| Description |
In many video applications, the segmentation of active objects and their speech in the captured video signal is required. Example applications are video surveillance where the synchronization of audio and visual signals is required to facilitate the monitoring of important places and visual fine arts where such synchronization is required artistically such as to visualize the speech of persons inside the extracted persons' silhouettes.
In this project, students will further develop a system to capture video, to segment video objects, to extract the speech of these objects, and to synchronize objects and speech. As a system application students will visualize the speech in the object silhouettes. Students need to integrate speech recognition software. Also, they also will need to set-up the whole system so to integrate the implemented the video and audio sub-systems.
|