Close
Metadata

Reference TypeConference Proceedings
Identifier8JMKD3MGPEW34M/438DG35
Repositorysid.inpe.br/sibgrapi/2020/09.11.16.08
Metadatasid.inpe.br/sibgrapi/2020/09.11.16.08.08
Sitesibgrapi.sid.inpe.br
Citation KeySantosPireColoPapa:2020:ScChDe
Author1 Santos, Daniel Felipe Silva
2 Pires, Rafael Gonçalves
3 Colombo, Danilo
4 Papa, João Paulo
Affiliation1 São Paulo State University (UNESP)
2 São Paulo State University (UNESP)
3 PETROBRAS - BR
4 São Paulo State University (UNESP)
TitleScene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
Conference NameConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Year2020
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
Book TitleProceedings
DateNov. 7-10, 2020
Publisher CityLos Alamitos
PublisherIEEE Computer Society
Conference LocationVirtual
Keywordschange, detection, learning, multiscale.
AbstractScene change detection is an image processing problem related to partitioning pixels of a digital image into foreground and background regions. Mostly, visual knowledge-based computer intelligent systems, like traffic monitoring, video surveillance, and anomaly detection, need to use change detection techniques. Amongst the most prominent detection methods, there are the learning-based ones, which besides sharing similar training and testing protocols, differ from each other in terms of their architecture design strategies. Such architecture design directly impacts on the quality of the detection results, and also in the device resources capacity, like memory. In this work, we propose a novel Multiscale Cascade Residual Convolutional Neural Network that integrates multiscale processing strategy through a Residual Processing Module, with a Segmentation Convolutional Neural Network. Experiments conducted on two different datasets support the effectiveness of the proposed approach, achieving average overall F -measure results of 0.9622 and 0.9664 over Change Detection 2014 and PetrobrasROUTES datasets respectively, besides comprising approximately eight times fewer parameters. Such obtained results place the proposed technique amongst the top four state-of-the-art scene change detection methods.
Languageen
Tertiary TypeFull Paper
FormatOn-line
Size1872 KiB
Number of Files1
Target File71.pdf
Last Update2020:10.01.14.27.23 sid.inpe.br/banon/2001/03.30.15.38 danielfssantos1@gmail.com
Metadata Last Update2020:10.01.14.27.23 sid.inpe.br/banon/2001/03.30.15.38 danielfssantos1@gmail.com {D 2020}
Document Stagecompleted
Is the master or a copy?is the master
Mirrorsid.inpe.br/banon/2001/03.30.15.38.24
e-Mail Addressdanielfssantos1@gmail.com
e-Mail (login)danielfssantos1@gmail.com
User Groupdanielfssantos1@gmail.com
Visibilityshown
Transferable1
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Content TypeExternal Contribution
Document Stagenot transferred
source Directory Content
71.pdf 28/09/2020 13:13 1.8 MiB
agreement Directory Content
agreement.html 11/09/2020 13:08 1.2 KiB 
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition nexthigherunit notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume
Access Date2020, Oct. 24
update 

Close