Summarizing video datasets in the spatiotemporal domain
- 8 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15294188,p. 906-912
- https://doi.org/10.1109/dexa.2000.875134
Abstract
We address the problem of analyzing and managing complex dynamic scenes captured in video. We present an approach to summarize video datasets by analyzing the trajectories of objects within them. Our work is based on the identification of nodes in these trajectories as critical points that describe the behavior of an object over a video segment. The time instances that correspond to these nodes are used to select critical frames for a video summary that describes adequately and concisely an object's behavior within a video segment. The analysis of relative positions of objects of interest within the video feed may dictate the selection of additional critical frames, to ensure the separability of converging trajectories. The paper presents a framework for video summarization using this approach, and addresses the use of self-organizing maps to identify trajectory nodes.Keywords
This publication has 8 references indexed in Scilit:
- Generating semantics-based trajectories of moving objectsComputers, Environment and Urban Systems, 2003
- 3D trajectory recovery for tracking multiple objects and trajectory guided recognition of actionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A spatiotemporal motion model for video summarizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Event detection and analysis from video streamsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Data resource selection in distributed visual information systemsIEEE Transactions on Knowledge and Data Engineering, 1998
- Video visualization for compact presentation and fast browsing of pictorial contentIEEE Transactions on Circuits and Systems for Video Technology, 1997
- Self-Organizing MapsPublished by Springer Nature ,1997
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982