| 摘要 |
The invention relates to a system 100 for the processing of audiovisual data 118,120 aimed at reducing the difficulty in using the systems 100 software or hardware and particularly post production tools 122. It involves user input for the selection of sound effects applied to objects by an audio manipulation module 108. The objects positions are identified from a visual data stream by an object recognition module 102 and the sound effects are based on the objects positions with the output of lists of the sound types and the selected effects. A communication module 110 receives these lists and outputs a set of instructions to an audio post-production system 122 to create the required effects. The user may mark objects and the object recognition module 102 then track the marked objects. The object recognition module 102 and the audio manipulation module 108 may operate automatically. User input may provide the position of an object such as a wall outside the cameras view, the position of which affects the sound of an object within the cameras view by, for example, reverb or echo. |
