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

dvmmPub35

Di Zhong, Shih-Fu Chang. Structure Parsing and Event Detection for Sports Video. ADVENT Technical Report #091 Columbia University, December 2000.

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.

Abstract

For video indexing, typically videos are first processed to obtain constituent objects and features. These extracted entities provide an intermediate content model to effectively describe videos. In earlier chapters, we have studied temporal segmentation that generates elementary video shots, and spatial-temporal segmentation that extracts video regions and objects. We also developed feature matching algorithms and query methods to support visual similarity search. These works provide very useful tools for accessing online digital videos. However, the objects and features we have extracted so far contain little information at the semantic level. To solve this problem, we can explore the knowledge and constraints in specific domain and apply domain-specific rules and/or unsupervised machine learning techniques. In this chapter, we present an event detection and structure parsing system for sports videos. This system is built on top of segmentation and search techniques we have presented in prior chapters. We also demonstrate a summarization and browsing interface that allows users to easily access content structure and event index of video data

Contact

Di Zhong
Shih-Fu Chang

BibTex Reference

@TechReport{dvmmPub35,
   Author = {Zhong, Di and Chang, Shih-Fu},
   Title = {Structure Parsing and Event Detection for Sports Video},
   Institution = {Columbia University},
   Month = {December},
   Year = {2000}
}

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).