Wavelet-based video indexing and querying

We present several algorithms suitable for analysis of broadcast video. Fir st. we show how wavelet analysis of frames of video can be used to detect t ransitions between shots in a video stream, thereby dividing the stream int o segments. Next we describe how each segment can be inserted into a video database using an indexing scheme that involves a wavelet-based "signature. " Finally, we show that during a subsequent broadcast of a similar or ident ical video clip, the segment can be found in the database by quickly search ing for the relevant signature. The method is robust against noise and typi cal variations in the video stream, even global changes in brightness that can fool histogram-based techniques. In the paper, we compare experimentall y our shot transition mechanism to a color histogram implementation. and al so evaluate the effectiveness of our database-searching scheme. Our algorit hms are very efficient and run in realtime on a desktop computer. We descri be how this technology could be employed to construct a "smart VCR" that wa s capable of alerting the viewer to the beginning of a specific program or identifying commercials and then muting the volume on the TV.