Title :
Golf video browsing system using three stage audio segmentation
Author :
Jun-Young Lee ; Hyoung-Gook Kim
Author_Institution :
Dept. of Electron. Convergence Eng., Kwangwoon Univ., Seoul, South Korea
Abstract :
In this paper, we propose a golf video browsing system using three stage audio segmentation. To increase the accuracy of audio segment boundaries for golf video browsing on digital video recorder, the proposed three-stage audio segmentation algorithm consists of Gaussian Mixture Model (GMM)-based classification, GMM-Linear Discriminant Analysis (LDA)-based classification, and occupation ratio-based segmentation. The detected audio segment is synchronized with the video frame for the extraction of thumbnails for use in the intelligent browsing of golf videos.
Keywords :
Gaussian processes; audio signal processing; feature extraction; mixture models; online front-ends; pattern classification; signal detection; video recording; GMM LDA classification; GMM linear discriminant analysis; Gaussian mixture model; audio segment detection; digital video recorder; golf video intelligent browsing system; occupation ratio segmentation; three-stage audio segmentation algorithm; thumbnail extraction; video frame; Filtering algorithms; Noise; Speech; TV; Audio Segmentation; Browsing; Gaussian Mixture Model; Linear Discriminant Analisys;
Conference_Titel :
Information and Communication Technologies (WICT), 2013 Third World Congress on
Conference_Location :
Hanoi
DOI :
10.1109/WICT.2013.7113118