Methods and apparatus to monitor environments
View Patent ↗Methods and apparatus to monitor environments are disclosed. An example method includes analyzing, with a processor, a plurality of three-dimensional data points having respective depth values representative of distances from a sensor of an environment; when a first set of the three-dimensional data points has a first depth value satisfying a threshold, executing, with the processor, a first type of recognition analysis on a first area of the environment corresponding to the first set of the three-dimensional data points; and when a second set of the three-dimensional data points has a second depth value not satisfying the threshold, executing, with the processor, a second type of recognition analysis different than the first type of recognition analysis on a second area of the environment corresponding to the second set of the three-dimensional data points.
1. A method, comprising:
analyzing, by executing an instruction with a processor, a plurality of three-dimensional data points having respective depth values representative of distances from a sensor of an environment;
when a first set of the three-dimensional data points has a first depth value satisfying a threshold, executing, by executing an instruction with the processor, a three-dimensional recognition analysis on a first area of the environment corresponding to the first set of the three-dimensional data points; and
when a second set of the three-dimensional data points has a second depth value not satisfying the threshold, executing, by executing an instruction with the processor, a two-dimensional recognition analysis on a second area of the environment corresponding to a first set of two-dimensional data points representative of at least a portion of the environment corresponding to the second set of three-dimensional data points.
2. The method as defined in claim 1 , wherein the three-dimensional data points are captured via a depth sensor using electromagnetic beams projected in a pattern, and the two-dimensional data points are captured via a camera.
3. The method as defined in claim 1 , further including storing a two-dimensional coordinate of the first set of the three-dimensional data points in association with a first frame.
4. The method as defined in claim 3 , further including using the two-dimensional coordinate to focus the two-dimensional recognition analysis on the first area of the environment for a second frame subsequent to the first frame.
5. The method as defined in claim 1 , further including triggering execution of the two-dimensional recognition analysis in response to elapsing of a time interval.
6. The method as defined in claim 1 , wherein the first three-dimensional and two-dimensional recognition analyses determine whether an object of the environment corresponds to a person, and further including calculating a people count using results of the at least one of the three dimensional or two dimensional recognition analyses.
7. A tangible machine readable storage medium comprising instructions that, when executed, cause a machine to at least:
analyze a plurality of three-dimensional data points having respective depth values representative of distances from a sensor of an environment;
when a first set of the three-dimensional data points has a first depth value satisfying a threshold, execute a three-dimensional recognition analysis on a first area of the environment corresponding to the first set of the three-dimensional data points; and
when a second set of the three-dimensional data points has a second depth value not satisfying the threshold, execute a two-dimensional recognition analysis on a second area of the environment corresponding to a first set of two-dimensional data points representative of at least a portion of the environment corresponding to the second set of three-dimensional data points.
8. The storage medium as defined in claim 7 , wherein the three-dimensional data points are captured via a depth sensor using electromagnetic beams projected in a pattern, and the two-dimensional data points are captured via a camera.
9. The storage medium as defined in claim 7 , wherein the instructions, when executed, cause the machine to store a two-dimensional coordinate of the first set of the three-dimensional data points in association with a first frame.
10. The storage medium as defined in claim 9 , wherein the instructions, when executed, cause the machine to use the two-dimensional coordinate to focus the two-dimensional recognition analysis on the first area of the environment for a second frame subsequent to the first frame.
11. The storage medium as defined in claim 7 , wherein the instructions, when executed, cause the machine to trigger execution of the two-dimensional recognition analysis in response to elapsing of a time interval.
12. The storage medium as defined in claim 7 , wherein the three-dimensional and two-dimensional recognition analyses determine whether an object of the environment corresponds to a person, and the instructions, when executed, cause the machine to calculate a people count using results of the at least one of the three-dimensional or two-dimensional of recognition analyses.
13. An audience measurement device, comprising:
a depth filter to analyze a plurality of three-dimensional data points having respective depth values representative of distances from a sensor of an environment;
a first data analyzer to, when the depth filter determines that a first set of the three-dimensional data points has a first depth value satisfying a threshold, execute a three-dimensional recognition analysis on a first area of the environment corresponding to the first set of the three-dimensional data points;
a second data analyzer to, when a second set of the three-dimensional data points has a second depth value not satisfying the threshold, execute a two-dimensional recognition analysis on a second area of the environment corresponding to a first set of two-dimensional data points representative of at least a portion of the environment corresponding to the second set of three-dimensional data points, at least one of the depth filter, the first data analyzer, or the second data analyzer implemented via a logic circuit.
14. The audience measurement device as defined in claim 13 , further including a depth sensor to capture the three-dimensional data points using electromagnetic beams projected in a pattern, and a camera to capture the two-dimensional data points.
15. The audience measurement device as defined in claim 13 , wherein the second data analyzer is to use a two-dimensional coordinate of the first set in a first frame to focus the two-dimensional recognition analysis on the first area of the environment for a second frame subsequent to the first frame.
16. The audience measurement device as defined in claim 13 , further including a trigger to trigger the second data analyzer to execute the two-dimensional recognition analysis in response to elapsing of a time interval.
17. The audience measurement device as defined in claim 13 , wherein the first and second data analyzers are to determine whether an object of the environment corresponds to a person, and further including a body counter to calculate a people count using results of the at least one of the first three-dimensional or two-dimensional recognition analyses.