| 摘要 |
An entertainment device captures a video image via a camera and an image analysis processor operates to identify those pixels of the video image, possibly on the basis of luminance, colour, spatial frequency, colour continuity or colour values within a tolerance range, corresponding to sky, and to generate a mask corresponding to those classified pixels. An augmented reality processor then operates to position a virtual object, which may be a person, a creature, a flying machine or a status bar on a horizontal plane at a predetermined height above the entertainment device and a rendering processor then operates to render the virtual object on the captured video image within the extent of the mask. The position of the virtual object may be adjusted based on changes in the camera viewpoint as detected by one or more motion sensors and the virtual object may be rendered with a transparency based on the cloud density at the respective pixel position as calculated by the image analysis processor. |
