Unsupervised and model-free news video segmentation

Author

Gao, Xinbo ; Tang, Xiaoou

Author_Institution

Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China

fYear

2001

fDate

2001

Firstpage

58

Lastpage

64

Abstract

Based on a simple temporal structural model of a news program, the paper presents a practical solution to automatic news story segmentation by integrating syntactic and semantic methods. First, a syntactic segmentation method is used to detect the shot boundaries in order to partition video frames into video shots. Then, a semantic segmentation method based on graph-theoretical cluster analysis is developed to classify the video shots into anchorperson shots and news footage shots. Finally, a structural model of news video is used to complete the news-story segmentation. The proposed method obtains a precision of 90.45% and a recall of 95.83% in the segmentation experiment of 168 news stories from two Hong Kong news stations

Keywords

computational linguistics; content-based retrieval; edge detection; graph theory; image retrieval; image segmentation; video signal processing; Hong Kong news stations; anchorperson shots; automatic news story segmentation; graph-theoretical cluster analysis; model-free news video segmentation; news footage shots; news program; news-story segmentation; semantic segmentation method; shot boundary detection; simple temporal structural model; structural model; syntactic segmentation method; unsupervised news video segmentation; video frame partitioning; video shots; Cameras; Content based retrieval; Gunshot detection systems; Image retrieval; Image segmentation; Indexing; Proposals; TV; Testing; Video sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Content-Based Access of Image and Video Libraries, 2001. (CBAIVL 2001). IEEE Workshop on

Conference_Location

Kauai, HI

Print_ISBN

0-7695-1354-9

Type

conf

DOI

10.1109/IVL.2001.990857

Filename

990857