Show simple item record

dc.contributor.authorLin, Xiao
dc.contributor.authorSánchez Escobedo, Dalila
dc.contributor.authorCasas Pla, Josep Ramon
dc.contributor.authorPardàs Feliu, Montse
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2019-04-26T21:01:14Z
dc.date.available2019-04-26T21:01:14Z
dc.date.issued2019-04-15
dc.identifier.citationLin, X. [et al.]. Depth estimation and semantic segmentation from a single RGB image using a hybrid convolutional neural network. "Sensors", 15 Abril 2019, vol. 19, núm. 1795, p. 1-20.
dc.identifier.issn1424-8220
dc.identifier.urihttp://hdl.handle.net/2117/132168
dc.description.abstractSemantic segmentation and depth estimation are two important tasks in computer vision, and many methods have been developed to tackle them. Commonly these two tasks are addressed independently, but recently the idea of merging these two problems into a sole framework has been studied under the assumption that integrating two highly correlated tasks may benefit each other to improve the estimation accuracy. In this paper, depth estimation and semantic segmentation are jointly addressed using a single RGB input image under a unified convolutional neural network. We analyze two different architectures to evaluate which features are more relevant when shared by the two tasks and which features should be kept separated to achieve a mutual improvement. Likewise, our approaches are evaluated under two different scenarios designed to review our results versus single-task and multi-task methods. Qualitative and quantitative experiments demonstrate that the performance of our methodology outperforms the state of the art on single-task approaches, while obtaining competitive results compared with other multi-task methods.
dc.format.extent20 p.
dc.language.isoeng
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshImage processing
dc.subject.otherdepth estimation
dc.subject.othersemantic segmentation
dc.subject.otherconvolutional neural networks
dc.subject.otherhybrid architecture
dc.titleDepth estimation and semantic segmentation from a single RGB image using a hybrid convolutional neural network
dc.typeArticle
dc.subject.lemacXarxes neuronals (Informàtica)
dc.subject.lemacImatges -- Processament
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.identifier.doi10.3390/s19081795
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://www.mdpi.com/1424-8220/19/8/1795
dc.rights.accessOpen Access
local.identifier.drac24248074
dc.description.versionPostprint (author's final draft)
local.citation.authorLin, X.; Sánchez, D.; Casas, J.; Pardas, M.
local.citation.publicationNameSensors
local.citation.volume19
local.citation.number1795
local.citation.startingPage1
local.citation.endingPage20


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain