Methods and apparatus to count people in images
AssigneeThe Nielsen Company (US), LLC
InventorsVenugopal Srinivasan, Padmanabhan Soundararajan
Life of this patent
Estimating the term…
Abstract
Methods and apparatus to count people in images are disclosed. An example method includes generating a first fluctuation factor for a first frame by averaging fluctuation values of a random set of pixels of the first frame; generating a second fluctuation factor for a person indication area of the first frame by averaging fluctuation values of pixels of the person indication area; and marking the person indication area as a false positive when the second fluctuation factor is less than or equal to the first fluctuation factor.
Claims20
A method, comprising:
- generating a first fluctuation factor for a first frame by averaging fluctuation values of a random set of pixels of the first frame;
- generating a second fluctuation factor for a person indication area of the first frame by averaging fluctuation values of pixels of the person indication area;
- and
- marking the person indication area as a false positive when the second fluctuation factor is less than or equal to the first fluctuation factor.
A tangible machine readable storage medium comprising instructions that, when executed, cause a machine to at least:
- generate a first fluctuation factor for a first frame by averaging fluctuation values of a random set of pixels of the first frame;
- generate a second fluctuation factor for a person indication area of the first frame by averaging fluctuation values of pixels of the person indication area;
- and
- identify the person indication area as a false positive when the second fluctuation factor is less than or equal to the first fluctuation factor.
An apparatus, comprising:
- a processor to generate a first fluctuation factor for a first frame by averaging fluctuation values of a random set of pixels of the first frame, the processor to generate a second fluctuation factor for a person indication area of the first frame by averaging fluctuation values of pixels of the person indication area;
- and
- a comparator to identify the person indication area as a false positive when the second fluctuation factor is less than or equal to the first fluctuation factor.
Dependencies are inferred from the claim text.