Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPBW34M/3C9KEBE
Repositorysid.inpe.br/sibgrapi/2012/07.13.19.41
Last Update2012:07.13.19.41.16 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2012/07.13.19.41.16
Metadata Last Update2022:06.14.00.07.32 (UTC) administrator
DOI10.1109/SIBGRAPI.2012.31
Citation KeyFührJung:2012:RoPaPe
TitleRobust patch-based pedestrian tracking using monocular calibrated cameras
FormatDVD, On-line.
Year2012
Access Date2024, Apr. 28
Number of Files1
Size3592 KiB
2. Context
Author1 Führ, Gustavo
2 Jung, Cláudio Rosito
Affiliation1 Universidade Federal do Rio Grande do Sul
2 Universidade Federal do Rio Grande do Sul
EditorFreitas, Carla Maria Dal Sasso
Sarkar, Sudeep
Scopigno, Roberto
Silva, Luciano
e-Mail Addressgfuhr@inf.ufrgs.br
Conference NameConference on Graphics, Patterns and Images, 25 (SIBGRAPI)
Conference LocationOuro Preto, MG, Brazil
Date22-25 Aug. 2012
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2012-09-20 16:45:34 :: gfuhr@inf.ufrgs.br -> administrator :: 2012
2022-03-08 21:03:24 :: administrator -> menottid@gmail.com :: 2012
2022-03-10 12:54:14 :: menottid@gmail.com -> administrator :: 2012
2022-03-10 18:00:16 :: administrator -> banon :: 2012
2022-03-10 18:03:24 :: banon -> administrator :: 2012
2022-06-14 00:07:32 :: administrator -> :: 2012
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordspatch-based tracking
wvmf
homography
pedestrian tracking
AbstractAlthough several methods for pedestrian tracking can be found in the literature, robustly tracking a person in unconstrained environments is an open and active research problem. In this paper, we propose a method that represents each pedestrian as a set of multiple fragments, aiming robustness with respect to occlusions. These patches are tracked individually and their translation vectors are combined robustly in the world coordinate frame using Weighted Vector Median Filters (WVMF). Additionally, the algorithm uses the camera parameters to both estimate the person scale in a straightforward manner and to limit the search region used to track each fragment. Experiments carried out using two publicly available datasets (PETS and TownCentre) are presented, and they indicate that the proposed method is robust to partial occlusions and large scale changes. According to our experiments, the proposed approach outperforms, regarding the quality of localization, some of the methods in the current state of the art.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2012 > Robust patch-based pedestrian...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Robust patch-based pedestrian...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 13/07/2012 16:41 0.7 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPBW34M/3C9KEBE
zipped data URLhttp://urlib.net/zip/8JMKD3MGPBW34M/3C9KEBE
Languageen
Target Filesibgrapi2012_revision_v3.pdf
User Groupgfuhr@inf.ufrgs.br
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/46SL8GS
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2022/05.15.03.31 4
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume


Close