Jump to : Download | Note | Abstract | Contact | BibTex reference | EndNote reference |

dvmmPub98

Di Zhong. Segmentation, Index and Summarization of Digital Video Content. PhD Thesis Graduate School of Arts and Sciences, Columbia University, 2001.

Download [help]

Download paper: Adobe portable document (pdf)

Copyright notice:This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Note on this paper

Advisor: Prof. Chang

Abstract

In this thesis, we propose and develop unique frameworks and methods for temporal and spatial video segmentation as well as object based video representation, indexing and retrieval at both the syntactic and the semantic level. In this thesis, we propose and develop unique frameworks and methods for temporal and spatial video segmentation as well as object based video representation, indexing and retrieval at both the syntactic and the semantic level. Then we present an automatic region segmentation system for content-based video search. The system segments and tracks consistent regions through each video shot, and then computes visual features of extracted regions to build visual libraries that support region level search. A web-based video query system that has more than 3,000 video shots has been built. The query system allows users to do spatial-temporal search of video shots by drawing regions and specifying features. It is the first video search engine that supports automatic extraction and object-level motion-based search. Semantic object segmentation and tracking is then studied to produce high-level object representation and description. We introduce an integrated scheme for semantic object segmentation and content-based object search. AMOS, a unique video object segmentation system that combines low-level automatic region segmentation with user inputs is developed. An object query model is developed to effectively combine local region-level features and spatial-temporal structures. This system is very useful for MPEG-4 and MPEG-7 applications. At the end we present a real-time framework to build semantic-level structure and event index of live sports videos. It utilized the segmentation and searching methods we have developed to detect specific scenes and events. Also it integrates knowledge about domain-specific video structures and generic machine learning algorithms. We show applications of such techniques in high-level video retrieval and browsing systems in specific domains such as sports videos. In addition, we demonstrate a summarization scheme that provides users intuitive structures of video content and statistics of game events and views

Contact

Di Zhong

BibTex Reference

@PhdThesis{dvmmPub98,
   Author = {Zhong, Di},
   Title = {Segmentation, Index and Summarization of Digital Video Content},
   School = {Graduate School of Arts and Sciences, Columbia University},
   Year = {2001}
}

EndNote Reference [help]

Get EndNote Reference (.ref)

 
bar

For problems or questions regarding this web site contact The Web Master.

This document was translated automatically from BibTEX by bib2html (Copyright 2003 © Eric Marchand, INRIA, Vista Project).