Automatic chaptering of VoD content based on DVD content

In this paper we propose a framework for automatically chaptering VoD content based on its DVD version. The idea is to benefit from artistic work performed for DVD chapter creation even if DVD and VoD video content are not exactly the same. The framework is based on a sparse to dense frame synchronization, combining both global and local image descriptions, together with adaptive video sequence splitting to enable the processing of very long sequences. A way to extract specific information from a DVD is also embedded in the framework. Results of the evaluation performed on official movie releases are presented in the paper.