CUDA Accelerated Visual Egomotion Estimation for Robotic Navigation

Safa Ouerghi, Remi Boutteau, Xavier Savatier, Fethi Tlili

2017

Abstract

Egomotion estimation is a fundamental issue in structure from motion and autonomous navigation for mobile robots. Several camera motion estimation methods from a set of variable number of image correspondances have been proposed. Five-point methods represent the minimal number of required correspondences to estimate the essential matrix, raised special interest for their application in a hypothesize-and-test framework. This algorithm allows relative pose recovery at the expense of a much higher computational time when dealing with higher ratios of outliers. To solve this problem with a certain amount of speedup, we propose in this work, a CUDA-based solution for the essential matrix estimation performed using the Grobner basis version of 5-point algorithm, complemented with robust estimation. The description of the hardware-specific implementation considerations as well as the parallelization methods employed are given in detail. Performance analysis against existing CPU implementation is also given, showing a speedup 4 times faster than the CPU for an outlier ratio e = 0.5, common for the essential matrix estimation from automatically computed point correspondences. More speedup was shown when dealing with higher outlier ratios.

Paper Citation

in Harvard Style

Ouerghi S., Boutteau R., Savatier X. and Tlili F. (2017). CUDA Accelerated Visual Egomotion Estimation for Robotic Navigation . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 107-114. DOI: 10.5220/0006171501070114

in Bibtex Style

@conference{visapp17,
author={Safa Ouerghi and Remi Boutteau and Xavier Savatier and Fethi Tlili},
title={CUDA Accelerated Visual Egomotion Estimation for Robotic Navigation},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={107-114},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006171501070114},
isbn={978-989-758-225-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - CUDA Accelerated Visual Egomotion Estimation for Robotic Navigation
SN - 978-989-758-225-7
AU - Ouerghi S.
AU - Boutteau R.
AU - Savatier X.
AU - Tlili F.
PY - 2017
SP - 107
EP - 114
DO - 10.5220/0006171501070114