Back to results
US 8,805,016 B2Granted
Method for augmenting a real scene
AssigneeTotal Immersion
InventorsValentin Lefevre, Nicolas Livet
Life of this patent
Estimating the term…
Abstract
Methods, systems and devices for augmenting a real scene in a video stream are disclosed herein.
Claims9
A method for augmenting video images of a real scene with a virtual object, the method comprising:
- receiving a first image from a video stream of the real scene, wherein the first image includes a marker-free object to be tracked;
- determining a pose of the marker-free object being tracked in the first image by comparing the pose of the object being tracked to a plurality of image blocks, wherein each image block of the plurality of image blocks is associated with a unique pose;
- determining a geometrical model of the real scene;
- calculating a geometrical transformation between the pose of the marker-free object being tracked and the geometrical model of the real scene, wherein the geometrical transformation is a geometrical relationship between the pose of the marker-free object being tracked relative to the geometrical model of the real scene;
- adding an animated virtual object to the video stream based on the geometrical transformation, wherein the animated virtual object moves as a function of the geometrical model of the real scene;
- and
- displaying the video stream including the animated virtual object.
4 more elements
A method for augmenting video images of a real scene with a virtual object, the method comprising:
- receiving a first image from a video stream of the real scene, wherein the first image includes marker-free object to be tracked;
- determining a pose of the marker-free object being tracked in the first image based on a comparison between the pose of the marker-free object being tracked and a plurality of image blocks, wherein each image block of the plurality of image blocks is associated with a unique pose;
- receiving a second image from the video stream, wherein the second image includes the marker-free object being tracked;
- evaluating the pose of the marker-free object being tracked in the second image based on the plurality of the image blocks;
- determining a geometrical model of the real scene;
- calculating a geometrical transformation between the pose of the marker-free object being tracked and the geometrical model of the real scene, wherein the geometrical transformation is a geometrical relationship between the pose of the marker-free object being tracked relative to the geometrical model of the real scene;
- adding an animated virtual object to the video stream based on the geometrical transformation, wherein the animated virtual object moves as a function of the geometrical model of the real scene;
- and
- displaying the video stream including the animated virtual object.
6 more elements
Dependencies are inferred from the claim text.