TV broadcast macro-segmentation
Sid-Ahmed Berrani, Patrick Lechat, Gaël Manson · 2007
In this paper, we study different approaches for TV broadcast macro-segmentation. This is needed in many novel services such as TV-on-Demand. TV broadcast macro-segmentation can be performed using either the metadata associated with the stream or by directly analyzing the audiovisual stream. This paper presents both approaches and analyzes their advantages and limitations with respect to applications. It then presents an experimental study. This study has been conducted on real data of more than 5 months of broadcasting. Two types of metadata have been considered and a video identification technique has been developed. The obtained results show in particular, the effectiveness of content-based solution and also highlight imprecision and limitations of metadata. They show in particular that over a 24 hour broadcast, more than 40% of the programs start more than 5 minutes earlier or later than that expected in the metadata.