Model-based video scene clustering with noise analysis

In content-based video analysis, scene clustering is an important step toward automated understanding of video semantics, identification of video events, and indexing and retrieval of relevant video contents. Many methods have been proposed to cluster video shots into scenes by using conventional k-means clustering and hierarchical clustering methods. However, "noise" shots analysis has not been fully investigated and incorporated in the clustering procedure. In this paper, we propose a Gaussian mixture model based clustering method incorporating noise analysis. The proposed method can identify noise shots and predict the scene types of new coming shots with satisfactory results.