文章基本信息

标题：Extracting Objects and Events from MPEG Videos for Highlight-based Indexing and Retrieval
本地全文：下载
作者：Ren, Jinchang ; Jiang, Jianmin ; Chen, Juan 等
期刊名称：Journal of Multimedia
印刷版ISSN：1796-2048
出版年度：2010
卷号：5
期号：2
页码：95-103
DOI：10.4304/jmm.5.2.95-103
语种：English
出版社：Academy Publisher
摘要：Automatic recognition of highlights from videos is a fundamental and challenging problem for content-based indexing and retrieval applications. In this paper, we propose techniques to solve this problem using knowledge supported extraction of semantics, and compressed-domain processing is employed for efficiency. Firstly, knowledgebased rules are utilized for shot detection on extracted DCimages, and statistical skin detection is applied for human object detection. Secondly, through filtering outliers in motion vectors, improved detection of camera motions like zooming, panning and tilting are achieved. Video highlight high-level semantics are then automatically extracted via low-level analysis in the detection of human objects and camera motion events, and finally these highlights are taken for shot-level annotation, indexing and retrieval. Results using a large test video data set have demonstrated the accuracy and robustness of the proposed techniques.
关键词：content-based retrieval; video highlights extraction; video semantics; compressed-domain processing