Close
Metadata

Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPBW34M/3C92QTP
Repositorysid.inpe.br/sibgrapi/2012/07.10.00.53
Last Update2012:07.10.00.53.06 jose.jgrimaldo@gmail.com
Metadatasid.inpe.br/sibgrapi/2012/07.10.00.53.06
Metadata Last Update2020:02.19.02.18.27 administrator
Citation KeySilvaFoSchnOliv:2012:MuSpRe
TitleMulti-Scale Spectral Residual Analysis to Speed up Image Object Detection
FormatDVD, On-line.
Year2012
Access Date2021, Jan. 27
Number of Files1
Size4541 KiB
Context area
Author1 Silva Filho, José Grimaldo da
2 Schnitman, Leizer
3 Oliveira, Luciano Rebouças de
Affiliation1 Universidade Federal da Bahia
2 Universidade Federal da Bahia
3 Universidade Federal da Bahia
EditorFreitas, Carla Maria Dal Sasso
Sarkar, Sudeep
Scopigno, Roberto
Silva, Luciano
e-Mail Addressjose.jgrimaldo@gmail.com
Conference NameConference on Graphics, Patterns and Images, 25 (SIBGRAPI)
Conference LocationOuro Preto
DateAug. 22-25, 2012
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Tertiary TypeFull Paper
History2012-09-20 16:45:34 :: jose.jgrimaldo@gmail.com -> administrator :: 2012
2020-02-19 02:18:27 :: administrator -> :: 2012
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Keywordsmulti-scale spectral residue, saliency, person detection.
AbstractAccuracy in image object detection has been usually achieved at the expense of much computational load. Therefore a trade-off between detection performance and fast execution commonly represents the ultimate goal of an object detector in real life applications. In this present work, we propose a novel method toward that goal. The proposed method was grounded on a multi-scale spectral residual (MSR) analysis for saliency detection. Compared to a regular sliding window search over the images, in our experiments, MSR was able to reduce by 75% (in average) the number of windows to be evaluated by an object detector. The proposed method was thoroughly evaluated over a subset of LabelMe dataset (person images), improving detection performance in most cases.
source Directory Contentthere are no files
agreement Directory Content
agreement.html 09/07/2012 21:53 0.7 KiB 
Conditions of access and use area
data URLhttp://urlib.net/rep/8JMKD3MGPBW34M/3C92QTP
zipped data URLhttp://urlib.net/zip/8JMKD3MGPBW34M/3C92QTP
Languageen
Target FilePID2440145.pdf
User Groupjose.jgrimaldo@gmail.com
Visibilityshown
Allied materials area
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage 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

Close