Share Email Print

Journal of Electronic Imaging

Multi-level video content represntation and retrieval
Author(s): Jianping Fan; Walid G. Aref; Ahmed K. Elmagarmid; Mohand-Said Hacid; Mirette S. Marzouk; Xingquan Zhu
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

In this article, several practical algorithms are proposed to support content-based video analysis, modeling, representation, summarization, indexing, and access. First, a multilevel video database model is given. One advantage of this model is that it provides a reasonable approach to bridging the gap between low-level representative features and high-level semantic concepts from a human point of view. Second, several model-based video analysis techniques are proposed. In order to detect the video shots, we present a novel technique, which can adapt the threshold for scene cut detection to the activities of variant videos or even different video shots. A seeded region aggregation and temporal tracking technique is proposed for generating the semantic video objects. The semantic video scenes can then be generated from these extracted video access units (e.g., shots and objects) according to some domain knowledge. Third, in order to categorize video contents into a set of semantic clusters, an integrated video classification technique is developed to support more efficient multilevel video representation, summarization, indexing, and access techniques.

Paper Details

Date Published: 1 October 2001
PDF: 14 pages
J. Electron. Imaging. 10(4) doi: 10.1117/1.1406944
Published in: Journal of Electronic Imaging Volume 10, Issue 4
Show Author Affiliations
Jianping Fan, Univ. of North Carolina/Charlotte (United States)
Walid G. Aref, Panasonic Technologies Inc. (United States)
Ahmed K. Elmagarmid, Purdue Univ. (United States)
Mohand-Said Hacid, Purdue Univ. (United States)
Mirette S. Marzouk, Purdue University (United States)
Xingquan Zhu, Purdue Univ. (United States)

© SPIE. Terms of Use
Back to Top