Abstract: The present disclosure includes, among other things, systems, methods and program products for generating a clean reference frame image. A method includes obtaining a color census of a color image. A color profile is selected based on the color census. One or more foreground areas of the image are identified, the foreground areas comprising image areas containing colors that do not fit the color profile. For each identified foreground area, a color is applied to the identified foreground area based on one or more colors of one or more non-identified image areas to create a clean reference image.

Abstract: Systems, methods, and apparatus, including software tangibly stored on a computer readable medium, involve receiving reference data and source data. The reference data includes a portion of a background image, and the background image includes an image of a background. The source data includes a portion of a source image, and the source image includes an image of the background and a foreground. A reference saturation value, which relates to a saturation of the portion of the background image, is calculated based on the reference data. A difference value, which relates to a difference between the portion of the background image and the portion of the source image, is calculated based on the source data and the reference data. A source image weighting value is determined based at least in part on a ratio between the difference value and the reference saturation value. The source image weighting value is stored, for example, in a machine-readable medium.

Abstract: An integrated and interactive real-time media creation system and method are disclosed that visually link the order and execution of media events to a scrolling on-screen text script that is spoken. As the user speaks, the on-screen text script scrolls under user control. Adjacent to the script text are visual images which represent associated media events. The visual images maintain a constant relative spatial relationship with the text. When the text reaches a predetermined region of the screen it is spoken out loud by the user and the media events are caused to occur at that time. The invention allows a single user with a single personal computer to easily self-produce a multimedia presentation of undetermined and variable length, featuring media events appropriately inserted in real-time without the assistance of a director or other operator.

Abstract: The present invention is concerned with client-side production in a personal computer environment of low bandwidth images and audio. A series of low bandwidth still images along with a “script” and audio data is sent over a network in a client/server architecture or is read from a compact disk or other memory. A “director” module residing in a client personal computer uses the “script” to tell the computer how to execute a sequence of “moves” on the still images. These moves include cuts, dissolves, fades, wipes, focuses, flying planes and digital video effects such as push and pull. Moves within a still image occur in real time, and are relatively smooth and continuous as compared to prior art network video. Low bandwidth is achieved because most of the production is done at the client location without relying upon slow, bandwidth-limited downloading of conventional network video formats.

Abstract: An integrated and interactive real-time media creation system and method are disclosed that visually link the order and execution of media events to a scrolling on-screen text script that is spoken. As the user speaks, the on-screen text script scrolls under user control. Adjacent to the script text are visual images which represent associated media events. The visual images maintain a constant relative spatial relationship with the text. When the text reaches a predetermined region of the screen it is spoken out loud by the user and the media events are caused to occur at that time. The invention allows a single user with a single personal computer to easily self-produce a multimedia presentation of undetermined and variable length, featuring media events appropriately inserted in real-time without the assistance of a director or other operator.

Abstract: A system and method for detecting the precise location of a reflective element in a video field wherein the determined location is subsequently utilized to generate a graphic to be added to a foreground video scene utilizing compositing techniques. A signal is generated specifying a precise point in the foreground video scene identifying a position of a reflective element. The signal is derived by comparing objects within the video field with a user specified size, shape and color. Graphics can be repositioned or lines or other graphic elements can be generated which track the movement of the reflective element.