DEVICES, SYSTEMS, AND METHODS FOR EXAMINING THE INTERACTIONS OF OBJECTS IN AN ENHANCED SCENE

摘要

Systems, devices, and methods obtain a sequence of images of a physical scene that includes a physical representation of a first object; calculate a sequence of first transform values of the physical representation of the first object based on the sequence of images; store the sequence of first transform values; generate an enhanced scene; maintain the first object in the enhanced scene at positions and orientations that are indicated by the sequence of first transform values; receive an indication of selected transform values in the sequence of first transform values; retrieve the selected transform values; and generate a replay image of the enhanced scene, from a second observer viewpoint, that shows the first object at the position and the orientation that are indicated by the selected transform values.

主权项

1. A method comprising:
obtaining a sequence of images of a physical scene that includes a physical representation of a first object; calculating a sequence of first transform values of the physical representation of the first object based on the sequence of images, wherein transform values in the first sequence of transform values indicate a position and an orientation of the physical representation of the first object in the physical scene; storing the sequence of first transform values of the physical representation of the first object on one or more computer-readable media; generating an enhanced scene, wherein the enhanced scene includes the first object; maintaining the first object in the enhanced scene at positions and orientations that are indicated by the transform values in the sequence of first transform values; generating images of the enhanced scene, wherein each of the images of the enhanced scene is generated from a respective observer viewpoint; receiving an indication of selected transform values in the sequence of first transform values of the physical representation of the first object; retrieving the selected transform values from the sequence of first transform values; and generating a replay image of the enhanced scene, from a first observer viewpoint, that shows the first object at the position and orientation that are indicated by the selected transform values.