Video Shot Boundary Detection Using Gist

Shot-boundary detection is the first step towards scene extraction in videos, which is useful for video content analysis and indexing. In this work, we apply gist and color features to represent the individual frames. Gist [15, 21] has been shown to characterize the structure of images well while being resistant to luminance change and also small translation. Thus, it is ideally suited for our application. We formalize the shot boundary detection task as a multidimensional outlier detection problem. We present a quantitative evaluation on TRECVID 2002 videos and show that the proposed approach compares favorably with existing approaches. We also discuss the choice of design parameters.