LELBanner980

Effective Replays and Summarization of Virtual Experiences

Kevin Ponto, Member, IEEE,
Joe Kohlmann and
Michael Gleicher, Member, IEEE

Living Environments Laboratory,
University of Wisconsin–Madison

Viewpoints in camera paths. The green path, shown on the left, corresponds to the original motion of 1,400 viewpoints. The pink path in the middle demonstrates that the filtered path, while smooth, does not show all of the items seen in the original path. The extracted path, shown in blue on the right, comprises five viewpoints that demonstrate the views seen in the original path.

Video

Paper Download

Researchers and students may download a copy of this publication.

ponto-ieee-vr-2012-virtual-experiences.pdf

Citation

@ARTICLE{6165142,
author={Ponto, Kevin and Kohlmann, Joe and Gleicher, Michael},
journal={Visualization and Computer Graphics, IEEE Transactions on}, title={Effective Replays and Summarization of Virtual Experiences},
year={2012},
month={april },
volume={18},
number={4},
pages={607 -616},
keywords={},
doi={10.1109/TVCG.2012.41},
ISSN={1077-2626},}

Abstract

Direct replays of the experience of a user in a virtual environment are difficult for others to watch due to unnatural camera motions. We present methods for replaying and summarizing these egocentric experiences that effectively communicate the user’s observations while reducing unwanted camera movements. Our approach summarizes the viewpoint path as a concise sequence of viewpoints that cover the same parts of the scene. The core of our approach is a novel content dependent metric that can be used to identify similarities between viewpoints. This enables viewpoints to be grouped by similar contextual view information and provides a means to generate novel viewpoints that can encapsulate a series of views. These resulting encapsulated viewpoints are used to synthesize new camera paths that convey the content of the original viewers experience. Projecting the initial movement of the user back on the scene can be used to convey the details of their observations, and the extracted viewpoints can serve as bookmarks for control or analysis. Finally we present performance analysis along with two forms of validation to test whether the extracted viewpoints are representative of the viewer’s original observations and to test for the overall effectiveness of the presented replay methods.

 

You can find sample videos of the early development of this project here.