Moving object detection in omnidirectional vision-based mobile robot
Detecting moving objects based on the camera attached in mobile robot is not trivial since both background and object are moving independently. For moving object detection the movement of moving object needs to be extracted by considering the background which has also changed by the ego-motion of mo...
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 | 4235 |
---|---|
container_issue | |
container_start_page | 4232 |
container_title | |
container_volume | |
creator | Chi-Min Oh Yong-Cheol Lee Dae-Young Kim Chil-Woo Lee |
description | Detecting moving objects based on the camera attached in mobile robot is not trivial since both background and object are moving independently. For moving object detection the movement of moving object needs to be extracted by considering the background which has also changed by the ego-motion of mobile robot. Affine transformation is widely used to estimate the background transformation between images. However when using omnidirectional camera, the mixed motion of scaling, rotation and translation appears in local areas and single affine transformation is not sufficient to describe those mixed nonlinear motions. In this paper, the proposed method divides the image as grid windows and obtains each affine transform for each window. This method can obtain stable background transformation when the background has few corner features. The area of moving objects can be obtained from the background transformation-compensated frame difference using every local affine transformation for each local window. The experimental results demonstrate the proposed method is very efficient in moving object detection in mobile robot environment. |
doi_str_mv | 10.1109/IECON.2012.6389210 |
format | Conference Proceeding |
fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6389210</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6389210</ieee_id><sourcerecordid>6389210</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-f3e7abc318c548707dad0c768b433c09ce0ded0bc27e269a8fbb7e7a4f5e17f23</originalsourceid><addsrcrecordid>eNotkE9Lw0AUxFdUsNZ8Ab3sF0h8bzfJZo8SqxaqvSh4K_vnRbYkWUlCwW9voDn9ZgZmDsPYPUKGCPpxu6n3H5kAFFkpKy0QLtgt5qWSIhcoL1miVbV41PqKrbAoZFoo8X3DknE8AgCiyGUJK_b8Hk-h_-HRHslN3NM0I8Seh57Hrg8-DOfAtPwUxlmk1ozkeRdtaIkP0cbpjl03ph0pWbhmXy-bz_ot3e1ft_XTLg2oiiltJCljncTKFXmlQHnjwamysrmUDrQj8OTBOqFIlNpUjbVqruRNQagaIdfs4bwbiOjwO4TODH-H5QT5DyU6T3I</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Moving object detection in omnidirectional vision-based mobile robot</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Chi-Min Oh ; Yong-Cheol Lee ; Dae-Young Kim ; Chil-Woo Lee</creator><creatorcontrib>Chi-Min Oh ; Yong-Cheol Lee ; Dae-Young Kim ; Chil-Woo Lee</creatorcontrib><description>Detecting moving objects based on the camera attached in mobile robot is not trivial since both background and object are moving independently. For moving object detection the movement of moving object needs to be extracted by considering the background which has also changed by the ego-motion of mobile robot. Affine transformation is widely used to estimate the background transformation between images. However when using omnidirectional camera, the mixed motion of scaling, rotation and translation appears in local areas and single affine transformation is not sufficient to describe those mixed nonlinear motions. In this paper, the proposed method divides the image as grid windows and obtains each affine transform for each window. This method can obtain stable background transformation when the background has few corner features. The area of moving objects can be obtained from the background transformation-compensated frame difference using every local affine transformation for each local window. The experimental results demonstrate the proposed method is very efficient in moving object detection in mobile robot environment.</description><identifier>ISSN: 1553-572X</identifier><identifier>ISBN: 9781467324199</identifier><identifier>ISBN: 1467324191</identifier><identifier>EISBN: 1467324213</identifier><identifier>EISBN: 9781467324205</identifier><identifier>EISBN: 9781467324212</identifier><identifier>EISBN: 1467324205</identifier><identifier>DOI: 10.1109/IECON.2012.6389210</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Compensated frame difference ; Computers ; Feature extraction ; Mobile Robot ; Moving Object Detection ; Omnidirectional Vision ; Transforms</subject><ispartof>IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society, 2012, p.4232-4235</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/6389210$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6389210$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chi-Min Oh</creatorcontrib><creatorcontrib>Yong-Cheol Lee</creatorcontrib><creatorcontrib>Dae-Young Kim</creatorcontrib><creatorcontrib>Chil-Woo Lee</creatorcontrib><title>Moving object detection in omnidirectional vision-based mobile robot</title><title>IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society</title><addtitle>IECON</addtitle><description>Detecting moving objects based on the camera attached in mobile robot is not trivial since both background and object are moving independently. For moving object detection the movement of moving object needs to be extracted by considering the background which has also changed by the ego-motion of mobile robot. Affine transformation is widely used to estimate the background transformation between images. However when using omnidirectional camera, the mixed motion of scaling, rotation and translation appears in local areas and single affine transformation is not sufficient to describe those mixed nonlinear motions. In this paper, the proposed method divides the image as grid windows and obtains each affine transform for each window. This method can obtain stable background transformation when the background has few corner features. The area of moving objects can be obtained from the background transformation-compensated frame difference using every local affine transformation for each local window. The experimental results demonstrate the proposed method is very efficient in moving object detection in mobile robot environment.