Stereo depth with a Unified Architecture GPU
Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, FL
2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2008) Publisher: Ieee, Pages: 1-6
@conference{gibson2008stereo,
title={Stereo depth with a unified architecture GPU},
author={Gibson, J. and Marques, O.},
booktitle={Computer Vision and Pattern Recognition Workshops, 2008. CVPRW’08. IEEE Computer Society Conference on},
pages={1–6},
year={2008},
organization={IEEE}
}
This paper describes how the calculation of depth from stereo images was accelerated using a GPU. The Compute Unified Device Architecture (CUDA) from NVIDIA was employed in novel ways to compute depth using BT cost matching and the semi-global matching algorithm. The challenges of mapping a sequential algorithm to a massively parallel thread environment and performance optimization techniques are considered.
March 11, 2011 by hgpu
