Publication:
Improved strategies for HPE employing learning-by-synthesis approaches

dc.contributor.authorLarumbe Bergera, Andoni
dc.contributor.authorAriz Galilea, Mikel
dc.contributor.authorBengoechea Irañeta, José Javier
dc.contributor.authorSegura, Rubén
dc.contributor.authorCabeza Laguna, Rafael
dc.contributor.authorVillanueva Larre, Arantxa
dc.contributor.departmentIngeniería Eléctrica, Electrónica y de Comunicaciónes_ES
dc.contributor.departmentIngeniaritza Elektrikoa, Elektronikoaren eta Telekomunikazio Ingeniaritzareneu
dc.date.accessioned2021-12-09T12:25:18Z
dc.date.available2021-12-09T12:25:18Z
dc.date.issued2018
dc.description.abstractThe first contribution of this paper is the presentation of a synthetic video database where the groundtruth of 2D facial landmarks and 3D head poses is available to be used for training and evaluating Head Pose Estimation (HPE) methods. The database is publicly available and contains videos of users performing guided and natural movements. The second and main contribution is the submission of a hybrid method for HPE based on Pose from Ortography and Scaling by Iterations (POSIT). The 2D landmark detection is performed using Random Cascaded-Regression Copse (R-CR-C). For the training stage we use, state of the art labeled databases. Learning-by-synthesis approach has been also used to augment the size of the database employing the synthetic database. HPE accuracy is tested by using two literature 3D head models. The tracking method proposed has been compared with state of the art methods using Supervised Descent Regressors (SDR) in terms of accuracy, achieving an improvement of 60%.en
dc.description.sponsorshipSpanish Ministry of Economy, Industry and Competitiveness, contract TIN2014-52897-R.en
dc.format.extent10 p.
dc.format.mimetypeapplication/pdfen
dc.identifier.citationA. Larumbe, M. Ariz, J. J. Bengoechea, R. Segura, R. Cabeza and A. Villanueva, 'Improved Strategies for HPE Employing Learning-by-Synthesis Approaches,' 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017, pp. 1545-1554, doi: 10.1109/ICCVW.2017.182.en
dc.identifier.doi10.1109/ICCVW.2017.182
dc.identifier.issn2473-9944 (Electronic)
dc.identifier.urihttps://academica-e.unavarra.es/handle/2454/41213
dc.language.isoengen
dc.publisherIEEEen
dc.relation.ispartof2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017, pp. 1545-1554en
dc.relation.projectIDinfo:eu-repo/grantAgreement/MINECO//TIN2014-52897-R/ES/en
dc.relation.publisherversionhttps://doi.org/10.1109/ICCVW.2017.182
dc.rights© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other work.en
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.subjectDatabasesen
dc.subjectThree-dimensional displaysen
dc.subjectFaceen
dc.subjectTwo dimensional displaysen
dc.subjectSolid modelingen
dc.subjectCamerasen
dc.titleImproved strategies for HPE employing learning-by-synthesis approachesen
dc.typeinfo:eu-repo/semantics/conferenceObject
dc.type.versioninfo:eu-repo/semantics/acceptedVersionen
dc.type.versionVersión aceptada / Onetsi den bertsioaes
dspace.entity.typePublication
relation.isAuthorOfPublication7d67c732-213a-47e0-82f8-81a897144cfa
relation.isAuthorOfPublication9d2b9c4c-9ede-4367-9ad9-8987addfbff6
relation.isAuthorOfPublicatione4686d1d-7687-4f70-81b2-2487764cabd7
relation.isAuthorOfPublication42fe20f8-5341-4c0e-8686-333ce816adfd
relation.isAuthorOfPublicationd3bfd5bf-8426-455b-bcc4-897ddb0d4c2e
relation.isAuthorOfPublication.latestForDiscovery7d67c732-213a-47e0-82f8-81a897144cfa

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Larumbe_Improved_strategies_acepted.pdf
Size:
6.06 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description: