People Detection under Occlusion in Multiple Camera Views
This paper proposes a method to locate people on a reference plane using multiple cameras. Previous works rely on people trajectories and color models to solve occlusion.This new approach solves people detection under occlusion by accumulating evidence from multiple views instantaneously and does no...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Tagungsbericht |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 60 |
---|---|
container_issue | |
container_start_page | 53 |
container_title | |
container_volume | |
creator | Santos, T.T. Morimoto, C.H. |
description | This paper proposes a method to locate people on a reference plane using multiple cameras. Previous works rely on people trajectories and color models to solve occlusion.This new approach solves people detection under occlusion by accumulating evidence from multiple views instantaneously and does not rely on previous segmentation of individuals in foreground data or any tracking information.First, foreground data from one view, segmented using background subtraction, is projected onto the ground plane or reference image. The projected foreground of a second view overlaps the first projected foreground only on the points where the foreground intersects the ground plane.Thus, by accumulating the evidence from multiple views,people can be located by detecting local maxima on the accumulated reference image. Experimental results using publicly available data from PETSpsila06 [9] show that the method robustly locates people in very challenging situations with occlusion in most of the views. The locations on the ground plane can further be used for segmentation and tracking on each camera view under severe occlusion. |
doi_str_mv | 10.1109/SIBGRAPI.2008.25 |
format | Conference Proceeding |
fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4654143</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4654143</ieee_id><sourcerecordid>4654143</sourcerecordid><originalsourceid>FETCH-LOGICAL-i217t-826daf8a3bf5237f75723647da07095d662f471df2bc9ba42312c5e5defe3a9f3</originalsourceid><addsrcrecordid>eNotj8lqwzAURUUHqJN2X-jGP2BH0tO4TN00MaQkdNoG2XoCFccJHij9-ya0q8uFw-VcQu4ZzRmjdvZWPi5f59sy55SanMsLknDQOpOCqUsyoVpZCSANvyIJk0AzZkDckEnff1HKrFUmIXaLh2OD6RMOWA_x0KZj67FLN3XdjP25xzZ9GZshnqnC7bFz6WfE7_6WXAfX9Hj3n1Py8bx4L1bZerMsi_k6i5zpITNceReMgyrIk13QUnNQQntHNbXSK8WD0MwHXtW2coID47VE6TEgOBtgSh7-diMi7o5d3LvuZyfU6aUA-AXR1Ugu</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>People Detection under Occlusion in Multiple Camera Views</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Santos, T.T. ; Morimoto, C.H.</creator><creatorcontrib>Santos, T.T. ; Morimoto, C.H.</creatorcontrib><description>This paper proposes a method to locate people on a reference plane using multiple cameras. Previous works rely on people trajectories and color models to solve occlusion.This new approach solves people detection under occlusion by accumulating evidence from multiple views instantaneously and does not rely on previous segmentation of individuals in foreground data or any tracking information.First, foreground data from one view, segmented using background subtraction, is projected onto the ground plane or reference image. The projected foreground of a second view overlaps the first projected foreground only on the points where the foreground intersects the ground plane.Thus, by accumulating the evidence from multiple views,people can be located by detecting local maxima on the accumulated reference image. Experimental results using publicly available data from PETSpsila06 [9] show that the method robustly locates people in very challenging situations with occlusion in most of the views. The locations on the ground plane can further be used for segmentation and tracking on each camera view under severe occlusion.</description><identifier>ISSN: 1530-1834</identifier><identifier>ISBN: 0769533582</identifier><identifier>ISBN: 9780769533582</identifier><identifier>EISSN: 2377-5416</identifier><identifier>DOI: 10.1109/SIBGRAPI.2008.25</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Classification algorithms ; Computational modeling ; detection ; Floors ; Image color analysis ; Image segmentation ; multiple view ; Pixel ; surveillance ; video analysis</subject><ispartof>2008 XXI Brazilian Symposium on Computer Graphics and Image Processing, 2008, p.53-60</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4654143$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4654143$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Santos, T.T.</creatorcontrib><creatorcontrib>Morimoto, C.H.