Repository logo
 
Publication

A generic framework for optimal 2D/3D key-frame extraction driven by aggregated saliency maps

2015-11Journal article Restricted access
Simple item page
datacite.subject.fosEngenharia e Tecnologia
datacite.subject.sdg09:Indústria, Inovação e Infraestruturas
dc.contributor.authorFerreira, Lino
dc.contributor.authorCruz, Luis A. da Silva
dc.contributor.authorAssunção, Pedro
dc.date.accessioned2025-06-04T13:59:12Z
dc.date.available2025-06-04T13:59:12Z
dc.date.issued2015-11
dc.description.abstractThis paper proposes a generic framework for extraction of key-frames from 2D or 3D video sequences, relying on a new method to compute 3D visual saliency. The framework comprises the following novel aspects that distinguish this work from previous ones: (i) the key-frame selection process is driven by an aggregated saliency map, computed from various feature maps, which in turn correspond to different visual attention models; (ii) a method for computing aggregated saliency maps in 3D video is proposed and validated using fixation density maps, obtained from ground-truth eye-tracking data; (iii) 3D video content is processed within the same framework as 2D video, by including a depth feature map into the aggregated saliency. A dynamic programming optimisation algorithm is used to find the best set of K frames that minimises the dissimilarity error (i.e., maximise similarity) between the original video shots of size and those reconstructed from the key-frames. Using different performance metrics and publicly available databases, the simulation results demonstrate that the proposed framework outperforms similar state-of-art methods and achieves comparable performance as other quite different approaches. Overall, the proposed framework is validated for a wide range of visual content and has the advantage of being independent from any specific visual saliency model or similarity metrics.eng
dc.description.sponsorshipFunding This work was supported by R&D Unit UID/EEA/50008/2013, Project 3DVQM and PhD Grant SFRH/BD/37510/2007, co-funded by FEDER-PT2020, FCT/MEC, Portugal .
dc.identifier.citationFerreira, Lino & da Silva Cruz, Luis & Assunção, Pedro. (2015). A generic framework for optimal 2D/3D key-frame extraction driven by aggregated saliency maps. Signal Processing: Image Communication. 39. 10.1016/j.image.2015.09.005.
dc.identifier.doi10.1016/j.image.2015.09.005
dc.identifier.issn0923-5965
dc.identifier.urihttp://hdl.handle.net/10400.8/13107
dc.language.isoeng
dc.peerreviewedyes
dc.publisherElsevier
dc.relationInstituto de Telecomunicações
dc.relationSCALABLE VIDEO CODING WITH DYNAMIC REGIONS OF INTEREST
dc.relation.hasversionhttps://www.sciencedirect.com/science/article/pii/S0923596515001459
dc.relation.ispartofSignal Processing: Image Communication
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subject3D key-frames
dc.subjectVisual saliency map
dc.subject3D video summary
dc.subjectAggregated saliency map
dc.titleA generic framework for optimal 2D/3D key-frame extraction driven by aggregated saliency mapseng
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleInstituto de Telecomunicações
oaire.awardTitleSCALABLE VIDEO CODING WITH DYNAMIC REGIONS OF INTEREST
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F50008%2F2020/PT
oaire.awardURIhttp://hdl.handle.net/10400.8/13106
oaire.citation.endPage110
oaire.citation.startPage98
oaire.citation.titleSignal Processing: Image Communication
oaire.citation.volume39, Part A
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStreamFARH
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameFerreira
person.familyNameAssunção
person.givenNameLino
person.givenNamePedro
person.identifier.ciencia-id061B-4DCB-78BE
person.identifier.ciencia-id6811-3984-C17B
person.identifier.orcid0000-0003-0648-6067
person.identifier.orcid0000-0001-9539-8311
person.identifier.ridAAA-4462-2020
person.identifier.ridA-4827-2017
person.identifier.scopus-author-id36881920000
person.identifier.scopus-author-id6701838347
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublication03a0439a-a3c2-4fb1-8239-10b98d64659a
relation.isAuthorOfPublication25649bb9-f135-48e8-8d0f-3706b86701d3
relation.isAuthorOfPublication.latestForDiscovery03a0439a-a3c2-4fb1-8239-10b98d64659a
relation.isProjectOfPublication91a8e212-cbb0-462f-b533-5ed3552e8067
relation.isProjectOfPublicationc9f7d818-7311-4d3f-8f04-1c64d39a8040
relation.isProjectOfPublication.latestForDiscovery91a8e212-cbb0-462f-b533-5ed3552e8067

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
A generic framework for optimal 2D 3D.pdf
Size:
1.49 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.32 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ESTG - Artigos em revistas internacionais