Multi-object tracking based on improved Mean Shift

Since Mean Shift algorithm can not track multiple objects, a full automatic multi-object tracking algorithm based on improved Mean Shift is proposed. The background subtraction image kernel density estimation algorithm is used to detect the foreground. The extracted moving objects are used as candid...

Full description

Saved in:
Bibliographic Details
Main Authors: Meifeng Gao, Di Liu
Format: Conference Proceeding
Language:English
Subjects:
Arrays
Histograms
Image color analysis
Kernel
Object tracking
Target tracking
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1592
container_issue
container_start_page 1588
container_title
container_volume
creator Meifeng Gao
Di Liu
description Since Mean Shift algorithm can not track multiple objects, a full automatic multi-object tracking algorithm based on improved Mean Shift is proposed. The background subtraction image kernel density estimation algorithm is used to detect the foreground. The extracted moving objects are used as candidate template to eliminate the influence of background. By adopting object matching based on distance matrix, new objects entering to the scene and occlusion-split between objects could be handled. The tracking accuracy is increased by using shadow removal and morphology processing. The experiment results show that the proposed method can achieve multiple-object tracking accurately, and deal with the occlusion-split between objects very well.
doi_str_mv 10.1109/ICIST.2013.6747840
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_6747840</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6747840</ieee_id><sourcerecordid>6747840</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-6c41aa81e09fe1edc50cbd6690538307eec92c1faa0e4a92c9104fd3445385613</originalsourceid><addsrcrecordid>eNotj8FKw0AURUesYK39Ad3kBxLfy7yZySwlaA20dNG6LpPJi05tk5JEwb83YFb3XA5cuEI8ICSIYJ-KvNjtkxRQJtqQyQiuxB2SNjI1mvT1VBRKY2ZinqKmmKQyt2LZ90cAkJhlltRcpJvv0xDitjyyH6Khc_4rNB9R6XquoraJwvnStT8jb9g10e4z1MO9uKndqefllAvx_vqyz9_i9XZV5M_rOKBRQ6w9oXMZMtiakSuvwJeV1haUzCQYZm9Tj7VzwORGtAhUV5Jo9EqjXIjH_93AzIdLF86u-z1Mf-Ufpo9GUg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Multi-object tracking based on improved Mean Shift</title><source>IEEE Xplore All Conference Series</source><creator>Meifeng Gao ; Di Liu</creator><creatorcontrib>Meifeng Gao ; Di Liu</creatorcontrib><description>Since Mean Shift algorithm can not track multiple objects, a full automatic multi-object tracking algorithm based on improved Mean Shift is proposed. The background subtraction image kernel density estimation algorithm is used to detect the foreground. The extracted moving objects are used as candidate template to eliminate the influence of background. By adopting object matching based on distance matrix, new objects entering to the scene and occlusion-split between objects could be handled. The tracking accuracy is increased by using shadow removal and morphology processing. The experiment results show that the proposed method can achieve multiple-object tracking accurately, and deal with the occlusion-split between objects very well.</description><identifier>ISSN: 2164-4357</identifier><identifier>ISBN: 1467351377</identifier><identifier>ISBN: 9781467351379</identifier><identifier>EISBN: 1467327646</identifier><identifier>EISBN: 9781467327640</identifier><identifier>EISBN: 1467327638</identifier><identifier>EISBN: 9781467327633</identifier><identifier>DOI: 10.1109/ICIST.2013.6747840</identifier><language>eng</language><publisher>IEEE</publisher><subject>Arrays ; Histograms ; Image color analysis ; Kernel ; Object tracking ; Target tracking</subject><ispartof>2013 IEEE Third International Conference on Information Science and Technology (ICIST), 2013, p.1588-1592</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6747840$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23928,23929,25138,27923,54553,54930</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6747840$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Meifeng Gao</creatorcontrib><creatorcontrib>Di Liu</creatorcontrib><title>Multi-object tracking based on improved Mean Shift</title><title>2013 IEEE Third International Conference on Information Science and Technology (ICIST)</title><addtitle>ICIST</addtitle><description>Since Mean Shift algorithm can not track multiple objects, a full automatic multi-object tracking algorithm based on improved Mean Shift is proposed. The background subtraction image kernel density estimation algorithm is used to detect the foreground. The extracted moving objects are used as candidate template to eliminate the influence of background. By adopting object matching based on distance matrix, new objects entering to the scene and occlusion-split between objects could be handled. The tracking accuracy is increased by using shadow removal and morphology processing. The experiment results show that the proposed method can achieve multiple-object tracking accurately, and deal with the occlusion-split between objects very well.