Smart Media Management

RELIABLE SHOT DETECTION. A shot is commonly defined as the uninterrupted recording of an event or locale. Any video sequence in this world consists of one or more shots concatenated by some kind of transition effects. Therefore, shots are generally considered as the elementary units constituting a video. Detecting shot boundaries thus means recovering those elementary video units, which in turn provide the ground for nearly all existing video abstraction and high-level video segmentation algorithms. In addition, during video production each transition type is chosen carefully in order to support the content and context of the video sequences. Therefore, automatically recovering all their positions and types may help the computer to deduce high-level semantics. For instance, in feature films dissolves are often used to convey a passage of time. Also dissolves occur much more often in features films, documentaries, biographical and scenic video material than in newscasts, sports, comedies and shows. The opposite is true for wipes. Therefore, automatic detection of transitions and their type can be used for automatic recognition of the video genre.