A Double Deep Learning-Based Solution for Efficient Event Data Coding and Classification

Event cameras have the ability to capture asynchronous per-pixel brightness changes, usually called "events", offering advantages over traditional frame-based cameras for computer vision tasks. Efficiently coding event data is critical for practical transmission and storage, given the very...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE access Ročník 13; s. 48703 - 48719
Hlavní autoři:	Seleem, Abdelrahman, Guarda, Andre F. R., Rodrigues, Nuno M. M., Pereira, Fernando
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 01.01.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Cameras Classification Codec Coding Coding standards Computer vision Correlation Decoding Deep learning Encoding event data event data classification event data coding Image compression Loss measurement point cloud coding Point cloud compression Spatial resolution Three-dimensional displays Transform coding Vision sensors
ISSN:	2169-3536, 2169-3536
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Event cameras have the ability to capture asynchronous per-pixel brightness changes, usually called "events", offering advantages over traditional frame-based cameras for computer vision tasks. Efficiently coding event data is critical for practical transmission and storage, given the very significant number of events captured. This paper proposes a novel double deep learning-based solution for efficient event data coding and classification, using a point cloud-based representation for events. Moreover, since the conversions from events to point clouds and back to events are key steps in the proposed solution, novel tools are proposed and their impact is evaluated in terms of compression and classification performance. Experimental results show that it is possible to achieve a classification performance for decompressed events which is similar to the one for original events, even after applying a lossy point cloud codec, notably the recent deep learning-based JPEG Pleno Point Cloud Coding standard, with a clear rate reduction. Experimental results also demonstrate that events coded using the JPEG standard achieve better classification performance than those coded using the conventional lossy MPEG Geometry-based Point Cloud Coding standard for the same rate. Furthermore, the adoption of deep learning-based coding offers future high potential for performing computer vision tasks in the compressed domain, which allows skipping the decoding stage, thus mitigating the impact of compression artifacts.
AbstractList	Event cameras have the ability to capture asynchronous per-pixel brightness changes, usually called "events", offering advantages over traditional frame-based cameras for computer vision tasks. Efficiently coding event data is critical for practical transmission and storage, given the very significant number of events captured. This paper proposes a novel double deep learning-based solution for efficient event data coding and classification, using a point cloud-based representation for events. Moreover, since the conversions from events to point clouds and back to events are key steps in the proposed solution, novel tools are proposed and their impact is evaluated in terms of compression and classification performance. Experimental results show that it is possible to achieve a classification performance for decompressed events which is similar to the one for original events, even after applying a lossy point cloud codec, notably the recent deep learning-based JPEG Pleno Point Cloud Coding standard, with a clear rate reduction. Experimental results also demonstrate that events coded using the JPEG standard achieve better classification performance than those coded using the conventional lossy MPEG Geometry-based Point Cloud Coding standard for the same rate. Furthermore, the adoption of deep learning-based coding offers future high potential for performing computer vision tasks in the compressed domain, which allows skipping the decoding stage, thus mitigating the impact of compression artifacts.
