Methods and apparatus to determine an audience composition based on thermal imaging and facial recognition
Methods, apparatus, systems and articles of manufacture are disclosed. An example apparatus includes a thermal image detector to determine a heat blob count based on a frame of thermal image data captured in the media environment, an audience image detector to identify a face of an audience member based on a frame of audience image data captured in the media environment, the frame of audience image data corresponding to a field of view associated with at least one heat blob included in the heat blob count, and a people meter controller to cause a people meter, which is to emit a prompt for audience identification information, not to emit the prompt for at least a first time period after the audience member is identified.
1 . A computing system comprising:
a thermal camera;
a visible-light camera having a default field of view of a media environment; and
a control system configured to:
identify, based on a frame of thermal image data captured by the thermal camera, a heat blob in the media environment,
determine a heat blob count based on the identified heat blob,
cause the visible-light camera to adjust the field of view of the visible-light camera based on a location of the heat blob in the media environment, wherein the adjusted field of view is a proper subset of the default field of view,
obtain a frame of audience image data captured by the visible-light camera with the adjusted field of view of the visible-light camera,
identify a face of an audience member based on the frame of audience image data,
generate exposure data using the identified face,
compare a number of identified audience members to the heat blob count, and
initiate a prompt for audience identification information based on a mismatch between the heat blob count and the number of identified audience members.
2 . The computing system of claim 1 , wherein the control system is further configured to identify the face of the audience member based on an eye, a mouth, or a nose.
3 . The computing system of claim 1 , wherein the control system is further configured to:
obtain the frame of audience image data based on a change in the heat blob count.
4 . The computing system of claim 1 , wherein the control system is further configured to identify the face based on a comparison of the frame of audience image data with a library of reference audience member images.
5 . The computing system of claim 3 , wherein the change in the heat blob count is an increase in the heat blob count from one to an integer that is greater than one.
6 . A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a set of operations comprising:
identifying, based on a frame of thermal image data captured by a thermal camera, a heat blob in a media environment;
determining a heat blob count based on the identified heat blob;
causing a visible-light camera to adjust a field of view of the visible-light camera based on a location of the heat blob in the media environment, wherein visible-light camera has a default field of view of the media environment, and wherein the adjusted field of view is a proper subset of the default field of view;
obtaining a frame of audience image data captured by the visible-light camera with the adjusted field of view of the visible-light camera;
identifying a face of an audience member based on the frame of audience image data;
generating exposure data using the identified face;
comparing a number of identified audience members to the heat blob count; and
initiating a prompt for audience identification information based on a mismatch between the heat blob count and the number of identified audience members.
7 . The non-transitory computer readable storage medium of claim 6 , wherein identifying the face of the audience member comprises identifying the face of the audience member based on an eye, a mouth, or a nose.
8 . The non-transitory computer readable storage medium of claim 6 , wherein;
the obtaining the frame of audience image data is based on a change in the heat blob count.
9 . The non-transitory computer readable storage medium of claim 6 , wherein identifying the face comprises identifying the face based on a comparison of the frame of audience image data with a library of reference audience member images.
10 . A method comprising:
identifying, based on a frame of thermal image data captured by a thermal camera, a heat blob in a media environment;
determining a heat blob count based on the identified heat blob;
causing a visible-light camera to adjust a field of view of the visible-light camera based on a location of the heat blob in the media environment, wherein visible-light camera has a default field of view of the media environment, and wherein the adjusted field of view is a proper subset of the default field of view;
obtaining a frame of audience image data captured by the visible-light camera with the adjusted field of view of the visible-light camera;
identifying a face of an audience member based on the frame of audience image data;
generating exposure data using the identified face;
comparing a number of identified audience members to the heat blob count; and
initiating a prompt for audience identification information based on a mismatch between the heat blob count and the number of identified audience members.
11 . The method of claim 10 , wherein identifying the face of the audience member comprises identifying the face of the audience member based on an eye, a mouth, or a nose.
12 . The method of claim 10 , wherein:
the obtaining the frame of audience image data is based on a change in the heat blob count.
13 . The method of claim 10 , wherein identifying the face comprises identifying the face based on a comparison of the frame of audience image data with a library of reference audience member images.
14 . The method of claim 12 , wherein the change in the heat blob count is an increase in the heat blob count from one to an integer that is greater than one.