Triplet Neural Networks for the Visual Localization of Mobile Robots

Marcos Alfaro, Juan Cabrera, Luis M. Jiménez, Óscar Reinoso, Óscar Reinoso, Luis Payá

2024

Abstract

Triplet networks are composed of three identical convolutional neural networks that function in parallel and share their weights. These architectures receive three inputs simultaneously and provide three different outputs, and have demonstrated to have a great potential to tackle visual localization. Therefore, this paper presents an exhaustive study of the main factors that influence the training of a triplet network, which are the choice of the triplet loss function, the selection of samples to include in the training triplets and the batch size. To do that, we have adapted and retrained a network with omnidirectional images, which have been captured in an indoor environment with a catadioptric camera and have been converted into a panoramic format. The experiments conducted demonstrate that triplet networks improve substantially the performance in the visual localization task. However, the right choice of the studied factors is of great importance to fully exploit the potential of such architectures.

Paper Citation

in Harvard Style

Alfaro M., Cabrera J., M. Jiménez L., Reinoso Ó. and Payá L. (2024). Triplet Neural Networks for the Visual Localization of Mobile Robots. In Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO; ISBN 978-989-758-717-7, SciTePress, pages 125-132. DOI: 10.5220/0012927400003822

in Bibtex Style

@conference{icinco24,
author={Marcos Alfaro and Juan Cabrera and Luis M. Jiménez and Óscar Reinoso and Luis Payá},
title={Triplet Neural Networks for the Visual Localization of Mobile Robots},
booktitle={Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO},
year={2024},
pages={125-132},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012927400003822},
isbn={978-989-758-717-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO
TI - Triplet Neural Networks for the Visual Localization of Mobile Robots
SN - 978-989-758-717-7
AU - Alfaro M.
AU - Cabrera J.
AU - M. Jiménez L.
AU - Reinoso Ó.
AU - Payá L.
PY - 2024
SP - 125
EP - 132
DO - 10.5220/0012927400003822
PB - SciTePress