| 摘要 |
Described is a video generation system that allows a user to be filmed and merged into a premade video sequence. The system is configured to receive a video having a plurality of characters, each character having a corresponding audio track. A user can remove one of characters and corresponding audio track from the video, leaving remaining characters and remaining audio track. The video with the remaining characters and remaining audio track is then played on a display. Using a sensor and microphone, a user video image and corresponding user audio track is received. The user video image and user audio track is recorded as it is received while the video with remaining characters and corresponding audio track is played on the display. Thus, once merged, the user video image and user audio track can be played along with the video with the remaining characters and the remaining audio track.
|
