Show simple item record

dc.contributor.authorRomera Carmena, Eduardo 
dc.contributor.authorBergasa Pascual, Luis Miguel 
dc.contributor.authorYang, Kailun
dc.contributor.authorAlvarez, Jose M.
dc.contributor.authorBarea Navarro, Rafael 
dc.date.accessioned2020-11-16T18:21:21Z
dc.date.available2020-11-16T18:21:21Z
dc.date.issued2019-06
dc.identifier.bibliographicCitationRomera, E., Bergasa, L. M., Yang, K., Álvarez, J. M. & Barea, R. 2019, "Bridging the day and night domain gap for semantic segmentation", en 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France, 2019, pp. 1312-1318
dc.identifier.isbn978-1-7281-0561-1
dc.identifier.urihttp://hdl.handle.net/10017/45110
dc.description2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France, 9-12 Jun. 2019
dc.description.abstractPerception in autonomous vehicles has progressed exponentially in the last years thanks to the advances of visionbased methods such as Convolutional Neural Networks (CNNs). Current deep networks are both efficient and reliable, at least in standard conditions, standing as a suitable solution for the perception tasks of autonomous vehicles. However, there is a large accuracy downgrade when these methods are taken to adverse conditions such as nighttime. In this paper, we study methods to alleviate this accuracy gap by using recent techniques such as Generative Adversarial Networks (GANs). We explore diverse options such as enlarging the dataset to cover these domains in unsupervised training or adapting the images on-the-fly during inference to a comfortable domain such as sunny daylight in a pre-processing step. The results show some interesting insights and demonstrate that both proposed approaches considerably reduce the domain gap, allowing IV perception systems to work reliably also at night.en
dc.description.sponsorshipMinisterio de Economía y competitividades_ES
dc.description.sponsorshipComunidad de Madrides_ES
dc.format.mimetypeapplication/pdfen
dc.language.isoengen
dc.publisherIEEE
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional*
dc.rights© 2019 IEEE
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.titleBridging the day and night domain gap for semantic segmentationen
dc.typeinfo:eu-repo/semantics/conferenceObjecten
dc.subject.ecienciaElectrónicaes_ES
dc.subject.ecienciaElectronicsen
dc.contributor.affiliationUniversidad de Alcalá. Departamento de Electrónicaes_ES
dc.relation.publisherversionhttps://doi.org/10.1109/IVS.2019.8813888
dc.type.versioninfo:eu-repo/semantics/acceptedVersionen
dc.identifier.doi10.1109/IVS.2019.8813888
dc.relation.projectIDinfo:eu-repo/grantAgreement/MINECO//TRA2015-70501-C2-1-R/ES/VEHICULO INTELIGENTE PARA PERSONAS MAYORES/en
dc.relation.projectIDinfo:eu-repo/grantAgreement/CAM//P2018%2FNMT-4331/ES/Madrid Robotics Digital Innovation Hub/RoboCity2030-DIH-CMen
dc.rights.accessRightsinfo:eu-repo/semantics/openAccessen
dc.identifier.publicationtitle2019 IEEE Intelligent Vehicles Symposium (IV)
dc.identifier.publicationlastpage1318
dc.identifier.publicationfirstpage1312


Files in this item

Thumbnail

This item appears in the following Collection(s)

Attribution-NonCommercial-NoDerivatives 4.0 Internacional
Este ítem está sujeto a una licencia Creative Commons.