Publication:
Analysis of the Influence of Training Data on Road User Detection

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.authorGuindel Gómez, Carlos
dc.contributor.authorMartín Gómez, David
dc.contributor.authorArmingol Moreno, José María
dc.contributor.authorStiller, Christoph
dc.contributor.funderComunidad de Madrides
dc.date.accessioned2021-05-25T10:19:20Z
dc.date.available2021-05-25T10:19:20Z
dc.date.issued2018-09-12
dc.description.abstractIn this paper, we discuss the relevance of training data on modern object detectors used on onboard applications. Whereas modern deep learning techniques require large amounts of data, datasets with typical scenarios for autonomous vehicles are scarce and have a reduced number of samples. We conduct a comprehensive set of experiments to understand the effect of using a combination of two relatively small datasets to train an end-to-end object detector, based on the popular Faster R-CNN and enhanced with orientation estimation capabilities. We also test the adequacy of training models using partially available ground-truth labels, as a consequence of combining datasets aimed at different applications. Data augmentation is also introduced into the training pipeline. Results show a significant performance improvement in our exemplary case as a result of the higher variability of the training samples, thus opening a new way to improve the detection performance independently from the detector architecture.en
dc.description.sponsorshipThis work was supported by the Spanish Government through the CICYT projects TRA2015-63708-R and TRA2016-78886-C3-1-R, and the Comunidad de Madrid through SEGVAUTO-TRIES (S2013/MIT-2713).en
dc.description.statusPublicadoes
dc.format.extent6
dc.identifier.bibliographicCitation2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES). Proceedings. IEEE, 2018. Pp. 1-6.en
dc.identifier.doihttps://doi.org/10.1109/ICVES.2018.8519510
dc.identifier.isbn978-1-5386-3543-8
dc.identifier.publicationfirstpage1
dc.identifier.publicationlastpage6
dc.identifier.publicationtitle2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES). Proceedingsen
dc.identifier.urihttps://hdl.handle.net/10016/32744
dc.identifier.uxxiCC/0000029833
dc.language.isoengen
dc.publisherIEEEen
dc.relation.eventdateSeptember 12-14, 2018en
dc.relation.eventnumber20
dc.relation.eventplaceMadrides
dc.relation.eventtitleIEEE International Conference on Vehicular Electronics and Safety (ICVES2018)en
dc.relation.projectIDGobierno de España. TRA2015-63708-Res
dc.relation.projectIDGobierno de España. TRA2016-78886-C3-1-Res
dc.relation.projectIDComunidad de Madrid. S2013/MIT-2713/SEGVAUTO-TRIESes
dc.rights©2018 IEEE.en
dc.rights.accessRightsopen accessen
dc.subject.ecienciaIngeniería Industriales
dc.subject.otherObject detectionen
dc.subject.otherTrainingen
dc.subject.otherProposalsen
dc.subject.otherEstimationen
dc.subject.otherFeature extractionen
dc.subject.otherDetectorsen
dc.subject.otherTask analysisen
dc.titleAnalysis of the Influence of Training Data on Road User Detectionen
dc.typeconference paper*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
analysis_IEEE_ICVES_2018_ps.pdf
Size:
399.29 KB
Format:
Adobe Portable Document Format
Download
Collections
DISA - LSI - Artículos en Congresos Internacionales
DISA - LSI - Capítulos de Monografías