Representing contents of single video shot using Rframes.

摘要

A computer implemented method for providing a representative frame (Rframe) for a group of frames in a video sequence comprises selecting a reference frame from the group of frames; storing the reference frame in a computer memory, defining a peripheral motion tracking region along an edge of the reference frame, and successively tracking movement of boundary pixels in the tracking region, symbolizing any of the length of the shot and the presence of any caption. <IMAGE> <IMAGE>