×

Automated cinematic decisions based on descriptive models

  • US 10,523,864 B2
  • Filed: 10/05/2018
  • Issued: 12/31/2019
  • Est. Priority Date: 04/10/2018
  • Status: Active Grant
First Claim
Patent Images

1. A method comprising, by a computing device:

  • identifying, from a set of coordinate points that correspond to a plurality of surface points of a person in an environment, one or more coordinate points that correspond to one or more facial features of the person;

    generating a facial structure associated with the person based on the one or more coordinate points, wherein the facial structure maps the one or more facial features, wherein generating the facial structure comprises;

    comparing the one or more coordinate points to a pre-determined facial structure to determine a likelihood that the pre-determined facial structure corresponds to a facial structure of the person;

    generating a body skeletal structure for the person based on the generated facial structure, wherein generating the body skeletal structure comprises;

    aligning a candidate body skeletal structure with the generated facial structure; and

    comparing the candidate body skeletal structure to a pre-determined body skeletal structure to determine a likelihood that the pre-determined body skeletal structure corresponds to a body skeletal structure of the person;

    associating the generated body skeletal structure and facial structure with the person in the environment; and

    determining one or more instructions for a camera, microphone, speaker, or display screen based on the generated body skeletal structure and facial structure.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×