Fully Convolutional Neural Network for Event Camera Pose Estimation

Ahmed Tabia, Fabien Bonardi, Samia Bouchafa-Bruneau

2023

Abstract

Event cameras are bio-inspired vision sensors that record the dynamics of a scene while filtering out unnecessary data. Many classic pose estimation methods have been superseded by camera relocalization approaches based on convolutional neural networks (CNN) and long short-term memory (LSTM) in the investigation of simultaneous localization and mapping systems. However, and due to the usage of LSTM layer these methods are easy to overfit and usually take a long time to converge. In this paper, we introduce a new method to estimate the 6DOF pose of an event camera with a deep learning. Our approach starts by processing the events and generates a set of images. It then uses two CNNs to extract relevant features from the generated images. Those features are multiplied using the outer product at each location of the image and pooled across locations. The model ends with a regression layer which outputs the estimated position and orientation of the event camera. Our approach has been evaluated on different datasets. The results show its superiority compared to state-of-the-art methods.

Paper Citation

in Harvard Style

Tabia A., Bonardi F. and Bouchafa-Bruneau S. (2023). Fully Convolutional Neural Network for Event Camera Pose Estimation. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 594-599. DOI: 10.5220/0011641500003417

in Bibtex Style

@conference{visapp23,
author={Ahmed Tabia and Fabien Bonardi and Samia Bouchafa-Bruneau},
title={Fully Convolutional Neural Network for Event Camera Pose Estimation},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={594-599},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011641500003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - Fully Convolutional Neural Network for Event Camera Pose Estimation
SN - 978-989-758-634-7
AU - Tabia A.
AU - Bonardi F.
AU - Bouchafa-Bruneau S.
PY - 2023
SP - 594
EP - 599
DO - 10.5220/0011641500003417
PB - SciTePress