Evaluation of RGB and LiDAR Combination for Robust Place Recognition

Farid Alijani, Jukka Peltomäki, Jussi Puura, Heikki Huttunen, Joni-Kristian Kämäräinen, Esa Rahtu

2022

Abstract

Place recognition is one of the main challenges in localization, mapping and navigation tasks of self-driving vehicles under various perceptual conditions, including appearance and viewpoint variations. In this paper, we provide a comprehensive study on the utility of fine-tuned Deep Convolutional Neural Network (DCNN) with three MAC, SpoC and GeM pooling layers to learn global image representation for place recognition in an end-to-end manner using three different sensor data modalities: (1) only RGB images; (2) only intensity or only depth 3D LiDAR point clouds projected into 2D images and (3) early fusion of RGB images and LiDAR point clouds (both intensity and depth) to form a unified global descriptor to leverage robust features of both modalities. The experimental results on a diverse and large long-term Oxford Radar RobotCar dataset illustrate an achievement of 5 m outdoor place recognition accuracy with high recall rate of 90 % using early fusion of RGB and LiDAR sensor data modalities when fine-tuned network with GeM pooling layer is utilized.

Paper Citation

in Harvard Style

Alijani F., Peltomäki J., Puura J., Huttunen H., Kämäräinen J. and Rahtu E. (2022). Evaluation of RGB and LiDAR Combination for Robust Place Recognition. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 650-658. DOI: 10.5220/0010909100003124

in Bibtex Style

@conference{visapp22,
author={Farid Alijani and Jukka Peltomäki and Jussi Puura and Heikki Huttunen and Joni-Kristian Kämäräinen and Esa Rahtu},
title={Evaluation of RGB and LiDAR Combination for Robust Place Recognition},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={650-658},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010909100003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - Evaluation of RGB and LiDAR Combination for Robust Place Recognition
SN - 978-989-758-555-5
AU - Alijani F.
AU - Peltomäki J.
AU - Puura J.
AU - Huttunen H.
AU - Kämäräinen J.
AU - Rahtu E.
PY - 2022
SP - 650
EP - 658
DO - 10.5220/0010909100003124
PB - SciTePress