Paper Info
Title
Weighted Block Matching-Based Anchor Shot Detection with Dynamic Background
Abstract
Anchor shot detection is fundamental to the structure analysis of news program, such as story segmentation and commercial block location. Previous work mainly tackled the problem of picture in frame on half screen, while there are also some news programs which have a global dynamic studio background. In this paper, a new block weighing based anchor shot detection algorithm is proposed. Firstly, the key frame of each shot is extracted and divided into 64 blocks equally. Then a weighted template is built automatically after clustering analysis of different types of shots, which indicates the degrees of variation on the different blocks in the anchor shot background. And lastly, all anchor shots are detected by a weighted template matching scheme. The detection results have shown that our method is effective, especially suitable for the news program which has a global dynamic background.
Year
DOI
Venue
2009
10.1007/978-3-642-02611-9_22
ICIAR
Keywords
Field
DocType
weighted block matching-based anchor,news program,global dynamic studio background,detection result,anchor shot background,weighted template,clustering analysis,anchor shot,shot detection,global dynamic background,detection algorithm,dynamic background,anchor shot detection,cluster analysis,template matching,structure analysis,clustering
Structure analysis,Template matching,Computer vision,Pattern recognition,Computer science,Segmentation,Artificial intelligence,Key frame,Cluster analysis
Conference
Volume
ISSN
Citations 
5627
0302-9743
3
PageRank 
References 
Authors
0.40
7
4
Name
Order
Citations
PageRank
Fuguang Zheng1120.94
Shijin Li2925.38
Hao Li32511.35
Jun Feng45116.68