</creatorcontrib><title>People Detection under Occlusion in Multiple Camera Views</title><title>2008 XXI Brazilian Symposium on Computer Graphics and Image Processing</title><addtitle>SIBGRA</addtitle><description>This paper proposes a method to locate people on a reference plane using multiple cameras. Previous works rely on people trajectories and color models to solve occlusion.This new approach solves people detection under occlusion by accumulating evidence from multiple views instantaneously and does not rely on previous segmentation of individuals in foreground data or any tracking information.First, foreground data from one view, segmented using background subtraction, is projected onto the ground plane or reference image. The projected foreground of a second view overlaps the first projected foreground only on the points where the foreground intersects the ground plane.Thus, by accumulating the evidence from multiple views,people can be located by detecting local maxima on the accumulated reference image. Experimental results using publicly available data from PETSpsila06 [9] show that the method robustly locates people in very challenging situations with occlusion in most of the views. The locations on the ground plane can further be used for segmentation and tracking on each camera view under severe occlusion.</description><subject>Cameras</subject><subject>Classification algorithms</subject><subject>Computational modeling</subject><subject>detection</subject><subject>Floors</subject><subject>Image color analysis</subject><subject>Image segmentation</subject><subject>multiple view</subject><subject>Pixel</subject><subject>surveillance</subject><subject>video analysis</subject><issn>1530-1834</issn><issn>2377-5416</issn><isbn>0769533582</isbn><isbn>9780769533582</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj8lqwzAURUUHqJN2X-jGP2BH0tO4TN00MaQkdNoG2XoCFccJHij9-ya0q8uFw-VcQu4ZzRmjdvZWPi5f59sy55SanMsLknDQOpOCqUsyoVpZCSANvyIJk0AzZkDckEnff1HKrFUmIXaLh2OD6RMOWA_x0KZj67FLN3XdjP25xzZ9GZshnqnC7bFz6WfE7_6WXAfX9Hj3n1Py8bx4L1bZerMsi_k6i5zpITNceReMgyrIk13QUnNQQntHNbXSK8WD0MwHXtW2coID47VE6TEgOBtgSh7-diMi7o5d3LvuZyfU6aUA-AXR1Ugu</recordid><startdate>200810</startdate><enddate>200810</enddate><creator>Santos, T.T.</creator><creator>Morimoto, C.H.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200810</creationdate><title>People Detection under Occlusion in Multiple Camera Views</title><author>Santos, T.T. ; Morimoto, C.H.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i217t-826daf8a3bf5237f75723647da07095d662f471df2bc9ba42312c5e5defe3a9f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Cameras</topic><topic>Classification algorithms</topic><topic>Computational modeling</topic><topic>detection</topic><topic>Floors</topic><topic>Image color analysis</topic><topic>Image segmentation</topic><topic>multiple view</topic><topic>Pixel</topic><topic>surveillance</topic><topic>video analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Santos, T.T.</creatorcontrib><creatorcontrib>Morimoto, C.H.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Santos, T.T.</au><au>Morimoto, C.H.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>People Detection under Occlusion in Multiple Camera Views</atitle><btitle>2008 XXI Brazilian Symposium on Computer Graphics and Image Processing</btitle><stitle>SIBGRA</stitle><date>2008-10</date><risdate>2008</risdate><spage>53</spage><epage>60</epage><pages>53-60</pages><issn>1530-1834</issn><eissn>2377-5416</eissn><isbn>0769533582</isbn><isbn>9780769533582</isbn><abstract>This paper proposes a method to locate people on a reference plane using multiple cameras. Previous works rely on people trajectories and color models to solve occlusion.This new approach solves people detection under occlusion by accumulating evidence from multiple views instantaneously and does not rely on previous segmentation of individuals in foreground data or any tracking information.First, foreground data from one view, segmented using background subtraction, is projected onto the ground plane or reference image. The projected foreground of a second view overlaps the first projected foreground only on the points where the foreground intersects the ground plane.Thus, by accumulating the evidence from multiple views,people can be located by detecting local maxima on the accumulated reference image. Experimental results using publicly available data from PETSpsila06 [9] show that the method robustly locates people in very challenging situations with occlusion in most of the views. The locations on the ground plane can further be used for segmentation and tracking on each camera view under severe occlusion.</abstract><pub>IEEE</pub><doi>10.1109/SIBGRAPI.2008.25</doi><tpages>8</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1530-1834 |
ispartof | 2008 XXI Brazilian Symposium on Computer Graphics and Image Processing, 2008, p.53-60 |
issn | 1530-1834 2377-5416 |
language | eng |
recordid | cdi_ieee_primary_4654143 |
source | IEEE Electronic Library (IEL) Conference Proceedings |
subjects | Cameras Classification algorithms Computational modeling detection Floors Image color analysis Image segmentation multiple view Pixel surveillance video analysis |
title | People Detection under Occlusion in Multiple Camera Views |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A27%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=People%20Detection%20under%20Occlusion%20in%20Multiple%20Camera%20Views&rft.btitle=2008%20XXI%20Brazilian%20Symposium%20on%20Computer%20Graphics%20and%20Image%20Processing&rft.au=Santos,%20T.T.&rft.date=2008-10&rft.spage=53&rft.epage=60&rft.pages=53-60&rft.issn=1530-1834&rft.eissn=2377-5416&rft.isbn=0769533582&rft.isbn_list=9780769533582&rft_id=info:doi/10.1109/SIBGRAPI.2008.25&rft_dat=%3Cieee_6IE%3E4654143%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4654143&rfr_iscdi=true |