Joint video scene segmentation and classification based on hidden Markov model

Video classification and segmentation are fundamental steps for efficient accessing, retrieving and browsing large amount 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, HMM classifier can effectively classify video segments into one of the predefined scene classes. In this paper, we describe two approaches for joint video classification and segmentation based on HMM, which works by searching for the most likely class transition path utilizing the dynamic programming technique.