Video classification and segmentation are fundamental steps for efficient accessing, retrieval and browsing of large amounts of video data. We have developed a scene classification scheme using a hidden Markov model (HMM) based classifier. By utilizing the temporal behaviors of different scene classes, the HMM classifier can effectively classify video segments into one of the pre-defined scene classes. In this paper, we describe two approaches for joint video classification and segmentation based on a HMM, which works by searching for the most likely class transition path utilizing the dynamic programming technique.
展开▼