×

Method for triggering events in a video

  • US 10,283,162 B2
  • Filed: 06/25/2014
  • Issued: 05/07/2019
  • Est. Priority Date: 02/05/2014
  • Status: Active Grant
First Claim
Patent Images

1. A computer-implemented method for triggering events in a video, the method being performed in connection with a computerized system comprising a processing unit and a memory, the method comprising:

  • providing a list comprising a set of objects, a set of object states associated with the set of objects, and a set of events, wherein the set of objects are associated with one or more images of a user and each object from the set of objects has at least one object state triggering at least one event from the set of events in the video and each object state is associated with at least one point of an object of the set of objects;

    detecting a face of the user within frames of the video, the face including a set of landmark points corresponding to facial features;

    aligning a mesh with the face of the user, the mesh containing a set of feature reference points, each feature reference point corresponding to a landmark point of the set of landmark points;

    detecting at least one object from the list that at least partially and at least occasionally is presented in frames of the video, the at least one object including at least a portion of the set of feature reference points, the portion of the set of feature reference points aligned with one or more points of the at least one object;

    tracking the at least one object across two or more frames, the at least one object having a first object state;

    identifying a change in the first object state of the at least one object to a second object state, the change from the first object state to the second object state corresponding to movement of a first portion of landmark points relative to one or more feature reference points of the mesh, indicating movement of the first portion of landmark points on the face of the user, while a second portion of landmark points remain aligned with corresponding feature reference points of the mesh;

    determining that the second object state of the at least one object matches a state from the set of object states; and

    in response to determining the match, triggering at least one event of the set of events in the video, the at least one event modifying the one or more images of the user by;

    selecting a visualization from a plurality of visualizations associated with the at least one event; and

    replacing at least a portion of the face, associated with the feature reference point within the frames of the video, with the selected visualization to modify the video, the feature reference point corresponding to the at least one point moved by the change from the first object state to the second object state.

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