| 摘要 |
A substantially vertical surface, such as in presentations, defines a gesture recognition computer input environment illuminated by at least one light source positioned and monitored by at least two cameras. The cameras generate image sets based on the reflected illuminating light, which can be used to determine a given input gesture based on changes in relative locations of the input object in each of the plurality of image sets. A controller may initiate a device input associated with the given input gesture, such as selecting a pen to draw or erase information in the projected presentation. An IR light source, and IR filters for the cameras may be used. A calibration unit may be used to determine input using parallax geometry in the separate pictures, using mid-points, en-points, length and pitch of a tracked object, such as a wand or a user's hand. The inputs may be mouse commands, zoom, rotate or other gesture controls. |
