Methods, apparatus and articles of manufacture to detect shapes

• US 9,866,900 B2
• Filed: 03/12/2013
• Issued: 01/09/2018
• Est. Priority Date: 03/12/2013
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Terrazas, Alejandro
• Primary Examiner(s): Flynn, Nathan
• Assistant Examiner(s): Fogg, Cynthia
• Application Number:
  US13/797,010
• Publication Number:
  US 20140282644A1
• Time in Patent Office: 1,764 Days
• Field of Search: 725 12, 348241, 382154
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: H04N 21/42201 biosensors, e.g. heat sensor for presence detection, EEG sensors or any limb activity sensors worn by the user input arrangements for interaction with the human body based on nervous system activity detection G06F3/015
• CPC Class Codes: H04N 21/4223 Cameras H04N23/00 takes precedence
• CPC Class Codes: H04N 21/442 Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk arrangements for monitoring broadcast services or broadcast-related services H04H60/29; arrangements for identifying or recognising characteristics with a direct linkage to broadcast information H04H60/35; monitoring of user activities for profile generation for accessing a video database G06F16/739; monitoring in wireless networks H04W24/00
• 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
• CPC Class Codes: H04N 23/45 for generating image signals from two or more image sensors being of different type or operating in different modes, e.g. with a CMOS sensor for moving images in combination with a charge-coupled device [CCD] for still images
• CPC Class Codes: H04N 5/33 Transforming infrared radiation cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20

Abstract

Methods, apparatus, and articles of manufacture to detect shapes are disclosed. An example method includes determining a depth value associated with an object outline detected in image data representative of an environment; and using the depth value to select a first group of reference shapes to be compared to the object outline from a collection of reference shapes, the first group representing a portion of the collection of reference shapes.

Claims

1. A method, comprising:

determining, by executing an instruction with a processor, a measured distance from an image capturing device to an object outline detected in image data representative of an environment, the determining of the measured distance including aggregating a plurality of depth values associated with the object outline;

when the measured distance corresponds to a first distance, selecting, by executing an instruction with the processor, a first group of reference shapes from a database for comparison to the object outline, the first group representing a subset of a collection of reference shapes in the database, the first group being selected to meet a first likelihood threshold of being detected at the first distance, the first likelihood threshold being different from a second likelihood threshold used to select a second group of reference shapes when the measured distance corresponds to a second distance different from the first distance; and

limiting comparison of the object outline to the reference shapes of the first group to reduce computational resource usage relative to comparing the object outline to each one of the collection of reference shapes in the database.

2. The method as defined in claim 1, further including identifying an object corresponding to the detected object outline based on a similarity between the detected object outline and a first one of the reference shapes of the first group.

3. The method as defined in claim 2, further including:

incrementing a people tally when the identified object corresponds to a person; and

associating the people tally with media detected in the environment at a same time as when the detection of the object outline occurred.

4. The method as defined in claim 1, wherein the reference shapes of the first group are determined unlikely to be detectable at the second distance.

5. The method as defined in claim 1, wherein the plurality of depth values are associated with points that fall within the detected object outline, the points selected according to a predetermined pattern.

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

determine a measured distance from an image capturing device to an object outline detected in image data representative of an environment, the measured distance determined by aggregating a plurality of depth values associated with the object outline;

when the measured distance corresponds to a first distance, selecting, for comparison to the object outline, a first subset of a collection of reference shapes from a database likely to be detected at the first measured distance, the first subset being selected to meet a first likelihood threshold of being detected at the first distance, the first likelihood threshold being different from a second likelihood threshold used to select a second subset of the collection of reference shapes when the measured distance corresponds to a second distance different from the first distance; and

limit comparison of the object outline to the reference shapes of the first subset to reduce computational resource usage relative to comparing the object outline to each one of the collection of reference shapes of the database.

7. The storage medium as defined in claim 6, wherein the instructions, when executed, further cause the machine to identify an object corresponding to the object outline based on a similarity between the object outline and a first one of the reference shapes of the first subset.

8. The storage medium as defined in claim 7, wherein the instructions, when executed, further cause the machine to:

increment a people tally when the object corresponds to a person; and

associate the people tally with media detected in the environment at a time corresponding to the detection of the object outline.

9. The storage medium as defined in claim 6, wherein the first subset includes a reference shape unlikely to be detectable at the second distance.

10. The storage medium as defined in claim 6, wherein the plurality of depth values are associated with points that fall within the detected object outline, the points selected according to a predetermined pattern.

11. An apparatus, comprising:

a calculator to calculate a first distance from an image capturing device to an object outline detected in image data representative of an environment by aggregating a plurality of depth values associated with the object outline;

a selector to select, based on the first distance, a first subset of reference shapes from a plurality of reference shapes in a database for comparison to the object outline, the first subset being selected to meet a first likelihood threshold of being detected at the first distance, the first likelihood threshold being different from a second likelihood threshold used to select a second subset of the collection of reference shapes when the measured distance corresponds to a second distance different from the first distance, at least one of the calculator or the selector being implemented via a logic circuit; and

a comparator to limit comparison of the object outline to the reference shapes of the first subset to reduce computational resource usage relative to comparing the object outline to each one of reference shapes in the database.

12. The apparatus as defined in claim 11, wherein the comparator is to identify an object corresponding to the object outline based on a similarity between the object outline and a first one of the reference shapes of the first subset.

13. The apparatus as defined in claim 11, wherein the plurality of depth values are associated with points that fall within the detected object outline, the points selected according to a predetermined pattern.

14. A method, comprising:

identifying, via a logic circuit, an object outline in image data generated by an image capturing device;

determining, via the logic circuit, a first distance between the object outline and the image capturing device by aggregating a plurality of depth values associated with the object outline;

identifying a first subset of a collection of reference shapes in a database, the first subset selected to meet a first likelihood threshold of being detected at the first distance, the first likelihood threshold being different from a second likelihood threshold used to select a second subset of the collection of reference shapes when the measured distance corresponds to a second distance different from the first distance; and

limiting comparison of the object shape to at least some of the first subset of the collection of reference shapes to reduce computational resource usage relative to comparing the object outline to each one of the collection of reference shapes in the database.

15. The method as defined in claim 14, wherein the plurality of depth values are associated with points that fall within the detected object outline, the points selected according to a predetermined pattern.