Segmentation TV series into scenes using speaker diarization
Hervé Bredin, Philippe Ercolessi, Christine Sénac, Philippe Joly · Research Repository (Delft University of Technology) · 2011
In this paper, we propose a novel approach to perform scene segmentation of TV series. Using the output of our existing speaker diarization system, any temporal segment of the video can be described as a binary feature vector. A straightforward segmentation algorithm then allows to group similar contiguous speaker segments into scenes. An additional visual-only color-based segmentation is then used to refine the first segmentation. Experiments are performed on a subset of the Ally McBeal TV series and show promising results, obtained with a rule-free and genericmethod. For comparison purposes, test corpus annotations and description are made available to the community.