System and method of user interaction for augmented reality
AssigneeSony Computer Entertainment Europe Limited
InventorsSharwin Winesh Raghoebardajal, Mark Lintott
Life of this patent
Estimating the term…
Abstract
A method of user interaction in augmented reality comprises the steps of capturing a video image of a scene, and for each pixel in at least a sub-region of the captured video, classifying the pixel as either a skin or non-skin pixel responsive to whether the color of the pixel exceeds a predetermined threshold purity of red; and generating a mask based upon the classification of the pixels of the captured video, generating an augmentation image layer to superpose on the captured video image, and limiting a mode of combination of the captured video and the augmentation image layer, responsive to the mask.
Claims14
A method of augmented reality comprising the steps of:
- providing a book having blue or green pages;
- capturing a video image of a scene comprising the book;
- for each pixel in at least a sub-region of the captured video image, classifying the pixel as either a skin or non-skin pixel responsive to whether the colour of the pixel exceeds a predetermined threshold ratio of red to blue or green;
- generating a mask based upon the classification of the pixels of the captured video;
- generating an image layer comprising a virtual entity to superpose on the book in the captured video image of the scene comprising the book;
- and
- generating an augmented image of the scene comprising the book by superposing the image layer on the captured video image of the scene comprising the book;
- in which the pixels of the image layer that correspond to skin pixels in the mask are masked out to retain skin pixels in the augmented image.
A system, comprising:
- a book having blue or green pages;
- and
- an entertainment device, comprising:
- video input means for receiving a captured video image of a scene comprising the book;
- image augmentation means for generating an image layer comprising a virtual entity to superpose on the book in the captured video image of the scene comprising the book;
- image processing means for classifying each pixel of at least a sub-region of the captured video as either a skin or non-skin pixel, responsive to whether the colour of the pixel exceeds a predetermined threshold ratio of red to blue or green;
- wherein the image augmentation means is operable to generate an augmented image of the scene comprising the book by superposing the image layer on the captured video image of the scene comprising the book;
- mask generating means operable to generate a mask based upon the classification of the pixels of the captured video of the scene comprising the book;
- and wherein
- the entertainment device is operable to mask out the pixels of the image layer that correspond to skin pixels in the mask, to retain skin pixels in the augmented image.
Dependencies are inferred from the claim text.