A Multi-Stage Approach for News Video Segmentation Based on Automatic Anchorperson Number Detection

Author

D´Anna, Leandro ; Percannella, Gennaro ; Sansone, Filip ; Vento, Mario

Author_Institution

Univ. di Salerno, Salerno

fYear

2007

fDate

4-9 Nov. 2007

Firstpage

229

Lastpage

234

Abstract

In this paper we present an algorithm for anchor shot detection that is a fundamental step for segmenting news video into stories. This is among key issues for achieving efficient treatment of news-based digital libraries. The proposed algorithm creates a set of audio/video templates of anchorperson shots in an unsupervised way, then classifies shots by comparing them to all the templates when there is one anchor and to a single best template when there are two anchors. In this paper we also propose an automatic selector, based only on the audio track, that is able to classify a news video as presented by one or two anchorpersons. The method has been tested on a wide database demonstrating its effectiveness.

Keywords

image segmentation; object detection; video signal processing; audio-video templates; automatic anchorperson number detection; automatic selector; multistage approach; news-based digital libraries; video segmentation; Databases; Gunshot detection systems; Joining processes; Mobile computing; Software libraries; Switches; Testing; Ubiquitous computing; Variable speed drives; Videoconference;

fLanguage

English

Publisher

ieee

Conference_Titel

Mobile Ubiquitous Computing, Systems, Services and Technologies, 2007. UBICOMM '07. International Conference on

Conference_Location

Papeete

Print_ISBN

978-0-7695-2993-6

Type

conf

DOI

10.1109/UBICOMM.2007.35

Filename

4402832