# Using Polynomial Eigenvalue Problem Modeling to Improve Visual Odometry for Autonomous Vehicles

### Anderson Souza, Leonardo Souto, Fabio Fonseca de Oliveira, Biswa Nath Datta, Luiz M. G. Gonçalves

#### Abstract

Visual Odometry (VO) is the process of calculating the motion of an agent (such as, robot and vehicle), using images captured by a single or multiple cameras embedded to it. VO is an important process to supplement autonomous navigation systems, since VO can provide accurate trajectory estimates. However, algorithms of VO work with several steps of hard numerical computation which generate numerical errors and demand considerable processing time. In this paper, we propose the use of a mathematical framework for monocular VO process based on Polynomial Eigenvalue Problem (PEP) modeling in order to achieve both more accurate motion estimation and to decrease the processing time of the VO process. Some previous experiments are shown in order to validate the proposed computation accuracy.

Download#### Paper Citation

#### in Harvard Style

Souza A., Souto L., de Oliveira F., Datta B. and Gonçalves L. (2017). **Using Polynomial Eigenvalue Problem Modeling to Improve Visual Odometry for Autonomous Vehicles** . In *Proceedings of the 14th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,* ISBN 978-989-758-264-6, pages 502-507. DOI: 10.5220/0006478005020507

#### in Bibtex Style

@conference{icinco17,

author={Anderson Souza and Leonardo Souto and Fabio Fonseca de Oliveira and Biswa Nath Datta and Luiz M. G. Gonçalves},

title={Using Polynomial Eigenvalue Problem Modeling to Improve Visual Odometry for Autonomous Vehicles},

booktitle={Proceedings of the 14th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},

year={2017},

pages={502-507},

publisher={SciTePress},

organization={INSTICC},

doi={10.5220/0006478005020507},

isbn={978-989-758-264-6},

}

#### in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,

TI - Using Polynomial Eigenvalue Problem Modeling to Improve Visual Odometry for Autonomous Vehicles

SN - 978-989-758-264-6

AU - Souza A.

AU - Souto L.

AU - de Oliveira F.

AU - Datta B.

AU - Gonçalves L.

PY - 2017

SP - 502

EP - 507

DO - 10.5220/0006478005020507