Title :
A contrario shot detection
Author :
Hellier, P. ; Demoulin, V. ; Oisel, Lionel ; Perez, Pablo
Author_Institution :
Technicolor, Rennes, France
fDate :
Sept. 30 2012-Oct. 3 2012
Abstract :
This paper presents a novel technique for video shot detection, including hard cuts and gradual transitions. The method builds on various similarity criteria, namely histogram difference, motion estimation and distribution of intensity difference. While these metrics are well known, the novelty of the paper resides in the probabilistic framework to assess the similarity between two images. The a contrario framework, introduced in [1, 2] enables to control explicitly the number of false alarms given a background noise model. Experiments have been conducted on the Trecvid 2007 database: for all transitions (cuts and gradual), a recall of 0.95 and a precision of 0.96 was obtained.
Keywords :
motion estimation; probability; video signal processing; Trecvid 2007 database; contrario shot detection; gradual transition; hard cut; histogram difference; intensity difference distribution; motion estimation; probabilistic framework; similarity criteria; video shot detection; Computational modeling; Databases; Feature extraction; Histograms; Image color analysis; Measurement; Robustness; Shot detection; a contrario; motion estimation; video processing;
Conference_Titel :
Image Processing (ICIP), 2012 19th IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4673-2534-9
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2012.6467552