Bucarest University POLITEHNICA publication.
U.P.B Sci. Bull., Series D, Vol. 65, No. 1, 2003
In this paper an improved method for detecting scenes in animation movies is proposed. The movies are considered to be already divided into the fundamental video units or shots. A scene is defined as an ensemble of similar neighbor shots which have the properties of unity of space, place, time and action. The proposed approach uses mean color histograms in order to measure the similarities between shots. Two kinds of histograms are proposed and compared: normal histograms and weighted histograms. Various applications of the scene detection are discussed: feedback for cut detection algorithms, detection of the “shot-reverse-shot” camera technique, multi-scale hierarchical representation of the animation movie content. Experimental results are presented.
Ionescu B., Buzuloiu V., Lambert P., Coquin D., IMPROVED CUT DETECTION FOR THE SEGMENTATION OF ANIMATION MOVIES, accepted for IEEE ICASSP'06, Toulouse 2006.
Abstract : In this paper an improved cut detection algorithm, adapted to the segmentation of animation movies, is proposed. As color is a major feature of animation movies (each movie has its own particular color distribution) the proposed algorithm applies second order derivatives on Euclidean distances between color histograms of frames quadrants in order to improve the cut detection. For the frame classification, an automatic threshold estimation is proposed. Also, in order to reduce false detections, we propose an algorithm to detect an effect specific to animation movies, named ”short color change” (i.e. thunders, lightening).
The resulting method achieved better results compared to the classical histogram based and motiondiscontinuity based approaches, as shown by tests conducted on several animation movies.
Ionescu B., Lambert P., Coquin D., Buzuloiu V., Influence of colors reduction upon scene direction changes in animated movies, 20th colloque GRETSI, CD-ROM , Louvain-la-Neuve, Belgium, september 2005.