Author	Seleem, Abdelrahman Pereira, Fernando Rodrigues, Nuno M. M. Guarda, Andre F. R.
Author_xml	– sequence: 1 givenname: Abdelrahman orcidid: 0000-0003-3254-0872 surname: Seleem fullname: Seleem, Abdelrahman email: a.seleem@lx.it.pt organization: Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal – sequence: 2 givenname: Andre F. R. orcidid: 0000-0001-5996-1074 surname: Guarda fullname: Guarda, Andre F. R. organization: Instituto de Telecomunicações, Lisbon, Portugal – sequence: 3 givenname: Nuno M. M. orcidid: 0000-0001-9536-1017 surname: Rodrigues fullname: Rodrigues, Nuno M. M. organization: Instituto de Telecomunicações, Lisbon, Portugal – sequence: 4 givenname: Fernando orcidid: 0000-0001-6100-947X surname: Pereira fullname: Pereira, Fernando organization: Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
BookMark	eNpNUUtr4zAQFksL26b5BbsHQc9OrVckHVMnuy0EekgPexOyPAoKXiuVnEL_fZW6lM5hZhi-x8B3jS6GOABCv0i9IKTWd6um2ex2C1pTsWBCkFqyH-iKkqWumGDLi2_7TzTP-VCXUuUk5BX6t8LreGp7wGuAI96CTUMY9tW9zdDhXexPY4gD9jHhjffBBRhGvHk997UdLW5iV-DYDh1ueptzKBh7ptygS2_7DPPPOUPPfzbPzUO1ffr72Ky2lWNKj5V22tVkyTlr3dJpxZlrW64VtIpScKplwmvJFQEOrrOCUMmZ1Z5LrVti2Qw9TrJdtAdzTOG_TW8m2mA-DjHtjU1jcD0YITtZi9YyRoFrXTSp7MB7JT31StGidTtpHVN8OUEezSGe0lC-N4wUP0JJMZ8hNqFcijkn8F-upDbnQMwUiDkHYj4DKazfEysAwDeGpoIJzd4BiriG-g
CODEN	IAECCG
Cites_doi	10.1109/CVPRW.2019.00208 10.1109/TPAMI.2020.3008413 10.1109/MSP.2019.2928127 10.1109/LSP.2020.3010128 10.3389/fnins.2017.00309 10.1109/TPAMI.2015.2392947 10.1109/ITSC.2006.1706816 10.1109/ICPR56361.2022.9956532 10.1017/ATSIP.2020.12 10.1109/JIOT.2020.3007866 10.1109/CVPR.2019.00698 10.1109/CVPR.2018.00568 10.1109/ACCESS.2020.2978109 10.1109/ISM55400.2022.00016 10.1109/WACV57701.2024.00237 10.1007/s11263-017-1050-6 10.1109/MMSP61759.2024.10743984 10.1109/DCC.2018.00020 10.1109/ACCESS.2023.3332599 10.1109/CVPR.2019.00108 10.1609/aaai.v38i10.29066 10.1109/TCSII.2002.807270 10.1109/ICIP49359.2023.10222190 10.1109/CVPR.2004.383 10.1109/IROS.2016.7759345 10.3389/fnins.2015.00437 10.5244/C.31.16 10.1109/TMM.2023.3338081 10.1186/s13640-024-00631-6 10.1117/12.2676419 10.1109/ACCESS.2023.3316143 10.1109/CVPR.2018.00186 10.3389/fnins.2013.00178 10.1109/TPAMI.2016.2574707 10.1109/EUVIP53989.2022.9922751 10.1109/ACCESS.2022.3222330 10.1109/CVPR.2017.781 10.1109/TPAMI.2013.71 10.1109/ICCPHOT.2015.7168370 10.1109/ICCV.2019.00573 10.1109/ICIP49359.2023.10222287
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2025.3551073
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	48719
ExternalDocumentID	oai_doaj_org_article_57d705ba332e49948127deff87f2f882 10_1109_ACCESS_2025_3551073 10925359
Genre	orig-research
GrantInformation_xml	– fundername: Fundação para a Ciência e a Tecnologia (FCT), Portugal, through the research project titled “Deep Learning-Based Point Cloud Representation” grantid: PTDC/EEI-COM/1125/2021 – fundername: FCT/Ministério da Educação, Ciência e Inovação (MECI) through national funds and co-funded by European Union (EU) funds with the Instituto de Telecomunicações grantid: UID/50008
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c389t-9c9c016443bc6c9843cbb498eb822ec8b35f97481e4ecda512743a9f4799b1a3
