Method for tracking subject head position from monocular-source image sequence
A subject's head position and motion can be tracked by analyzing a series of frames from a monocular camera and mapping distinguishing points visible in the frames onto an elliptical cylinder. The tracking data can be used to control a physical pan/tilt actuator or to reconfigure/reposition virtual objects, images of which can be synthesized and displayed, or composited back into the original frames and displayed.
1. A non-transitory computer-readable medium containing data and instructions to cause a programmable processor to perform operations comprising:
analyzing an initial sequence of raster images of a subject to find a neutral image where a head of the subject is in a facing-forward position;
identifying neutral fiducials in the neutral image;
mapping the neutral fiducials to at least one three-dimensional cylinder model in a neutral position;
receiving a tracking raster image after the initial sequence of raster images, said tracking raster image showing the head of the subject in a displaced position relative to the forward-facing position;
identifying tracking fiducials in the tracking raster image;
finding a displaced position of the at least one three-dimensional cylinder model such that the tracking fiducials map near the neutral fiducials on the at least one three-dimensional cylinder model;
emitting tracking data to indicate how the displaced position is different from the neutral position;
altering a configuration of a three-dimensional virtual model according to the tracking data;
rendering an image of the three-dimensional virtual model; and
displaying the image of the three-dimensional virtual model.
2. The non-transitory computer-readable medium of claim 1 , wherein the at least one three-dimensional cylinder model is exactly one three-dimensional elliptical cylinder model.
3. The non-transitory computer-readable medium of claim 1 , wherein the at least one three-dimensional cylinder model is at least two concentric round cylinders having a common central axis.
4. The non-transitory computer-readable medium of claim 1 , wherein the three-dimensional virtual model is a character in a massively multiplayer online role-playing game (“MMPORG”).
5. The non-transitory computer-readable medium of claim 1 , wherein the image of the three-dimensional virtual model is displayed to an individual different from the subject.
6. The non-transitory computer-readable medium of claim 1 , wherein the three-dimensional virtual model is a pair of eyeglasses.
7. The non-transitory computer-readable medium of claim 6 , wherein the image of the three-dimensional virtual model is displayed to the subject.
8. The non-transitory computer-readable medium of claim 1 , wherein the three-dimensional virtual model is hair.
9. The non-transitory computer-readable medium of claim 8 , wherein the image of the three-dimensional virtual model is displayed to the subject.