Improving the Speed of Virtual Rear Projection: A GPU-Centric Architecture
GVU Center and College of Computing, Georgia Institute of Technology, Atlanta, GA 30332
IEEE Computer Society Conference on Computer Vision and Pattern Recognition – Workshops, 2005. CVPR Workshops.
@inproceedings{flagg2005improving,
title={Improving the speed of virtual rear projection: A GPU-centric architecture},
author={Flagg, M. and Summet, J. and Rehg, J.M.},
booktitle={Computer Vision and Pattern Recognition-Workshops, 2005. CVPR Workshops. IEEE Computer Society Conference on},
pages={105–105},
organization={IEEE},
year={2005}
}
Projection is the only viable way to produce very large displays. Rear projection of large-scale upright displays is often preferred over front projection because of the lack of shadows that occlude the projected image. However, rear projection is not always a feasible option for space and cost reasons. Recent research suggests that many of the desirable features of rear projection, in particular lack of shadows, can be reproduced using active virtual rear projection (VRP). We present a new approach to shadow detection that addresses limitations with previous work. Furthermore, we demonstrate how to exploit the image processing capabilities of a GPU to shift the main performance bottleneck from image processing to camera capture and projector display rates. The improvements presented in this paper enable a speed increase in image processing from 15Hz to 110Hz in our new active VRP prototype.
May 22, 2011 by hgpu