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001449680800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:44:07 EDT 2025 Mon Jun 30 12:08:41 EDT 2025 Sat Nov 29 08:04:38 EST 2025 Wed Aug 27 01:39:08 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c389t-9c9c016443bc6c9843cbb498eb822ec8b35f97481e4ecda512743a9f4799b1a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-6100-947X 0000-0001-9536-1017 0000-0003-3254-0872 0000-0001-5996-1074
OpenAccessLink	https://ieeexplore.ieee.org/document/10925359
PQID	3179912174
PQPubID	4845423
PageCount	17
ParticipantIDs	doaj_primary_oai_doaj_org_article_57d705ba332e49948127deff87f2f882 crossref_primary_10_1109_ACCESS_2025_3551073 ieee_primary_10925359 proquest_journals_3179912174
PublicationCentury	2000
PublicationDate	2025-01-01
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– month: 01 year: 2025 text: 2025-01-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2025
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref36 ref31 Guarda (ref25) 2024 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref39 ref16 ref38 (ref41) 2020 ref19 ref18 ref24 ref23 ref45 ref26 ref20 ref42 ref22 ref44 ref21 ref28 (ref40) 2022 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 Bjontegaard (ref43) 2001
References_xml	– ident: ref11 doi: 10.1109/CVPRW.2019.00208 – ident: ref12 doi: 10.1109/TPAMI.2020.3008413 – ident: ref4 doi: 10.1109/MSP.2019.2928127 – ident: ref42 doi: 10.1109/LSP.2020.3010128 – ident: ref35 doi: 10.3389/fnins.2017.00309 – ident: ref15 doi: 10.1109/TPAMI.2015.2392947 – ident: ref6 doi: 10.1109/ITSC.2006.1706816 – ident: ref45 doi: 10.1109/ICPR56361.2022.9956532 – ident: ref22 doi: 10.1017/ATSIP.2020.12 – year: 2024 ident: ref25 article-title: The JPEG pleno learning-based point cloud coding standard: Serving man and machine publication-title: arXiv:2409.08130 – ident: ref36 doi: 10.1109/JIOT.2020.3007866 – ident: ref10 doi: 10.1109/CVPR.2019.00698 – ident: ref38 doi: 10.1109/CVPR.2018.00568 – ident: ref3 doi: 10.1109/ACCESS.2020.2978109 – ident: ref30 doi: 10.1109/ISM55400.2022.00016 – ident: ref2 doi: 10.1109/WACV57701.2024.00237 – ident: ref8 doi: 10.1007/s11263-017-1050-6 – ident: ref28 doi: 10.1109/MMSP61759.2024.10743984 – ident: ref37 doi: 10.1109/DCC.2018.00020 – ident: ref26 doi: 10.1109/ACCESS.2023.3332599 – ident: ref21 doi: 10.1109/CVPR.2019.00108 – ident: ref44 doi: 10.1609/aaai.v38i10.29066 – volume-title: Common Test Conditions for Point Cloud Compression year: 2020 ident: ref41 – ident: ref1 doi: 10.1109/TCSII.2002.807270 – ident: ref24 doi: 10.1109/ICIP49359.2023.10222190 – ident: ref39 doi: 10.1109/CVPR.2004.383 – ident: ref5 doi: 10.1109/IROS.2016.7759345 – ident: ref34 doi: 10.3389/fnins.2015.00437 – volume-title: JPEG Pleno Point Cloud Coding Common Training and Test Conditions V1.1 year: 2022 ident: ref40 – ident: ref20 doi: 10.5244/C.31.16 – ident: ref23 doi: 10.1109/TMM.2023.3338081 – ident: ref27 doi: 10.1186/s13640-024-00631-6 – ident: ref33 doi: 10.1117/12.2676419 – ident: ref18 doi: 10.1109/ACCESS.2023.3316143 – ident: ref14 doi: 10.1109/CVPR.2018.00186 – ident: ref17 doi: 10.3389/fnins.2013.00178 – ident: ref13 doi: 10.1109/TPAMI.2016.2574707 – ident: ref29 doi: 10.1109/EUVIP53989.2022.9922751 – ident: ref31 doi: 10.1109/ACCESS.2022.3222330 – volume-title: Calculation of Average PSNR Differences Between RD-Curves year: 2001 ident: ref43 – ident: ref7 doi: 10.1109/CVPR.2017.781 – ident: ref16 doi: 10.1109/TPAMI.2013.71 – ident: ref9 doi: 10.1109/ICCPHOT.2015.7168370 – ident: ref19 doi: 10.1109/ICCV.2019.00573 – ident: ref32 doi: 10.1109/ICIP49359.2023.10222287
