METHODS, APPARATUS AND ARTICLES OF MANUFACTURE TO MONITOR ENVIRONMENTS

• US 20140254880A1
• Filed: 03/06/2013
• Published: 09/11/2014
• Est. Priority Date: 03/06/2013
• 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
• Granted Patent: US 9,292,923 B2
• Time in Patent Office: Days
• US Class Current: 382/106
• CPC Class Codes: G01B 11/22 for measuring depth
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

Methods, apparatus, and articles of manufacture to monitor environments are disclosed. An example method includes analyzing a first depth value corresponding to a coordinate of an object of an image captured by a depth sensor, the first depth value having been captured with the depth sensor positioned at a first angle relative to a reference axis; moving the depth sensor to a second angle relative to the reference axis, the second angle being different than the first angle; triggering capture of a second depth value at the coordinate with the depth sensor positioned at the second angle; and calculating a depth gradient for the coordinate based on the first and second depth values.

Claims

1. A method, comprising:

analyzing a first depth value corresponding to a coordinate of an object of an image captured by a depth sensor, the first depth value having been captured with the depth sensor positioned at a first angle relative to a reference axis;

moving the depth sensor to a second angle relative to the reference axis, the second angle being different than the first angle;

triggering capture of a second depth value at the coordinate with the depth sensor positioned at the second angle; and

calculating a depth gradient for the coordinate based on the first and second depth values.

2. A method as defined in claim 1, further comprising triggering the capture of the second depth value with the depth sensor at the second angle based on a comparison of the first depth value and a threshold.

3. A method as defined in claim 2, wherein a value of the threshold depends on whether an object, a movement or a gesture is being analyzed.

4. A method as defined in claim 1, further comprising triggering the capture of the second depth value with the depth sensor at the second angle in response detecting movement at the coordinate.

5. A method as defined in claim 1, wherein moving the depth sensor comprises actuating a tilt motor of coupled to a housing of the depth sensor.

6. A method as defined in claim 1, further comprising triggering capture of a third depth value at the coordinate with the depth sensor positioned at a third angle relative to the reference axis, the third angle being different than the first and second angles.

7. A method as defined in claim 6, wherein the calculation of the depth gradient for the coordinate includes consideration of the third depth value.

8. A method as defined in claim 1, wherein the reference axis is a horizontal axis extending away from the depth sensor into the environment.

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

analyze a first depth value corresponding to a coordinate of an object in an image captured by a depth sensor, the first depth value having been captured with the depth sensor positioned at a first angle relative to a reference axis;

determine whether a condition associated with a recognition analysis coordinate is present at the coordinate; and

in response to the condition being present at the coordinate;

trigger capture of a second depth value at the coordinate with the depth sensor positioned at a second angle relative to the reference axis, the second angle being different than the first angle; and

calculate an accumulated value for the coordinate based on the first and second depth values.

10. A storage medium as defined in claim 9, wherein the condition comprises an indication that a person is detected at the coordinate at a distance from the depth sensor greater than a threshold distance associated with a person detector.

11. A storage medium as defined in claim 9, wherein the condition comprises an indication that movement is detected at the coordinate at a distance from the depth sensor greater than a threshold distance associated with a movement detector.

12. A storage medium as defined in claim 9, wherein the condition comprises an indication that a gesture is detected at the coordinate at a distance from the depth sensor greater than a threshold distance associated with a gesture detector.

13. A storage medium as defined in claim 9, wherein the instructions cause the machine to trigger capture of a third depth value at the coordinate with the depth sensor positioned at a third angle relative to the reference axis, the third angle being different than the first and second angles.

14. A storage medium as defined in claim 13, wherein the instructions cause the machine to calculate the accumulated value based on the first, second and third depth values.

15. An audience measurement device, comprising:

a recognizer to identify an object as likely being a person by analyzing data representative of the environment; and

a depth analyzer to, when a first depth value associated with the object captured by a depth sensor is greater than a threshold distance;

cause the depth sensor to capture a second depth value at the coordinate with the depth sensor positioned at a first tilt; and

calculate an accumulated value for the coordinate based on a comparison of the first and second depth values.

16. An audience measurement device as defined in claim 15, wherein when the depth sensor is positioned at the first tilt, the depth sensor is positioned at a first angle different than a baseline angle at which the first depth value was captured.

17. An audience measurement device as defined in claim 15, further comprising using the accumulated value to confirm that the object is a person.

18. An audience measurement device as defined in claim 15, wherein the depth analyzer is to move the depth sensor to the first tilt from a baseline angle by actuating a tilt motor.

19. An audience measurement device as defined in claim 15, wherein the first tilt is a predefined angular position a particular degree away from a reference axis extending away from the depth sensor.

20. An audience measurement device as defined in claim 15, wherein the depth sensor utilizes a projected dot array, and a first dot of the dot array corresponds to the coordinate.

21. An apparatus, comprising:

a depth sensor to collect images of an environment, the depth sensor having a housing;

a tilt mechanism to tilt the housing of the depth sensor relative to a reference axis; and

a processor to;

determine a first depth value associated with a coordinate of a first image collected with the housing at a first angle relative to the reference axis;

instruct the tilt mechanism to move the housing to a second angle relative to the reference axis, the second angle being different from the first angle;

determine a second depth value associated with the coordinate detected by the depth sensor with the housing at the second angle; and

calculate a depth gradient for the coordinate based on the first depth value, the second depth value, and the second angle.