Conference proceeding
Video Event Detection as Matching of Spatiotemporal Projection
Advances in Visual Computing, pp.139-150
Lecture Notes in Computer Science, 6455
2010
DOI: 10.1007/978-3-642-17277-9_15
Abstract
Detection of events and actions in video entails substantial processing of very large, even open-ended, video streams. Video data presents a unique challenge for the information retrieval community because it is hard to find a way to properly represent video events. We propose a novel approach to analyze temporal aspects of video data. We consider the video data as a sequence of images that form a 3-dimensional spatiotemporal structure, and multiview orthographic projection is performed to transform the video data into 2-dimensional representations. The projected views allow a unique way to represent video events, and we apply template matching using color moments to detect video events.
Details
- Title: Subtitle
- Video Event Detection as Matching of Spatiotemporal Projection
- Creators
- Dong-Jun Park - Institute for Clinical and Translational Sciences, The University of Iowa, Iowa City, USADavid Eichmann - Institute for Clinical and Translational Sciences, The University of Iowa, Iowa City, USA
- Resource Type
- Conference proceeding
- Publication Details
- Advances in Visual Computing, pp.139-150
- Publisher
- Springer Berlin Heidelberg; Berlin, Heidelberg
- Series
- Lecture Notes in Computer Science; 6455
- DOI
- 10.1007/978-3-642-17277-9_15
- eISSN
- 1611-3349
- ISSN
- 0302-9743
- Language
- English
- Date published
- 2010
- Academic Unit
- Library and Information Science
- Record Identifier
- 9984003175602771
Metrics
13 Record Views