A probabilistic framework for spatio-temporal video representation and indexing

Hayit Greenspan, J. Goldberger, Arnaldo Mayer

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


In this work we describe a novel statistical video representation and modeling scheme. Video representation schemes are needed to enable segmenting a video stream into meaningful video-objects, useful for later indexing and retrieval applications. In the proposed methodology, unsupervised clustering via Guassian mixture modeling extracts coherent space-time regions in feature space, and corresponding coherent segments (video-regions) in the video content. A key feature of the system is the analysis of video input as a single entity as opposed to a sequence of separate frames. Space and time are treated uniformly. The extracted space-time regions allow for the detection and recognition of video events. Results of segmenting video content into static vs. dynamic video regions and video content editing are presented.
Original languageAmerican English
Title of host publicationEuropean Conference on Computer Vision
EditorsAnders Heyden, Gunnar Sparr, Mads Nielsen, Peter Johansen
PublisherSpringer Berlin Heidelberg
StatePublished - 2002

Bibliographical note

Place of conference:Denmark


Dive into the research topics of 'A probabilistic framework for spatio-temporal video representation and indexing'. Together they form a unique fingerprint.

Cite this