claim 1, wherein the first pixel data comprises a brightness value and a color value.

14. An apparatus as defined in claim 1, further comprising a count comparator to determine whether the count of persons is equal to a previous count of persons.

5. (canceled)

13. (canceled)

15. (canceled)

16. A method to count a number of persons in a monitored environment, comprising:

pseudorandomly selecting a first pixel from a plurality of pixels in an image sensor;

collecting first information sensed by the first pixel at a first time;

comparing the first information to second information sensed by the first pixel at a second time different from the first time to generate a change value; and

determining whether the change value is indicative of a person in the monitored environment.

17. A method as defined in claim 16, further comprising pseudorandomly selecting a second pixel from the plurality of pixels, collecting third information sensed by the second pixel, and comparing the third information to fourth information sensed by the second pixel to generate a second change value.

18. A method as defined in claim 17, wherein determining whether the change value is indicative of the person further comprises determining whether the first and second change values in combination are indicative of the person in the monitored environment.

19. A method as defined in claim 18, further comprising determining whether the second change value is indicative of a second person in the monitored environment.

20. A method as defined in claim 16, wherein pseudorandomly selecting the first pixel comprises generating one or more pseudorandom coordinates corresponding to a location of the first pixel within the plurality of pixels.

21. A method as defined in claim 16, further comprising placing the change value in a map.

25. A method as defined in claim 16, further comprising determining whether the change value is indicative of a high-motion event.

22. (canceled)

23. (canceled)

24. (canceled)

26. An article of manufacture comprising instructions, which, upon execution, cause a machine to:

pseudorandomly select a first pixel from a plurality of pixels in an image sensor;

collect first information sensed by the first pixel at a first time;

compare the first information to second information sensed by the first pixel at a second time different from the first time to generate a change value; and

determine whether the change value is indicative of a person in a monitored environment.

27. An article of manufacture as defined in claim 26, wherein the instructions further cause the machine to pseudorandomly select a second pixel from the plurality of pixels, collecting third information sensed by the second pixel, and comparing the third information to fourth information sensed by the second pixel to generate a second change value.

28. An article of manufacture as defined in claim 27, wherein determining whether the change value is indicative of the person comprises determining whether the first and second change values in combination are indicative of the person in the monitored environment.

30. An article of manufacture as defined in claim 26, wherein pseudorandomly selecting the first pixel comprises generating one or more pseudorandom coordinates corresponding to a location of the first pixel within the plurality of pixels.

31. An article of manufacture as defined in claim 26, further comprising placing the change value in a map.

32. An article of manufacture as defined in claim 31, wherein the instructions further cause the machine to process the map to determine a count of persons present in the map.

29. (canceled)

33. (canceled)

34. (canceled)

35. (canceled)