Mostrar el registro sencillo del ítem

Ponencia

dc.creatorParra Barrero, Eloyes
dc.creatorFernández Berni, Jorgees
dc.creatorOliveira, Fernanda D.V.R.es
dc.creatorCarmona Galán, Ricardoes
dc.creatorRodríguez Vázquez, Ángel Benitoes
dc.date.accessioned2019-09-19T14:15:47Z
dc.date.available2019-09-19T14:15:47Z
dc.date.issued2016
dc.identifier.citationParra Barrero, E., Fernández Berni, J., Oliveira, F.D.V.R., Carmona Galán, R. y Rodríguez Vázquez, Á.B. (2016). High-Level Performance Evaluation of Object Detection Based on Massively Parallel Focal-Plane Acceleration Requiring Minimum Pixel Area Overhead. En Proceedings of 11th International Conference on Computer Vision Theory and Applications (VISAPP) (79-85), Roma, Italia: Springer.
dc.identifier.urihttps://hdl.handle.net/11441/89209
dc.description.abstractSmart CMOS image sensors can leverage the inherent data-level parallelism and regular computational flow of early vision by incorporating elementary processors at pixel level. However, it comes at the cost of extra area having a strong impact on the sensor sensitivity, resolution and image quality. In this scenario, the fundamental challenge is to devise new strategies capable of boosting the performance of the targeted vision pipeline while minimally affecting the sensing function itself. Such strategies must also feature enough flexibility to accommodate particular application requirements. From these high-level specifications, we propose a focal-plane processing architecture tailored to speed up object detection via the Viola-Jones algorithm. This architecture is supported by only two extra transistors per pixel and simple peripheral digital circuitry that jointly make up a massively parallel reconfigurable processing lattice. A performance evaluation of the proposed scheme in terms of accuracy and acceleration for face detection is reported.es
dc.description.sponsorshipMinisterio de Economía y Competitividad TEC2012-38921-C02es
dc.description.sponsorshipJunta de Andalucía TIC 2338-2013es
dc.description.sponsorshipOffice of Naval Research (USA) N000141410355es
dc.formatapplication/pdfes
dc.language.isoenges
dc.publisherSpringeres
dc.relation.ispartofProceedings of 11th International Conference on Computer Vision Theory and Applications (VISAPP) (2016), p 79-85
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectEmbedded Systemses
dc.subjectVision Pipelinees
dc.subjectEarly Visiones
dc.subjectSmart Image Sensorses
dc.subjectVision Chipses
dc.subjectFocal-Plane Processinges
dc.subjectObject Detectiones
dc.subjectViola-Jones Algorithmes
dc.subjectPerformancees
dc.subjectProcessing Accelerationes
dc.titleHigh-Level Performance Evaluation of Object Detection Based on Massively Parallel Focal-Plane Acceleration Requiring Minimum Pixel Area Overheades
dc.typeinfo:eu-repo/semantics/conferenceObjectes
dcterms.identifierhttps://ror.org/03yxnpp24
dc.type.versioninfo:eu-repo/semantics/acceptedVersiones
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses
dc.contributor.affiliationUniversidad de Sevilla. Departamento de Electrónica y Electromagnetismoes
dc.relation.projectIDTEC2012-38921-C02es
dc.relation.projectIDTIC 2338-2013es
dc.relation.projectIDN000141410355es
idus.format.extent7 p.es
dc.publication.initialPage79es
dc.publication.endPage85es
dc.eventtitleProceedings of 11th International Conference on Computer Vision Theory and Applications (VISAPP)es
dc.eventinstitutionRoma, Italiaes

FicherosTamañoFormatoVerDescripción
High-Level Performance Evaluat ...1.288MbIcon   [PDF] Ver/Abrir  

Este registro aparece en las siguientes colecciones

Mostrar el registro sencillo del ítem

Attribution-NonCommercial-NoDerivatives 4.0 Internacional
Excepto si se señala otra cosa, la licencia del ítem se describe como: Attribution-NonCommercial-NoDerivatives 4.0 Internacional