</description><subject>Arrays</subject><subject>Histograms</subject><subject>Image color analysis</subject><subject>Kernel</subject><subject>Object tracking</subject><subject>Target tracking</subject><issn>2164-4357</issn><isbn>1467351377</isbn><isbn>9781467351379</isbn><isbn>1467327646</isbn><isbn>9781467327640</isbn><isbn>1467327638</isbn><isbn>9781467327633</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8FKw0AURUesYK39Ad3kBxLfy7yZySwlaA20dNG6LpPJi05tk5JEwb83YFb3XA5cuEI8ICSIYJ-KvNjtkxRQJtqQyQiuxB2SNjI1mvT1VBRKY2ZinqKmmKQyt2LZ90cAkJhlltRcpJvv0xDitjyyH6Khc_4rNB9R6XquoraJwvnStT8jb9g10e4z1MO9uKndqefllAvx_vqyz9_i9XZV5M_rOKBRQ6w9oXMZMtiakSuvwJeV1haUzCQYZm9Tj7VzwORGtAhUV5Jo9EqjXIjH_93AzIdLF86u-z1Mf-Ufpo9GUg</recordid><startdate>201303</startdate><enddate>201303</enddate><creator>Meifeng Gao</creator><creator>Di Liu</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201303</creationdate><title>Multi-object tracking based on improved Mean Shift</title><author>Meifeng Gao ; Di Liu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-6c41aa81e09fe1edc50cbd6690538307eec92c1faa0e4a92c9104fd3445385613</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Arrays</topic><topic>Histograms</topic><topic>Image color analysis</topic><topic>Kernel</topic><topic>Object tracking</topic><topic>Target tracking</topic><toplevel>online_resources</toplevel><creatorcontrib>Meifeng Gao</creatorcontrib><creatorcontrib>Di Liu</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 Xplore Digital Library</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>Meifeng Gao</au><au>Di Liu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Multi-object tracking based on improved Mean Shift</atitle><btitle>2013 IEEE Third International Conference on Information Science and Technology (ICIST)</btitle><stitle>ICIST</stitle><date>2013-03</date><risdate>2013</risdate><spage>1588</spage><epage>1592</epage><pages>1588-1592</pages><issn>2164-4357</issn><isbn>1467351377</isbn><isbn>9781467351379</isbn><eisbn>1467327646</eisbn><eisbn>9781467327640</eisbn><eisbn>1467327638</eisbn><eisbn>9781467327633</eisbn><abstract>Since Mean Shift algorithm can not track multiple objects, a full automatic multi-object tracking algorithm based on improved Mean Shift is proposed. The background subtraction image kernel density estimation algorithm is used to detect the foreground. The extracted moving objects are used as candidate template to eliminate the influence of background. By adopting object matching based on distance matrix, new objects entering to the scene and occlusion-split between objects could be handled. The tracking accuracy is increased by using shadow removal and morphology processing. The experiment results show that the proposed method can achieve multiple-object tracking accurately, and deal with the occlusion-split between objects very well.</abstract><pub>IEEE</pub><doi>10.1109/ICIST.2013.6747840</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2164-4357
ispartof 2013 IEEE Third International Conference on Information Science and Technology (ICIST), 2013, p.1588-1592
issn 2164-4357
language eng
recordid cdi_ieee_primary_6747840
source IEEE Xplore All Conference Series
subjects Arrays
Histograms
Image color analysis
Kernel
Object tracking
Target tracking
title Multi-object tracking based on improved Mean Shift
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T10%3A16%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Multi-object%20tracking%20based%20on%20improved%20Mean%20Shift&rft.btitle=2013%20IEEE%20Third%20International%20Conference%20on%20Information%20Science%20and%20Technology%20(ICIST)&rft.au=Meifeng%20Gao&rft.date=2013-03&rft.spage=1588&rft.epage=1592&rft.pages=1588-1592&rft.issn=2164-4357&rft.isbn=1467351377&rft.isbn_list=9781467351379&rft_id=info:doi/10.1109/ICIST.2013.6747840&rft.eisbn=1467327646&rft.eisbn_list=9781467327640&rft.eisbn_list=1467327638&rft.eisbn_list=9781467327633&rft_dat=%3Cieee_CHZPO%3E6747840%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-6c41aa81e09fe1edc50cbd6690538307eec92c1faa0e4a92c9104fd3445385613%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6747840&rfr_iscdi=true