Publication:
A method for synthetic LiDAR generation to create annotated datasets for autonomous vehicles perception

Simple item page
dc.affiliation.dptoUC3M. Departamento de Ingeniería de Sistemas y Automáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Laboratorio de Sistemas Inteligenteses
dc.contributor.authorBeltrán de la Cita, Jorge
dc.contributor.authorCortes Lafuente, Irene
dc.contributor.authorBarrera Del Pozo, Alejandro
dc.contributor.authorUrdiales de la Parra, Jesús
dc.contributor.authorGuindel Gómez, Carlos
dc.contributor.authorGarcía Fernández, Fernando
dc.contributor.authorEscalera Hueso, Arturo de la
dc.contributor.funderComunidad de Madrides
dc.contributor.funderMinisterio de Ciencia, Innovación y Universidades (España)es
dc.date.accessioned2021-11-18T09:26:15Z
dc.date.available2021-11-18T09:26:15Z
dc.date.issued2019-10-27
dc.descriptionProceedings of: 2019 IEEE Intelligent Transportation Systems Conference (ITSC)en
dc.description.abstractLiDAR devices have become a key sensor for autonomous vehicles perception due to their ability to capture reliable geometry information. Indeed, approaches processing LiDAR data have shown an impressive accuracy for 3D object detection tasks, outperforming methods solely based on image inputs. However, the wide diversity of on-board sensor configurations makes the deployment of published algorithms into real platforms a hard task, due to the scarcity of annotated datasets containing laser scans. We present a method to generate new point clouds datasets as captured by a real LiDAR device. The proposed pipeline makes use of multiple frames to perform an accurate 3D reconstruction of the scene in the spherical coordinates system that enables the simulation of the sweeps of a virtual LiDAR sensor, configurable both in location and inner specifications. The similarity between real data and the generated synthetic clouds is assessed through a set of experiments performed using KITTI Depth and Object Benchmarks.en
dc.description.sponsorshipResearch supported by the Spanish Government through the CICYT projects (TRA2016-78886-C3-1-R and RTI2018-096036-B-C21), and the Comunidad de Madrid through SEGVAUTO-4.0-CM (P2018/EMT-4362). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPUs used for this research.en
dc.format.extent6
dc.identifier.bibliographicCitationBeltrán, J., Cortés, I., Barrera, A., Urdiales, J., Guindel, C., García, F. & de la Escalera, A. (27-30 October, 2019). A method for synthetic LiDAR generation to create annotated datasets for autonomous vehicles perception [Proceedings]. 2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, pp. 1091-1096.en
dc.identifier.doihttps://doi.org/10.1109/ITSC.2019.8917176
dc.identifier.isbn978-1-5386-7024-8
dc.identifier.publicationfirstpage1091
dc.identifier.publicationlastpage1096
dc.identifier.publicationtitle2019 IEEE Intelligent Transportation Systems Conference (ITSC)en
dc.identifier.urihttps://hdl.handle.net/10016/33633
dc.identifier.uxxiCC/0000030346
dc.language.isoeng
dc.publisherIEEE
dc.relation.eventdate2019-10-27
dc.relation.eventplaceAuckland, Nueva Zelandaes
dc.relation.eventtitleITSC 2019: IEEE Intelligent Transportation Systems Conferenceen
dc.relation.projectIDGobierno de España. TRA2016-78886-C3-1-Res
dc.relation.projectIDGobierno de España. RTI2018-096036-B-C21es
dc.relation.projectIDComunidad de Madrid. P2018/EMT-4362es
dc.rights© 2019, IEEEen
dc.rights.accessRightsopen accessen
dc.subject.ecienciaInformáticaes
dc.subject.ecienciaRobótica e Informática Industriales
dc.subject.otherThree-dimensional displaysen
dc.subject.otherLaser radaren
dc.subject.otherAutonomous vehiclesen
dc.subject.otherObject detectionen
dc.subject.otherGeometryen
dc.subject.otherLasersen
dc.subject.otherPipelinesen
dc.titleA method for synthetic LiDAR generation to create annotated datasets for autonomous vehicles perceptionen
dc.typeconference output*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Method_ITSC_2019_ps.pdf
Size:
3.83 MB
Format:
Adobe Portable Document Format
Download
Collections
DISA - LSI - Artículos en Congresos Internacionales