Method and apparatus for generating a summary of an audio/visual data stream

Apparatus for generating a summary of an audio/visual data stream, said data stream comprising a plurality of consecutive frames having audio and visual properties, the apparatus comprising:

• a shot detector for detecting a plurality of shots of the audio/visual data stream, wherein each shot comprises a plurality of consecutive frames of said date stream that focus on a same view shot;
• a determining means for determining a plurality of segments of said data stream, wherein each segment comprises a plurality of shots of the detected plurality of shots of said data stream having similar visual properties;
• a first selector for selecting a segment of said determined plurality of segments;
• an extractor for extracting, for each respective shot of said selected segment of said data stream, audio of a plurality of consecutive frames of said data stream which occur after an end of said respective shot;
• a second selector for selecting at least one of said shots of said selected segment based on the extracted audio;
• and
• a summary generator for generating a summary to include said selected at least one of said shots,
• wherein said extracting the audio comprises calculating an audio power of the audio in the plurality of consecutive frames of said data stream which occur after the end of said respective shot for a predefined part of an audio frequency spectrum.