Local subspace-based denoising for shot boundary detection

Shot boundary detection (SBD) has long been an important problem in content based video analyzing. In existing works, researchers proposed kinds of methods to analyze the continuity of video sequence for SBD. However, the conventional methods focus on analyzing adjacent frame continuity information in some common feature space. The feature space for content representing and continuity computing is seldom specialized for different parts of video content. In this paper, we demonstrate the shortage of using common feature space, and propose a denoising method that can effectively restrain the in-shot change for SBD. A local subspace specialized for every period of video content is used to develop the denoising method. The experiment results show the proposed method can remove the noise effectively and promote the performance of SBD.