Methods and apparatus to count people

Patent metadata

Field	Value
Publication number	US-9986289-B2
Application number	US-201514635360-A
Country	US
Kind code	B2
Filing date	Mar 2, 2015
Priority date	Mar 2, 2015
Publication date	May 29, 2018
Grant date	May 29, 2018

Abstract

Methods and apparatus to count people are disclosed. An example apparatus includes a populator to populate a list with first characteristic datasets obtained from first image data representative of an environment during a first period of time, respective ones of the first characteristic datasets representative of a face detected in the environment during the first period of time; a comparator to compare the first characteristic datasets to each other to determine a first number of unique faces in the environment during the first period of time; and a discarder to delete the first characteristic datasets from the list when the first period of time has ended, the populator to re-populate the list with second characteristic datasets obtained from second image data representative of the environment during a second period of time subsequent to the first period of time.

First claim

What is claimed is:

1. An apparatus comprising:
a discarder to delete existing characteristic datasets from a list;
a populator to populate the list with first characteristic datasets obtained from a first plurality of images representative of an environment during a first period of time of a media presentation, respective ones of the first characteristic datasets representative of corresponding faces detected in the environment during the first period of time;
a limiter to limit a number of the first characteristic datasets stored in the list for a first location represented in the first plurality of images;
a comparator to compare the first characteristic datasets to each other to determine a first number of unique faces in the environment during the first period of time, the comparator to limit the comparisons of the respective first characteristic datasets to other first characteristic datasets obtained during the first period of time; and
the discarder to delete the first characteristic datasets from the list after the first period of time has ended, the populator to re-populate the list with second characteristic datasets obtained from a second plurality of images representative of the environment during a second period of time of the media presentation, subsequent to the first period of time, and the discarder, the populator, the limiter and the comparator implemented in a circuit.

2. The apparatus as defined in claim 1 , wherein the apparatus is not to query a facial recognition database to determine the first number of unique faces in the environment.

3. The apparatus as defined in claim 2 , wherein the facial recognition database is separately implemented from the list.

4. The apparatus as defined in claim 1 , wherein the comparator is to compare the second characteristic datasets to each other to determine a second number of unique faces in the environment during the second period of time, the comparator to limit the comparison of the respective second characteristic datasets to other ones of the second characteristic datasets obtained during the second period of time.

5. The apparatus as defined in claim 1 , further including a time period manager, implemented in a circuit, to:
trigger the comparator to compare the first characteristic datasets to each other after the first period of time has ended; and
trigger the discarder to delete the first characteristic datasets from the list after the first period of time has ended.

6. The apparatus as defined in claim 1 , further including a media detector to obtain media identifying information during the first period of time.

7. The apparatus as defined in claim 6 , further including a reporter to generate a data package including the media identifying information detected during the first period of time and the first number of unique faces determined by the comparator to be in the environment during the first period of time.

8. The apparatus as defined in claim 1 , further including a face detector to detect faces in the first image data, the first characteristic datasets being obtained from locations generated by the face detector.

9. The apparatus as defined in claim 1 , further including a characteristic dataset obtainer to obtain the first and second characteristic datasets, the first and second characteristic datasets including facial feature vectors.

10. A method comprising:
deleting, by executing an instruction with a processor, existing characteristic datasets from a list;
obtaining, by executing an instruction with the processor, first characteristic datasets for corresponding faces detected in a first plurality of images representative of an environment over a first period of time of a media presentation;
populating, by executing an instruction with the processor, the list with the first characteristic datasets;
limiting, by executing an instruction with the processor, a number of the first characteristic datasets stored in the list for a particular location represented in the first plurality of images to an upper limit, the limiting to reduce an amount of memory used to store the list; and
after the first period of time expires:
comparing, by executing an instruction with the processor, the first characteristic datasets to each other to determine a uniqueness of respective ones of the first characteristic datasets, the comparing limited to comparisons of the respective first characteristic datasets to other ones of the first characteristic datasets obtained during the first period of time;
deleting, by executing an instruction with the processor, the first characteristic datasets from the list; and
storing, in a memory, a first people count for the first period of time based on the comparing of the first characteristic datasets to each other.

11. The method as defined in claim 10 , further including obtaining, by executing an instruction with the processor, second characteristic datasets for corresponding faces detected in a second plurality of images representative of the environment over a second period of time of the media presentation, the second period of time subsequent to the first time.

12. The method as defined in claim 11 , further including:
populating, by executing an instruction with the processor, the list with the second characteristic datasets; and
when the second period of time expires:
comparing, by executing an instruction with the processor, the second characteristic datasets to each other to determine a uniqueness of respective ones of the second characteristic datasets, the comparing limited to comparisons of the respective second characteristic datasets to other ones of the second characteristic datasets obtained during the second period of time;
deleting, by executing an instruction with the processor, the second characteristic datasets from the list; and
storing, in the memory, a second people count for the second period of time based on the comparing of the second characteristic datasets to each other.

13. The method as defined in claim 10 , wherein the comparing of the first characteristic datasets to each other includes not comparing the first characteristic datasets to data of a facial recognition database.

14. The method as defined in claim 10 , further including obtaining media identifying information during the first period of time.

15. The method as defined in claim 14 , further including generating a data package including the media identifying information detected during the first period of time and the first people count.

16. A tangible computer readable storage medium comprising instructions that, when executed, cause a machine to at least:
delete existing characteristic datasets from a list;
populate the list with first characteristic datasets obtained from a first plurality of images representative of an environment during a first period of time of a media presentation, respective ones of the first characteristic datasets representative of respective faces detected in the environment during the first period of time;
limit a number of the first characteristic datasets stored in the list for a first location in respective ones of the first plurality of images to not exceed an upper limit;
compare the first characteristic datasets to each other to determine a first number of unique faces in the environment during the first period of time, the comparing limited to comparisons of the respective first characteristic datasets to other ones of the first characteristic datasets obtained during the first period of time;
delete the first characteristic datasets from the list afte

Assignees

• Nielsen Co Us Llc

Inventors

• Soundararajan Padmanabhan
• Usaj Marko
• Srinivasan Venugopal

Classifications

• G06T2207/30201

  Face · CPC title

• G09B5/02

  with visual presentation of the material to be studied, e.g. using film strip · CPC title

• G01B5/30

  for measuring the deformation in a solid, e.g. mechanical strain gauge · CPC title

• H04N21/4223

  Cameras (H04N23/00 takes precedence) · CPC title

• H04N21/6582

  Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number (arrangements where receivers interact with the broadcast H04H20/38) · CPC title