GROUPING VIDEO SHOTS INTO SCENES BASED ON 1D MOSAIC DESCRIPTORS (MP-L2)

Author(s) : Henri Nicolas (INRIA, France) Anne Manoury (INRIA, France) Jenny Benois-Pineau (Labri, University of Bordeaux, France) William Dupuis (IRCCyn, France) Dominique Barba (IRCCyn, France)

Abstract : This paper describes an original approach for structuring of video documents into scenes by grouping video shots. The method is based on the construction of 1-D mosaics. 1-D mosaics are built based on X-ray projections of color video frames representing integration along vertical and horizontal axes. The mosaicing is realized by motion compensation in 1D domain. Grouping of shots in a scene is done by local and global matching of mosaics based on piecewise linear approximation and hierarchical clustering. The results obtained on feature documentaries are promising.

Menu