The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nous présentons une boîte à outils de fusion multi-capteurs précise et facile à utiliser pour les véhicules autonomes. Il comprend un multi-LiDAR (détection et télémétrie de la lumière) « sans cible », un étalonnage caméra-LiDAR, une fusion de capteurs et un classificateur au sol de nuages de points rapide et précis. Nos méthodes d'étalonnage ne nécessitent pas de procédures de configuration complexes, et une fois les capteurs calibrés, notre cadre facilite la fusion de plusieurs nuages de points et caméras. De plus, nous présentons un classificateur original d'obstacles au sol en temps réel, qui fonctionne sur le processeur et est conçu pour être utilisé avec n'importe quel type et nombre de LiDAR. Les résultats de l'évaluation sur l'ensemble de données KITTI confirment que notre méthode d'étalonnage a une précision comparable à celle d'autres concurrents de pointe dans le benchmark.
Abraham MONRROY CANO
Nagoya University
Eijiro TAKEUCHI
Nagoya University
Shinpei KATO
The University of Tokyo
Masato EDAHIRO
Nagoya University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Abraham MONRROY CANO, Eijiro TAKEUCHI, Shinpei KATO, Masato EDAHIRO, "An Open Multi-Sensor Fusion Toolbox for Autonomous Vehicles" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 1, pp. 252-264, January 2020, doi: 10.1587/transfun.2019TSP0005.
Abstract: We present an accurate and easy-to-use multi-sensor fusion toolbox for autonomous vehicles. It includes a ‘target-less’ multi-LiDAR (Light Detection and Ranging), and Camera-LiDAR calibration, sensor fusion, and a fast and accurate point cloud ground classifier. Our calibration methods do not require complex setup procedures, and once the sensors are calibrated, our framework eases the fusion of multiple point clouds, and cameras. In addition we present an original real-time ground-obstacle classifier, which runs on the CPU, and is designed to be used with any type and number of LiDARs. Evaluation results on the KITTI dataset confirm that our calibration method has comparable accuracy with other state-of-the-art contenders in the benchmark.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2019TSP0005/_p
Copier
@ARTICLE{e103-a_1_252,
author={Abraham MONRROY CANO, Eijiro TAKEUCHI, Shinpei KATO, Masato EDAHIRO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={An Open Multi-Sensor Fusion Toolbox for Autonomous Vehicles},
year={2020},
volume={E103-A},
number={1},
pages={252-264},
abstract={We present an accurate and easy-to-use multi-sensor fusion toolbox for autonomous vehicles. It includes a ‘target-less’ multi-LiDAR (Light Detection and Ranging), and Camera-LiDAR calibration, sensor fusion, and a fast and accurate point cloud ground classifier. Our calibration methods do not require complex setup procedures, and once the sensors are calibrated, our framework eases the fusion of multiple point clouds, and cameras. In addition we present an original real-time ground-obstacle classifier, which runs on the CPU, and is designed to be used with any type and number of LiDARs. Evaluation results on the KITTI dataset confirm that our calibration method has comparable accuracy with other state-of-the-art contenders in the benchmark.},
keywords={},
doi={10.1587/transfun.2019TSP0005},
ISSN={1745-1337},
month={January},}
Copier
TY - JOUR
TI - An Open Multi-Sensor Fusion Toolbox for Autonomous Vehicles
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 252
EP - 264
AU - Abraham MONRROY CANO
AU - Eijiro TAKEUCHI
AU - Shinpei KATO
AU - Masato EDAHIRO
PY - 2020
DO - 10.1587/transfun.2019TSP0005
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2020
AB - We present an accurate and easy-to-use multi-sensor fusion toolbox for autonomous vehicles. It includes a ‘target-less’ multi-LiDAR (Light Detection and Ranging), and Camera-LiDAR calibration, sensor fusion, and a fast and accurate point cloud ground classifier. Our calibration methods do not require complex setup procedures, and once the sensors are calibrated, our framework eases the fusion of multiple point clouds, and cameras. In addition we present an original real-time ground-obstacle classifier, which runs on the CPU, and is designed to be used with any type and number of LiDARs. Evaluation results on the KITTI dataset confirm that our calibration method has comparable accuracy with other state-of-the-art contenders in the benchmark.
ER -