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 properly representing video events is challenging. We propose a novel approach to analyze temporal aspects of video data. We consider video data as a sequence of images that form a 3-dimensional spatiotemporal structure, and perform multiview orthographic projection to transform the video data into 2-dimensional representations. The projected views allow a unique way to rep- resent video events and capture the temporal aspect of video data. We extract local salient points from 2D projection views and perform detection-via-similarity approach on a wide range of events against real-world surveillance data. We demonstrate our example-based detection framework is competitive and robust. We also investigate the synthetic example driven retrieval as a basis for query-by-example.
Dissertation
Video event detection framework on large-scale video data
University of Iowa
Doctor of Philosophy (PhD), University of Iowa
Autumn 2011
DOI: 10.17077/etd.ypfqd78c
Free to read and download, Open Access
Abstract
Details
- Title: Subtitle
- Video event detection framework on large-scale video data
- Creators
- Dong-Jun Park - University of Iowa
- Contributors
- David Eichmann (Advisor)Joseph Kearney (Committee Member)William Street (Committee Member)Juan Pablo Hourcade (Committee Member)Michael Mackey (Committee Member)
- Resource Type
- Dissertation
- Degree Awarded
- Doctor of Philosophy (PhD), University of Iowa
- Degree in
- Computer Science
- Date degree season
- Autumn 2011
- Publisher
- University of Iowa
- DOI
- 10.17077/etd.ypfqd78c
- Number of pages
- ix, 115 pages
- Copyright
- Copyright 2011 Dong-Jun Park
- Language
- English
- Description bibliographic
- Includes bibliographical references (pages 103-115).
- Academic Unit
- Computer Science
- Record Identifier
- 9983777281302771
Metrics
1808 File views/ downloads
377 Record Views