System and associated methods of calibration and use for an interactive imaging environment
In various embodiments, the present invention provides a system and associated methods of calibration and use for an interactive imaging environment based on the optimization of parameters used in various segmentation algorithm techniques. These methods address the challenge of automatically calibrating an interactive imaging system, so that it is capable of aligning human body motion, or the like, to a visual display. As such the present invention provides a system and method of automatically and rapidly aligning the motion of an object to a visual display.
1. A system, comprising:
an infrared image sensor configured to detect infrared energy;
a light sensor configured to detect visible light;
a vision engine configured to detect one or more objects in a field of view in front of a projected image and configured to segment the one or more objects and a background;
wherein the vision engine comprises a segmentation algorithm with a plurality of parameters and an objective function to set and adjust one or more of the plurality of parameters of the segmentation algorithm.
2. The system of claim 1 , further comprising:
one or more illumination energy devices configured to flood the field of view in front of the projected image with illumination energy;
an interaction engine operable for inserting an abstraction related to one or more users or the background; and
a rendering engine configured to modify the projected image in response to a presence or motion of the one or more users, thereby providing user interaction with the projected image.
3. The system of claim 2 , wherein the illumination energy comprises near-infrared light.
4. The system of claim 2 , wherein the illumination energy comprises structured infrared light.
5. The system of claim 2 , wherein illumination energy comprises structured and strobed infrared light.
6. The system of claim 2 , wherein the vision engine is configured to:
detect the one or more users in the field of view in front of the projected image; and
segment the one or more users and the background, utilizing the parallax effect, wherein the segmenting comprises calibrating the segmentation algorithm.
7. The system of claim 1 , further comprising an optical filter coupled with the infrared image sensor operable to filter out illumination energy of a predetermined wavelength or wavelength range.
8. The system of claim 1 , further comprising an optical filter coupled with the light image sensor operable to filter out illumination energy of a predetermined wavelength or wavelength range.
9. The system of claim 1 , wherein the segmentation algorithm is background subtraction.
10. The system of claim 1 , wherein the segmentation algorithm is stereo disparity-based foreground detection.
11. The system of claim 1 , wherein the objective function comprises a gradient descent method.
12. The system of claim 1 , wherein the objective function comprises a Levenberg-Marquardt method.
13. A method, comprising:
projecting an image with an image generator;
detecting infrared energy with an infrared image sensor;
detecting visible light with an image sensor; and
detecting one or more users in a field of view in front of the projected image; and
segmenting the one or more users and a background, wherein the segmenting comprises calibrating a segmentation algorithm with a plurality of parameters and an objective function to set and adjust one or more of the parameters of the segmentation algorithm.
14. A method, comprising:
creating or projecting an image with an interactive imaging system; and
detecting a user in a field of view in front of the created or projected image and segmenting the users and a background, wherein the segmenting comprises calibrating a segmentation algorithm with a plurality of parameters and an objective function to set and adjust one or more of the parameters of the segmentation algorithm.