</description><subject>Cameras</subject><subject>Compensated frame difference</subject><subject>Computers</subject><subject>Feature extraction</subject><subject>Mobile Robot</subject><subject>Moving Object Detection</subject><subject>Omnidirectional Vision</subject><subject>Transforms</subject><issn>1553-572X</issn><isbn>9781467324199</isbn><isbn>1467324191</isbn><isbn>1467324213</isbn><isbn>9781467324205</isbn><isbn>9781467324212</isbn><isbn>1467324205</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotkE9Lw0AUxFdUsNZ8Ab3sF0h8bzfJZo8SqxaqvSh4K_vnRbYkWUlCwW9voDn9ZgZmDsPYPUKGCPpxu6n3H5kAFFkpKy0QLtgt5qWSIhcoL1miVbV41PqKrbAoZFoo8X3DknE8AgCiyGUJK_b8Hk-h_-HRHslN3NM0I8Seh57Hrg8-DOfAtPwUxlmk1ozkeRdtaIkP0cbpjl03ph0pWbhmXy-bz_ot3e1ft_XTLg2oiiltJCljncTKFXmlQHnjwamysrmUDrQj8OTBOqFIlNpUjbVqruRNQagaIdfs4bwbiOjwO4TODH-H5QT5DyU6T3I</recordid><startdate>201210</startdate><enddate>201210</enddate><creator>Chi-Min Oh</creator><creator>Yong-Cheol Lee</creator><creator>Dae-Young Kim</creator><creator>Chil-Woo Lee</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201210</creationdate><title>Moving object detection in omnidirectional vision-based mobile robot</title><author>Chi-Min Oh ; Yong-Cheol Lee ; Dae-Young Kim ; Chil-Woo Lee</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-f3e7abc318c548707dad0c768b433c09ce0ded0bc27e269a8fbb7e7a4f5e17f23</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Cameras</topic><topic>Compensated frame difference</topic><topic>Computers</topic><topic>Feature extraction</topic><topic>Mobile Robot</topic><topic>Moving Object Detection</topic><topic>Omnidirectional Vision</topic><topic>Transforms</topic><toplevel>online_resources</toplevel><creatorcontrib>Chi-Min Oh</creatorcontrib><creatorcontrib>Yong-Cheol Lee</creatorcontrib><creatorcontrib>Dae-Young Kim</creatorcontrib><creatorcontrib>Chil-Woo Lee</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chi-Min Oh</au><au>Yong-Cheol Lee</au><au>Dae-Young Kim</au><au>Chil-Woo Lee</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Moving object detection in omnidirectional vision-based mobile robot</atitle><btitle>IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society</btitle><stitle>IECON</stitle><date>2012-10</date><risdate>2012</risdate><spage>4232</spage><epage>4235</epage><pages>4232-4235</pages><issn>1553-572X</issn><isbn>9781467324199</isbn><isbn>1467324191</isbn><eisbn>1467324213</eisbn><eisbn>9781467324205</eisbn><eisbn>9781467324212</eisbn><eisbn>1467324205</eisbn><abstract>Detecting moving objects based on the camera attached in mobile robot is not trivial since both background and object are moving independently. For moving object detection the movement of moving object needs to be extracted by considering the background which has also changed by the ego-motion of mobile robot. Affine transformation is widely used to estimate the background transformation between images. However when using omnidirectional camera, the mixed motion of scaling, rotation and translation appears in local areas and single affine transformation is not sufficient to describe those mixed nonlinear motions. In this paper, the proposed method divides the image as grid windows and obtains each affine transform for each window. This method can obtain stable background transformation when the background has few corner features. The area of moving objects can be obtained from the background transformation-compensated frame difference using every local affine transformation for each local window. The experimental results demonstrate the proposed method is very efficient in moving object detection in mobile robot environment.</abstract><pub>IEEE</pub><doi>10.1109/IECON.2012.6389210</doi><tpages>4</tpages></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1553-572X |
ispartof | IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society, 2012, p.4232-4235 |
issn | 1553-572X |
language | eng |
recordid | cdi_ieee_primary_6389210 |
source | IEEE Electronic Library (IEL) Conference Proceedings |
subjects | Cameras Compensated frame difference Computers Feature extraction Mobile Robot Moving Object Detection Omnidirectional Vision Transforms |
title | Moving object detection in omnidirectional vision-based mobile robot |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T09%3A46%3A38IST&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=Moving%20object%20detection%20in%20omnidirectional%20vision-based%20mobile%20robot&rft.btitle=IECON%202012%20-%2038th%20Annual%20Conference%20on%20IEEE%20Industrial%20Electronics%20Society&rft.au=Chi-Min%20Oh&rft.date=2012-10&rft.spage=4232&rft.epage=4235&rft.pages=4232-4235&rft.issn=1553-572X&rft.isbn=9781467324199&rft.isbn_list=1467324191&rft_id=info:doi/10.1109/IECON.2012.6389210&rft_dat=%3Cieee_6IE%3E6389210%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1467324213&rft.eisbn_list=9781467324205&rft.eisbn_list=9781467324212&rft.eisbn_list=1467324205&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6389210&rfr_iscdi=true |