Methods and apparatus to count people in images

• US 9,465,999 B2
• Filed: 05/19/2014
• Issued: 10/11/2016
• Est. Priority Date: 03/29/2012
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Srinivasan, Venugopal, Soundararajan, Padmanabhan
• Primary Examiner(s): CHANG, JON CARLTON
• Application Number:
  US14/281,104
• Publication Number:
  US 20140254876A1
• Time in Patent Office: 876 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks

Abstract

Methods and apparatus to count people in images are disclosed. An example method includes maintaining a history of instances in which a person is detected by a first image sensor and by a second sensor different than the first image sensor at approximately a same time, respective ones of the instances including a first coordinate at which a first person was detected via the first image sensor, and a second coordinate at which the first person was detected via the second image sensor; and, in response to first image data captured by the first image sensor including a second person at the first coordinate, determining whether second image data captured by the second image sensor includes the second person without comparing the first image data to the second image data.

Claims

1. A method, comprising:

Maintaining, with a processor, a history of instances in which a person is detected by a first image sensor and by a second sensor different than the first image sensor at approximately a same time, respective ones of the instances including;

a first coordinate at which a first person was detected via the first image sensor; and

a second coordinate at which the first person was detected via the second image sensor; and

in response to first image data captured by the first image sensor including a second person at the first coordinate, determining, with a processor, whether second image data captured by the second image sensor includes the second person without comparing the first image data to the second image data; and

eliminating, with the processor, the second person from a count of people.

2. The method as defined in claim 1, wherein the determining of whether the second image data includes the second person without comparing the first image data to the second image data includes determining whether a person indication is included at the second coordinate of the second image data.

3. The method as defined in claim 1, wherein the first coordinate corresponds to a location relative to the first image sensor, and the second coordinate corresponds to a same location relative to the second image sensor.

4. The method as defined in claim 1, wherein the first image data is captured at approximately a same time as the second image data.

5. The method as defined in claim 1, further including determining the first person detected via the first image sensor and the first person detected via the second image sensor at approximately the same time are a same person via image comparison.

6. The method as defined in claim 1, wherein the second person is detected in an overlap region corresponding to an intersection of a first field of view associated with the first image sensor and a second field of view associated with the second image sensor.

7. A tangible computer readable storage medium comprising instructions that, when executed, cause a machine to at least:

maintain a history of instances in which a person is detected by a first image sensor and by a second sensor different than the first image sensor at approximately a same time, respective ones of the instances including;

a first coordinate at which a first person was detected via the first image sensor; and

a second coordinate at which the first person was detected via the second image sensor; and

in response to first image data captured by the first image sensor including a second person at the first coordinate, determine whether second image data captured by the second image sensor includes the second person without comparing the first image data to the second image data; and

when the second image data includes the second person, eliminate the second person from a tally of people.

8. The tangible computer readable storage medium as defined in claim 7, wherein the instructions, when executed, cause the machine to, determine whether the second image data includes the second person without comparing the first image data to the second image data by determining whether a person indication is included at the second coordinate of the second image data.

9. The tangible computer readable storage medium as defined in claim 7, wherein the first coordinate corresponds to a location relative to the first image sensor, and the second coordinate corresponds to a same location relative to the second image sensor.

10. The tangible computer readable storage medium as defined in claim 7, wherein the first image data is captured at approximately a same time as the second image data.

11. The tangible computer readable storage medium as defined in claim 7, wherein the instructions cause the machine to perform image comparison to determine whether the first person detected via the first image sensor and the first person detected via the second image sensor at approximately the same time are a same person.

12. The tangible computer readable storage medium as defined in claim 7, wherein the second person is detected in an overlap region corresponding to an intersection of a first field of view associated with the first image sensor and a second field of view associated with the second image sensor.

13. An apparatus, comprising:

memory to store a history of instances in which a person is detected by a first image sensor and by a second sensor different than the first image sensor at approximately a same time, respective ones of the instances including;

a first coordinate at which a first person was detected via the first image sensor; and

a second coordinate at which the first person was detected via the second image sensor; and

an overlap eliminator to, in response to first image data captured by the first image sensor including a second person at the first coordinate, determine whether second image data captured by the second image sensor includes the second person without comparing the first image data to the second image data, and, the overlap eliminator is to eliminate the second person from a count of people.

14. The apparatus as defined in claim 13, wherein the overlap eliminator is to determine whether the second image data includes the second person indication without comparing the first image data to the second image data by determining whether a person indication is included at the second coordinate of the second image data.

15. The apparatus as defined in claim 13, wherein the first image data is captured at approximately a same time as the second image data.

16. The apparatus as defined in claim 13, wherein the first person detected via the first image sensor and the first person detected via the second image sensor at approximately the same time are determined to be a same person via image comparison.

17. The apparatus as defined in claim 13, wherein the second person is detected in an overlap region corresponding to an intersection of a first field of view associated with the first image sensor and a second field of view associated with the second image sensor.