Logo do repositório
 
Publicação

Deep Learning-Based Event Data Coding: A Joint Spatiotemporal and Polarity Solution

2026-01-20Artigo científico Acesso restrito
Ver registo simples
datacite.subject.fosEngenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
datacite.subject.sdg09:Indústria, Inovação e Infraestruturas
datacite.subject.sdg10:Reduzir as Desigualdades
datacite.subject.sdg11:Cidades e Comunidades Sustentáveis
dc.contributor.authorSeleem, Abdelrahman
dc.contributor.authorGuarda, André F. R.
dc.contributor.authorRodrigues, Nuno M. M.
dc.contributor.authorPereira, Fernando
dc.date.accessioned2026-03-02T10:25:59Z
dc.date.available2026-03-02T10:25:59Z
dc.date.issued2026-01-20
dc.date.updated2026-02-21T09:11:31Z
dc.descriptionSubmitted version: 5 Feb 2025.
dc.description.abstractNeuromorphic vision sensors, commonly referred to as event cameras, generate a massive number of pixel-level events, composed by spatiotemporal and polarity information, thus demanding highly efficient coding solutions. Existing solutions focus on lossless coding of event data, assuming that no distortion is acceptable for the target use cases, mostly including computer vision tasks such as classification and recognition. One promising coding approach exploits the similarity between event data and point clouds, both being sets of 3D points, thus allowing to use current point cloud coding solutions to code event data, typically adopting a two-point clouds representation, one for each event polarity. This paper proposes a novel lossy Deep Learning-based Joint Event data Coding (DL-JEC) solution, which adopts for the first time a single-point cloud representation, where the event polarity plays the role of a point cloud attribute, thus enabling to exploit the correlation between the geometry/spatiotemporal and polarity event information. Moreover, this paper also proposes novel adaptive voxel binarization strategies which may be used in DL-JEC, optimized for either quality-oriented or computer vision task-oriented purposes which allow to maximize the performance for the task at hand. DL-JEC can achieve significant compression performance gains when compared with relevant conventional and DL-based state-of-the-art event data coding solutions, notably the MPEG G-PCC and JPEG Pleno PCC standards. Furthermore, it is shown that it is possible to use lossy event data coding, with significantly reduced rate regarding lossless coding, without compromising the target computer vision task performance, notably event classification, thus changing the current event data coding paradigm.eng
dc.description.sponsorshipThis work was supported by the National Funds through FCT– Fundação para a Ciência e a Tecnologia, I.P., and, when eligible, co-funded by EU Funds under Project/Support UID/50008/2025– Instituto de Telecomunicações., [DOI:10.54499/UID/50008/2025].
dc.description.versionN/A
dc.identifier.citationSeleem, Abdelrahman & Guarda, André & Rodrigues, Nuno. (2025). Deep Learning-based Event Data Coding: A Joint Spatiotemporal and Polarity Solution. 10.48550/arXiv.2502.03285.
dc.identifier.doi10.1109/ojsp.2026.3656104en_US
dc.identifier.issn2644-1322en_US
dc.identifier.slugcv-prod-4757762
dc.identifier.urihttp://hdl.handle.net/10400.8/15748
dc.language.isoeng
dc.peerreviewedn/a
dc.publisherIEEE
dc.relationInstituto de Telecomunicações
dc.relation.hasversionhttps://signalprocessingsociety.org/publications-resources/ieee-open-journal-signal-processing?field_magazine_category_target_id_selective=1200
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectDeeplearning
dc.subjectevent data classification
dc.subjectevent data coding
dc.subjectpoint cloud coding
dc.titleDeep Learning-Based Event Data Coding: A Joint Spatiotemporal and Polarity Solutioneng
dc.typejournal article
dspace.entity.typePublication
oaire.awardNumberUID/50008/2025
oaire.awardTitleInstituto de Telecomunicações
oaire.awardURIhttp://hdl.handle.net/10400.8/15747
oaire.citation.endPage237
oaire.citation.startPage222
oaire.citation.titleIEEE Open Journal of Signal Processingen_US
oaire.citation.volume7en_US
oaire.fundingStreamAvaliação UID 2023/2024
oaire.versionhttp://purl.org/coar/version/c_71e4c1898caa6e32
person.familyNameM. M. Rodrigues
person.givenNameNuno
person.identifier.ciencia-id6917-B121-4E34
person.identifier.orcid0000-0001-9536-1017
person.identifier.scopus-author-id7006052345
rcaap.cv.cienciaid6917-B121-4E34 | NUNO MIGUEL MORAIS RODRIGUES
rcaap.rightsopenAccessen_US
relation.isAuthorOfPublicationb4ebe652-7f0e-4e67-adb0-d5ea29fc9e69
relation.isAuthorOfPublication.latestForDiscoveryb4ebe652-7f0e-4e67-adb0-d5ea29fc9e69
relation.isProjectOfPublicationfb51562e-8a49-4d10-b530-5f39dca8aa62
relation.isProjectOfPublication.latestForDiscoveryfb51562e-8a49-4d10-b530-5f39dca8aa62

Ficheiros

Principais
A mostrar 1 - 2 de 2
Miniatura indisponível
Nome:
OJSP3656104.pdf
Tamanho:
3.18 MB
Formato:
Adobe Portable Document Format
Descrição:
Versão editora, IEEE Open Journal of Signal Processing A. Seleem, A. Guarda, Nuno M. M. Rodrigues, F. Pereira, Deep Learning-based Event Data Coding: A Joint Spatiotemporal and Polarity Solution, IEEE Open Journal of Signal Processing, Vol. 7, No., pp. 222 - 237, 2026. 10.54499/UID/50008/2025.
Ver/Abrir
Miniatura indisponível
Nome:
Versão submetida.pdf
Tamanho:
913.04 KB
Formato:
Adobe Portable Document Format
Descrição:
_PDF em arXiv:2502.03285 [cs.CV].
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
1.33 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

CiênciaVitae