Methods and apparatus to count people in images

• US 9,292,736 B2
• Filed: 12/20/2013
• Issued: 03/22/2016
• 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:
  US14/136,748
• Publication Number:
  US 20140105461A1
• Time in Patent Office: 823 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 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• 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 analyzing frame pairs of a plurality of frame pairs captured over a period of time to identify a redundant person indication detected in an overlap region, the overlap region corresponding to an intersection of a first field of view and a second field of view; eliminating the identified redundant person indication to form a conditioned set of person indications for the period of time; grouping similarly located ones of the person indications of the conditioned set to form groups; analyzing the groups to identify redundant groups detected in the overlap region; and eliminating the redundant groups from a people tally generated based on the groups.

Claims

1. A method, comprising:

Analyzing, with a processor, frame pairs of a plurality of frame pairs captured over a period of time to identify a redundant person indication detected in an overlap region, the overlap region corresponding to an intersection of a first field of view and a second field of view;

eliminating, with the processor, the identified redundant person indication to form a conditioned set of person indications for the period of time;

grouping, with the processor, similarly located ones of the person indications of the conditioned set to form groups;

analyzing, with the processor, the groups to identify redundant groups detected in the overlap region; and

eliminating, with the processor, the redundant groups from a people tally generated based on the groups.

2. A method as defined in claim 1, further including eliminating a first one of the groups having less than a threshold amount of members from the people tally.

3. A method as defined in claim 1, wherein the redundant person is indicated by comparing first image data captured by a first image sensor in the first field of view to second image data captured by a second image sensor in the overlap region.

4. A method as defined in claim 3, further including generating a correlation score based on the comparison of the first image data to the second image data.

5. A method as defined in claim 4, further including, when the correlation score is greater than a threshold, designating the person indication corresponding to the second image data as redundant.

6. A method as defined in claim 4, further including, when the correlation score is greater than a threshold, calculating first and second locations of the first and second image data and storing the first and second locations in a correlated pair history.

7. A method as defined in claim 1, further including associating the people tally with media identifying information detected in a media exposure environment.

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

analyze frame pairs of a plurality of frame pairs captured over a period of time to identify a redundant person indication detected in an overlap region, the overlap region corresponding to an intersection of a first field of view and a second field of view;

eliminate the identified redundant person indication to form a conditioned set of person indications for the period of time;

group similarly located ones of the person indications of the conditioned set to form groups;

analyze the groups to identify redundant groups detected in the overlap region; and

eliminate the redundant groups from a people tally generated based on the groups.

9. A tangible computer readable medium as defined in claim 8, wherein the instructions, when executed, cause the computer to eliminate a first one of the groups having less than a threshold amount of members from the people tally.

10. A tangible computer readable medium as defined in claim 8, wherein the instructions, when executed, cause the computer to identify the redundant person indication by comparing first image data captured by a first image sensor in the first field of view to second image data captured by a second image sensor in the overlap region.

11. A tangible computer readable medium as defined in claim 10, wherein the instructions, when executed, cause the computer to generate a correlation score based on the comparison of the first image data to the second image data.

12. A tangible computer readable medium as defined in claim 11, wherein the instructions, when executed, cause the computer to, when the correlation score is greater than a threshold, designate the person indication corresponding to the second image data as redundant.

13. A tangible computer readable medium as defined in claim 11, wherein the instructions, when executed, cause the computer to calculate first and second locations of the first and second image data and storing the first and second locations in a correlated pair history.

14. An apparatus, comprising:

a processor to analyze frame pairs of a plurality of frame pairs captured over a period of time to identify person indications detected in an overlap region, the overlap region corresponding to an intersection of a first field of view and a second field of view;

a first eliminator to eliminate a redundant one of the identified person indications to form a conditioned set of person indications for the period of time;

a grouper to group similarly located ones of the person indications of the conditioned set to form one or more groups, each of the one or more groups being indicative of a person in an environment during the period of time, wherein the processor is to analyze the one or more groups to identify a redundant group detected in the overlap region; and

a second eliminator to eliminate the redundant groups from a people tally generated based on the one or more groups.

15. An apparatus as defined in claim 14, wherein the second eliminator is to eliminate a group having less than a threshold amount of members from the people tally.

16. An apparatus as defined in claim 14, wherein the first eliminator is to identify the redundant person indication by comparing first image data captured by a first image sensor in the first field of view to second image data captured by a second image sensor in the overlap region.

17. An apparatus as defined in claim 16, wherein the first eliminator is to generate a correlation score based on the comparison of the first image data to the second image data.

18. An apparatus as defined in claim 17, wherein the first eliminator is to, when the correlation score is greater than a threshold, designate the person indication corresponding to the second image data as redundant.

19. An apparatus as defined in claim 17, wherein the first eliminator is to, when the correlation score is greater than a threshold, calculate first and second locations of the first and second image data and store the first and second locations in a correlated pair history.

20. An apparatus as defined in claim 14, wherein the environment is a media exposure environment, and further including an audience measurement device to associate the people tally with media identifying information detected in the media exposure environment.