Video shot meta-segmentation based on multiple criteria for gradual transition detection

Shot boundaries provide the basis for almost all high-level video content analysis approaches, validating it as one of the major prerequisites for efficient video indexing and retrieval in large video databases. The successful detection of both gradual and abrupt transitions is necessary to this end. In this paper a new gradual transition detection algorithm is proposed, based on novel features exhibiting less sensitivity to local or global motion than previously proposed ones. These features, each of which could serve as a stand-alone transition detection approach, are then combined using a machine learning technique, to result in a meta-segmentation scheme. Besides significantly improved performance, advantage of the proposed scheme is that there is no need for threshold selection, as opposed to what would be the case if any of the proposed features were used by themselves and as is typically the case in the relevant literature. Comparison of the proposed approach with four popular algorithms of the literature reveals the significantly improved performance of it.