Title
Integrating Multiple Levels Of Zoom To Enable Activity Analysis
Keywords
Action recognition; Activity analysis; Multi zoom; Multiple cameras; Multiple zoom
Abstract
In this paper, we present a multi-zoom framework for activity analysis in situations requiring combinations of both detailed and coarse views of the scene. The epipolar geometry is employed in several novel ways in the context of activity analysis. Detecting and tracking objects in time and consistently labeling these objects across zoom levels are two necessary tasks for such activity analysis. First, a multiview approach to automatically detect and track heads and hands in a scene is described. Then, by making use of epipolar, spatial, trajectory, and appearance constraints, objects are labeled consistently across cameras (zooms). Finally, we demonstrate how multiple levels of zoom can cooperate and complement each other to help solve problems related to activity analysis. © 2006 Elsevier Inc. All rights reserved.
Publication Date
7-1-2006
Publication Title
Computer Vision and Image Understanding
Volume
103
Issue
1
Number of Pages
33-51
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/j.cviu.2006.02.006
Copyright Status
Unknown
Socpus ID
33646808082 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/33646808082
STARS Citation
Smith, Paul; Shah, Mubarak; and da Vitoria Lobo, Niels, "Integrating Multiple Levels Of Zoom To Enable Activity Analysis" (2006). Scopus Export 2000s. 8309.
https://stars.library.ucf.edu/scopus2000/8309