SSID	ssj0000816957
Score	2.3412547
Snippet	Event cameras have the ability to capture asynchronous per-pixel brightness changes, usually called "events", offering advantages over traditional frame-based... Event cameras have the ability to capture asynchronous per-pixel brightness changes, usually called “events”, offering advantages over traditional frame-based...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Index Database Publisher
StartPage	48703
SubjectTerms	Cameras Classification Codec Coding Coding standards Computer vision Correlation Decoding Deep learning Encoding event data event data classification event data coding Image compression Loss measurement point cloud coding Point cloud compression Spatial resolution Three-dimensional displays Transform coding Vision sensors
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELUQYoAB8VFEoSAPjASS2I59Y-mHmCqGDt0s27EREmqrtvD7OTspKmJgYY0i2b5L7r1n2e8IuQMJoXSyyJxyMuOV9VgH83jBJ4iCVcYWzKVmE3IyUbMZvOy0-opnwhp74CZwKNhrmQtrGCs9snOOgCRrH4KSoQxID2P1zSXsiKlUg1VRgZCtzVCRw2N_MMAVoSAsxQNiLKoe9gOKkmN_22LlV11OYDM-IcctS6T9ZnanZM_Pz8jRjnfgOZn1KZJf--7p0PslbX1SX7MnhKWabne7KHJSOko2EYgudBRPN9Kh2Rg6WETUomZe09QYMx4ZSlnqkOl4NB08Z22bhMwh29hk4MBFoyzOrKscKM6ctRyUtwj-3inLREDVoArPvasNIjyyBgOBSwBbGHZB9ueLub8klBluPBjmggIuDAcrlKrqnDtgJq-gS-63AdPLxgxDJxGRg27iq2N8dRvfLnmKQf1-NTpZpweYX93mV_-V3y7pxJTsjAelYALn0tvmSLe_3Vqz6G9XRJV19R9jX5PDuJ5mx6VH9jerD39DDtzn5m29uk1f3Be0k9WY priority: 102 providerName: Directory of Open Access Journals
Title	A Double Deep Learning-Based Solution for Efficient Event Data Coding and Classification
URI	https://ieeexplore.ieee.org/document/10925359 https://www.proquest.com/docview/3179912174 https://doaj.org/article/57d705ba332e49948127deff87f2f882
Volume	13
WOSCitedRecordID	wos001449680800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB3RigMcKB9FXVoqHziSksR27Dlut1txoeLQw94s2xkjJLRbtVuO_HbGjrcqQhy4RFHkKI5f7Jk38bwB-IAGUx9N10QbTaOGQLwOtjnBJ-lODj50MpZiE-bqyq5W-LUmq5dcGCIqm8_oLJ-Wf_njJt7nUBnPcOy11LgHe8YMU7LWQ0AlV5BAbaqyEDf9NF8s-CWYA_b6jM0qEx35h_UpIv21qspfS3GxL5cH_9mzl_CiOpJiPiH_Cp7Q-jU8fyQv-AZWc8H-cfhB4oLoRlQp1W_NOVuuUewCYoLdVrEsShL8DLHMGyDFhd96sdhkwyb8ehSldmbeVVSAPITry-X14nNTKyk0kR2SbYMRY9bSUjLEIaJVMoag0FJg_4CiDVInJha2I0Vx9OwEsGPhMSmDGDov38L-erOmIxDSK0_oZUwWlfYKg7Z2GFsVUfp2wBl83A2wu5n0MlzhGS26CQ-X8XAVjxmcZxAemmax63KBR9fVueO0GU2rg5eyJyZo3M3ejJSSNalPzBBmcJgRefS8CYwZnOwwdXVm3jmZJfC6TMTe_eO2Y3iWuzjFWU5gf3t7T-_hafy5_X53e1pIOx-__Fqelg_wN_tF1d8
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB1BQQIOfBZ1oYAPHElJYjv2HLfbrYooKw572JtlOxOEhHardsvv79jxVkWIA7cocmTHL_bMm3jeAHxEg0MbTVNFG02lukC8D9YpwWfQjex8aGTMxSbMYmFXK_xektVzLgwR5cNndJQu87_8fhOvU6iMVzi2Wmq8Dw9S6aySrnUbUkk1JFCboi3EjT9PZzN-DWaBrT5iw8pUR_5hf7JMf6mr8tdmnC3M6bP_HNtzeFpcSTEdsX8B92j9Ep7cERh8BaupYA85_CJxQnQhipjqj-qYbVcvdiExwY6rmGctCe5DzNMRSHHit17MNsm0Cb_uRa6emc4VZSj3YXk6X87OqlJLoYrskmwrjBiTmpaSIXYRrZIxBIWWAnsIFG2QemBqYRtSFHvPbgC7Fh4HZRBD4-Vr2Ftv1nQAQnrlCb2Mg0WlvcKgre36WkWUvu5wAp92E-wuRsUMl5lGjW7EwyU8XMFjAscJhNumSe463-DZdWX1OG16U-vgpWyJKRoPszU9DYM1QzswR5jAfkLkTn8jGBM43GHqytq8cjKJ4DWJir35x2Mf4NHZ8tu5O_-y-PoWHqfhjlGXQ9jbXl7TO3gYf29_Xl2-zx_gDTMi1wI
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Double+Deep+Learning-Based+Solution+for+Efficient+Event+Data+Coding+and+Classification&rft.jtitle=IEEE+access&rft.au=Seleem%2C+Abdelrahman&rft.au=Guarda%2C+Andre+F.+R.&rft.au=Rodrigues%2C+Nuno+M.+M.&rft.au=Pereira%2C+Fernando&rft.date=2025-01-01&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=13&rft.spage=48703&rft.epage=48719&rft_id=info:doi/10.1109%2FACCESS.2025.3551073&rft.externalDocID=10925359
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon