Detecting Video Shot Boundaries up to 16 Times Faster

摘要

Shot boundary detection (SBD) is the first fundamental step to managing video databases. Existing automatic SBD techniques, however, are based on sequentail search, and threr-fore too expensive for practical use. To address this problem, we investigate a non-linear approach in which most video frames do not need to be compared. It can improve their performance substantially. Our experiments show that this idea speeds up a conventional method based on color histograms up to 16 times (five times on average) while preserving the same accuracy.