Color Video Segmentation by Dissimilarity Based on Edges

被引:0
作者
Ramos, Lucia [1 ]
Novo, Jorge [1 ]
Rouco, Jose [1 ]
Mosquera, Antonio [2 ]
Penedo, Manuel G. [1 ]
机构
[1] Univ A Coruna, VARPA Grp, Dept Comp Sci, La Coruna, Spain
[2] Univ Santiago de Compostela, Dept Elect & Comp Sci, Artificial Vision Grp, Santiago De Compostela, Spain
来源
HYBRID ARTIFICIAL INTELLIGENCE SYSTEMS, PT 2 | 2010年 / 6077卷
关键词
Video segmentation; detection of changes of scene; cuts; fades; dissolves;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work new approaches are proposed to the extension to color-space of different shot change detection methods. These techniques are those ones that use the dissimilarity based on edges, in particular on space and frequency domains. They were previously defined to deal with grayscale videos, so the methods are redesigned to provide the best possible results in color-space videos. Moreover, some improvements are performed to obtain better results, as the use of an adaptative threshold instead of the fixed one previously used. Some experiments are presented to show the better behaviour of the new developed approaches.
引用
收藏
页码:264 / +
页数:2
相关论文
共 9 条
[1]  
[Anonymous], TREC VIDEO RETRIEVAL
[2]   Robust 3D clue-based video segmentation for video indexing [J].
Ardebilian, M ;
Chen, L ;
Tu, X .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2000, 11 (01) :58-79
[4]  
Kasturi R., 1996, INT WORKSH IM DAT MU, V9
[5]  
Kobla V., 1999, SPIE C STORAGE RETRI
[6]  
Nagasaka A., 1991, VIS DAT SYST IFIP WO, P113
[7]  
Porter S.V., 2000, DETECTION CLASSIFICA
[8]  
Theo G., 1999, PATTERN RECOGN, V32, P453
[9]   A feature-based algorithm for detecting and classifying production effects [J].
Zabih, R ;
Miller, J ;
Mai, K .
MULTIMEDIA SYSTEMS, 1999, 7 (02) :119-128