Identificador persistente para citar o vincular este elemento: https://accedacris.ulpgc.es/handle/10553/139745
Campo DC Valoridioma
dc.contributor.authorMohamed, Sondosen_US
dc.contributor.authorZimmer, Walteren_US
dc.contributor.authorGreer, Rossen_US
dc.contributor.authorGhita, Ahmed Alaaeldinen_US
dc.contributor.authorCastrillón-Santana, Modestoen_US
dc.contributor.authorTrivedi, Mohanen_US
dc.contributor.authorKnoll, Aloisen_US
dc.contributor.authorCarta, Salvatore Marioen_US
dc.contributor.authorMarras, Mirkoen_US
dc.date.accessioned2025-06-09T12:03:26Z-
dc.date.available2025-06-09T12:03:26Z-
dc.date.issued2025en_US
dc.identifier.isbn9783031918124en_US
dc.identifier.issn0302-9743en_US
dc.identifier.otherScopus-
dc.identifier.urihttps://accedacris.ulpgc.es/handle/10553/139745-
dc.description.abstractAccurately detecting 3D objects from monocular images in dynamic roadside scenarios remains a challenging problem due to varying camera perspectives and unpredictable scene conditions. This paper introduces a two-stage training strategy to address these challenges. Our approach initially trains a model on the large-scale synthetic dataset, RoadSense3D, which offers a diverse range of scenarios for robust feature learning. Subsequently, we fine-tune the model on a combination of real-world datasets to enhance its adaptability to practical conditions. Experimental results of the Cube R-CNN model on challenging public benchmarks show a remarkable improvement in detection performance, with a mean average precision rising from 0.26 to 12.76 on the TUM Traffic A9 Highway dataset and from 2.09 to 6.60 on the DAIR-V2X-I dataset, when performing transfer learning. Code, data, and qualitative video results are available at https://roadsense3d.github.io.en_US
dc.languageengen_US
dc.relation.ispartofLecture Notes in Computer Scienceen_US
dc.sourceLecture Notes in Computer Science[ISSN 0302-9743],v. 15630 LNCS, p. 309-325, (Enero 2025)en_US
dc.subject33 Ciencias tecnológicasen_US
dc.subject.otherIntelligent Transportation Systemsen_US
dc.subject.otherIntelligent Vehiclesen_US
dc.subject.otherMonocular 3D Object Detectionen_US
dc.subject.otherSynthetic Dataen_US
dc.subject.otherTransfer Learningen_US
dc.titleTransfer Learning from Simulated to Real Scenes for Monocular 3D Object Detectionen_US
dc.typeinfo:eu-repo/semantics/conferenceObjecten_US
dc.typeConferenceObjecten_US
dc.relation.conferenceWorkshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024en_US
dc.identifier.doi10.1007/978-3-031-91813-1_20en_US
dc.identifier.scopus105006880501-
dc.contributor.orcid0009-0002-5647-6895-
dc.contributor.orcid0000-0003-4565-1272-
dc.contributor.orcid0000-0001-8595-0379-
dc.contributor.orcid0000-0003-3702-8042-
dc.contributor.orcid0000-0002-8673-2725-
dc.contributor.orcid0000-0002-0937-6771-
dc.contributor.orcid0000-0003-4840-076X-
dc.contributor.orcid0000-0001-9481-511X-
dc.contributor.orcid0000-0003-1989-6057-
dc.contributor.authorscopusid57193795607-
dc.contributor.authorscopusid57607056800-
dc.contributor.authorscopusid57220950660-
dc.contributor.authorscopusid58898119100-
dc.contributor.authorscopusid57218418238-
dc.contributor.authorscopusid7103153314-
dc.contributor.authorscopusid7102250639-
dc.contributor.authorscopusid59734046700-
dc.contributor.authorscopusid59469344200-
dc.identifier.eissn1611-3349-
dc.description.lastpage325en_US
dc.description.firstpage309en_US
dc.relation.volume15630 LNCSen_US
dc.investigacionIngeniería y Arquitecturaen_US
dc.type2Actas de congresosen_US
dc.utils.revisionen_US
dc.date.coverdateEnero 2025en_US
dc.identifier.conferenceidevents155916-
dc.identifier.ulpgcen_US
dc.contributor.buulpgcBU-INFen_US
dc.description.sjr0,606
dc.description.sjrqQ2
dc.description.miaricds10,0
item.grantfulltextnone-
item.fulltextSin texto completo-
crisitem.author.deptGIR SIANI: Inteligencia Artificial, Robótica y Oceanografía Computacional-
crisitem.author.deptIU Sistemas Inteligentes y Aplicaciones Numéricas-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.orcid0000-0002-8673-2725-
crisitem.author.parentorgIU Sistemas Inteligentes y Aplicaciones Numéricas-
crisitem.author.fullNameCastrillón Santana, Modesto Fernando-
crisitem.event.eventsstartdate29-09-2024-
crisitem.event.eventsenddate04-10-2024-
Colección:Actas de congresos
Vista resumida

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.