Retrieval of Sports Video Clips Using Audio - Visual Features and Text Information *

Video clip retrieval plays a critical role in the content-based sports video retrieval. This paper proposes a content-based retrieval strategy of sports video clip in which visual and auditory features and text information are extracted to locate similar video clips. Because in sports game play scenes are concerned and interested for most audiences, a long sport video is first automatically segmented into play segments and time-out segments based on audio feature in compressed domain. And then we obtain similar video clips based on sliding shot window algorithm and equivalence relation theory. Finally similar video clips are ranked by visual factor and order factor in terms of longest common sequence (LCS). The experimental results showed that the proposed method could effectively and efficiently retrieve similar video clips corresponding with a query clip in a sports video of TV program.