GPU OPTIMIZER: A 3D RECONSTRUCTION ON THE GPU USING MONTE CARLO SIMULATIONS - How to Get Real Time without Sacrificing Precision

Jairo R. Sánchez, Hugo Álvarez, Diego Borro

2010

Abstract

The reconstruction of a 3D map is the key point of any SLAM algorithm. Traditionally these maps are built using non-linear minimization techniques, which need a lot of computational resources. In this paper we present a highly paralellizable stochastic approach that fits very well on the graphics hardware. It can achieve the same precision as non-linear optimization methods without loosing the real time performance. Results are compared against the well known Levenberg-Marquardt algorithm using real video sequences.

Download


Paper Citation


in Harvard Style

R. Sánchez J., Álvarez H. and Borro D. (2010). GPU OPTIMIZER: A 3D RECONSTRUCTION ON THE GPU USING MONTE CARLO SIMULATIONS - How to Get Real Time without Sacrificing Precision . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 443-446. DOI: 10.5220/0002826704430446

in Bibtex Style

@conference{visapp10,
author={Jairo R. Sánchez and Hugo Álvarez and Diego Borro},
title={GPU OPTIMIZER: A 3D RECONSTRUCTION ON THE GPU USING MONTE CARLO SIMULATIONS - How to Get Real Time without Sacrificing Precision},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={443-446},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002826704430446},
isbn={978-989-674-028-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - GPU OPTIMIZER: A 3D RECONSTRUCTION ON THE GPU USING MONTE CARLO SIMULATIONS - How to Get Real Time without Sacrificing Precision
SN - 978-989-674-028-3
AU - R. Sánchez J.
AU - Álvarez H.
AU - Borro D.
PY - 2010
SP - 443
EP - 446
DO - 10.5220/0002826704430446