We describe a "constant pace" framework for video summarization via fast playback or temporal subsampling. The pace of the summary serves as a parameter that enables production of a video summary of any desired length. Earlier, we showed that the intensity of motion activity (or pace) of a video sequence is a good indication of its "summarizability." Here we build on this notion by adapting the playback frame-rate or the temporal subsampling rate to the pace. Either the less active parts of the sequence are played back at a faster frame rate or the less active parts of the sequence are sub-sampled more heavily than are the more active parts, so as to produce a summary with constant pace. The basic idea is to skip over the less interesting parts of the video. Our technique is computationally simple and gives satisfactory results with surveillance and entertainment video.
Ajay Divakaran, Kadir A. Peker, Huifang Sun