Methods and apparatus to count people in images

• US 8,620,088 B2
• Filed: 08/31/2011
• Issued: 12/31/2013
• Est. Priority Date: 08/31/2011
• Status: Active Grant

• Current Assignee: Nielsen Company (US) LLC (RR Donnelley & Sons Company)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Lee, Morris
• Primary Examiner(s): Ahmed, Samir
• Assistant Examiner(s): Harandi, Siamak
• Application Number:
  US13/222,084
• Publication Number:
  US 20130051677A1
• Time in Patent Office: 853 Days
• Field of Search: None
• US Class Current: 382/192
• 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 60/45 for identifying users
• CPC Class Codes: H04N 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45

Abstract

Methods, articles of manufacture, and apparatus to count people in an image are disclosed. An example method includes capturing an image of a body region in a first frame; and when a second frame different from the first frame includes the image of the body region, incrementing a first count of persons in the second frame.

Claims

1. A method to count people, comprising:

capturing an image of a body region in a first frame;

when a second frame different from the first frame includes the image of the body region, incrementing a first count of persons in the second frame; and

counting a number of faces in the second frame to form a second count.

2. A method as defined in claim 1, wherein the image is captured in response to a detection of a face corresponding to the body region.

3. A method as defined in claim 1, further comprising storing the image in association with a position of the image in the first frame.

4. A method as defined in claim 1, further comprising comparing a portion of the second frame and the image of the body region to determine if the second frame includes the image.

5. A method as defined in claim 1, further comprising determining if a body region counted in the second frame corresponds to a face counted in the second count;

and

reducing the first count if the body region corresponds to the face counted in the second count.

6. A method as defined in claim 1, further comprising summing the first count and the second count to obtain a tally of people in the second frame.

7. A method as defined in claim 6, further comprising associating the tally with media.

8. An apparatus to count people, comprising:

a face detector to detect faces in a first frame and to increment a face tally associated with the first frame based on a number of faces detected in the first frame;

a body image capturer to collect an image of a body region adjacent to a detected face from a second frame different from the first frame; and

a comparator to compare image data of the first frame to the image of the body region from the second frame, and to increment a body region count associated with the first frame when the image data of the first frame matches the image of the body region from the second frame, wherein at least one of the face detector, the body image capturer, or the comparator is implemented via a logic circuit.

9. An apparatus as defined in claim 8, further comprising a redundancy checker to check for redundancy between the body region count associated with the first frame and the face tally associated with the first frame.

10. An apparatus as defined in claim 9, wherein the redundancy checker is to decrement the body region count when the redundancy checker detects the redundancy.

11. An apparatus as defined in claim 9, wherein the redundancy checker is to sum the face tally and the body region count to form a people tally.

12. An apparatus as defined in claim 11, further comprising a content identifier to associate the people tally with media identifying information corresponding to media associated with the first frame.

13. An apparatus as defined in claim 8, wherein a location of the body region is based on a position of the adjacent face.

14. An apparatus as defined in claim 13, wherein the position is a coordinate of a grid overlaid on the first and second frames.

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

detect a first face in a first frame corresponding to a first time;

capture an image of a region adjacent the first face in the first frame, the region being at a first position within the first frame;

determine whether a second frame corresponding to a second time includes the image at the first position; and

increment a people tally associated with the second frame when the second frame includes the image at the first position and the detected face of the first frame is not detected in the second frame.

16. A computer readable medium as defined in claim 15, the instructions to cause the machine to associate the people tally with media being presented at the second time.

17. A computer readable medium as defined in claim 15, wherein the region adjacent the first face is calculated by generating a box based on a reference point of the detected first face.

18. A computer readable medium as defined in claim 15, the instructions to cause the machine to determine that the second frame includes the image at the first position when the second frame includes image data similar within a threshold to the image of the region adjacent the first face at the first position.