Abstract
We propose a framework for event detection and summary generation in football broadcast video. First, we formulate summarization as a play detection problem, with play being defined as the most basic segment of time during which the ball is being played. Then we propose both deterministic and probabilistic approaches to the detection of the plays. The detected plays are concatenated to generate a compact, time-compressed summary of the original video. Such a summary is complete in the sense that it contains every meaningful action of the underlying game, and it also servers as a much better starting point for higher-level summarization and other analyses than the original video does. Based on the summary, we also propose an audio-based hierarchical summarization method. Experimental results show the proposed methods work very well on consumer grade platforms.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of SPIE - The International Society for Optical Engineering |
Editors | M.M. Yeung, C.S. Li, R.W. Lienhart |
Pages | 202-213 |
Number of pages | 12 |
Volume | 4676 |
DOIs | |
State | Published - 2002 |
Externally published | Yes |
Event | Storage and Retrieval for Media Databases 2002 - San Jose, CA, United States Duration: Jan 23 2002 → Jan 25 2002 |
Other
Other | Storage and Retrieval for Media Databases 2002 |
---|---|
Country/Territory | United States |
City | San Jose, CA |
Period | 1/23/02 → 1/25/02 |
Keywords
- Event detection
- Video summarization
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Condensed Matter Physics