GPU implementation of belief propagation using CUDA for cloud tracking and reconstruction
Department of Computer and Information Sciences, University of Delaware, Newark, DE 19716
IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008), 2008, p. 1-4
@conference{grauer2008gpu,
title={GPU implementation of belief propagation using CUDA for cloud tracking and reconstruction},
author={Grauer-Gray, S. and Kambhamettu, C. and Palaniappan, K.},
booktitle={Pattern Recognition in Remote Sensing (PRRS 2008), 2008 IAPR Workshop on},
pages={1–4},
organization={IEEE}
}
This paper describes an efficient CUDA-based GPU implementation of the belief propagation algorithm that can be used to speed up stereo image processing and motion tracking calculations without loss of accuracy. Preliminary results in using belief propagation to analyze satellite images of hurricane Luis for real-time cloud structure and tracking are promising with speed-ups of nearly a factor of five.
March 22, 2011 by hgpu
