Towards multi-cue urban curb recognition

This paper presents a multi-cue approach to curb recognition in urban traffic. We propose a novel texture-based curb classifier using local receptive field (LRF) features in conjunction with a multi-layer neural network. This classification module operates on both intensity images and on three-dimen...

Full description

Saved in:
Bibliographic Details
Main Authors: Enzweiler, Markus, Greiner, Pierre, Knoppel, Carsten, Franke, Uwe
Format: Conference Proceeding
Language:English
Subjects:
Cameras
Image edge detection
Kalman filters
Roads
Sensors
Support vector machines
Three-dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 907
container_issue
container_start_page 902
container_title
container_volume
creator Enzweiler, Markus
Greiner, Pierre
Knoppel, Carsten
Franke, Uwe
description This paper presents a multi-cue approach to curb recognition in urban traffic. We propose a novel texture-based curb classifier using local receptive field (LRF) features in conjunction with a multi-layer neural network. This classification module operates on both intensity images and on three-dimensional height profile data derived from stereo vision. We integrate the proposed multi-cue curb classifier as an additional measurement module into a state-of-the-art Kaiman filter-based urban lane recognition system. Our experiments involve a challenging real-world dataset captured in urban traffic with manually labeled ground-truth. We quantify the benefit of the proposed multi-cue curb classifier in terms of the improvement in curb localization accuracy of the integrated system. Our results indicate a 25% reduction of the average curb localization error at real-time processing speeds.
doi_str_mv 10.1109/IVS.2013.6629581
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_6629581</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6629581</ieee_id><sourcerecordid>6629581</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-168b0bb89733e7d6b07f418430a60dbb02b5dfe7d091b522347d3f3794ad2ae3</originalsourceid><addsrcrecordid>eNotjztLxEAURkdRMLvaCzYpbSbeO3eepSw-FhYsDLbLTGYiI7uJ5IH47w241Sk-OHyHsVuEChHcw_bjvRKAVGktnLJ4xlYotSFhlHTnrBBaCm4EygtWoCPkoKy5Yqtx_AJQSggs2H3d__ghjuVxPkyZN3Mq5yH4rmwWlENq-s8uT7nvrtll6w9jujlxzernp3rzyndvL9vN445nNGriqG2AEKwzRMlEHcC0Eq0k8BpiCCCCiu2ygMOwXCBpIrVknPRR-ERrdvevzSml_feQj3743Z8C6Q_sGkFI</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Towards multi-cue urban curb recognition</title><source>IEEE Xplore All Conference Series</source><creator>Enzweiler, Markus ; Greiner, Pierre ; Knoppel, Carsten ; Franke, Uwe</creator><creatorcontrib>Enzweiler, Markus ; Greiner, Pierre ; Knoppel, Carsten ; Franke, Uwe</creatorcontrib><description>This paper presents a multi-cue approach to curb recognition in urban traffic. We propose a novel texture-based curb classifier using local receptive field (LRF) features in conjunction with a multi-layer neural network. This classification module operates on both intensity images and on three-dimensional height profile data derived from stereo vision. We integrate the proposed multi-cue curb classifier as an additional measurement module into a state-of-the-art Kaiman filter-based urban lane recognition system. Our experiments involve a challenging real-world dataset captured in urban traffic with manually labeled ground-truth. We quantify the benefit of the proposed multi-cue curb classifier in terms of the improvement in curb localization accuracy of the integrated system. Our results indicate a 25% reduction of the average curb localization error at real-time processing speeds.</description><identifier>ISSN: 1931-0587</identifier><identifier>EISSN: 2642-7214</identifier><identifier>EISBN: 1467327549</identifier><identifier>EISBN: 9781467327541</identifier><identifier>EISBN: 9781467327558</identifier><identifier>EISBN: 1467327557</identifier><identifier>DOI: 10.1109/IVS.2013.6629581</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Image edge detection ; Kalman filters ; Roads ; Sensors ; Support vector machines ; Three-dimensional displays</subject><ispartof>2013 IEEE Intelligent Vehicles Symposium (IV), 2013, p.902-907</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/6629581$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2056,27923,54553,54918,54930</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6629581$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Enzweiler, Markus</creatorcontrib><creatorcontrib>Greiner, Pierre</creatorcontrib><creatorcontrib>Knoppel, Carsten</creatorcontrib><creatorcontrib>Franke, Uwe</creatorcontrib><title>Towards multi-cue urban curb recognition</title><title>2013 IEEE Intelligent Vehicles Symposium (IV)</title><addtitle>IVS</addtitle><description>This paper presents a multi-cue approach to curb recognition in urban traffic. We propose a novel texture-based curb classifier using local receptive field (LRF) features in conjunction with a multi-layer neural network. This classification module operates on both intensity images and on three-dimensional height profile data derived from stereo vision. We integrate the proposed multi-cue curb classifier as an additional measurement module into a state-of-the-art Kaiman filter-based urban lane recognition system. Our experiments involve a challenging real-world dataset captured in urban traffic with manually labeled ground-truth. We quantify the benefit of the proposed multi-cue curb classifier in terms of the improvement in curb localization accuracy of the integrated system. Our results indicate a 25% reduction of the average curb localization error at real-time processing speeds.</description><subject>Cameras</subject><subject>Image edge detection</subject><subject>Kalman filters</subject><subject>Roads</subject><subject>Sensors</subject><subject>Support vector machines</subject><subject>Three-dimensional displays</subject><issn>1931-0587</issn><issn>2642-7214</issn><isbn>1467327549</isbn><isbn>9781467327541</isbn><isbn>9781467327558</isbn><isbn>1467327557</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjztLxEAURkdRMLvaCzYpbSbeO3eepSw-FhYsDLbLTGYiI7uJ5IH47w241Sk-OHyHsVuEChHcw_bjvRKAVGktnLJ4xlYotSFhlHTnrBBaCm4EygtWoCPkoKy5Yqtx_AJQSggs2H3d__ghjuVxPkyZN3Mq5yH4rmwWlENq-s8uT7nvrtll6w9jujlxzernp3rzyndvL9vN445nNGriqG2AEKwzRMlEHcC0Eq0k8BpiCCCCiu2ygMOwXCBpIrVknPRR-ERrdvevzSml_feQj3743Z8C6Q_sGkFI</recordid><startdate>201306</startdate><enddate>201306</enddate><creator>Enzweiler, Markus</creator><creator>Greiner, Pierre</creator><creator>Knoppel, Carsten</creator><creator>Franke, Uwe</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201306</creationdate><title>Towards multi-cue urban curb recognition</title><author>Enzweiler, Markus ; Greiner, Pierre ; Knoppel, Carsten ; Franke, Uwe</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-168b0bb89733e7d6b07f418430a60dbb02b5dfe7d091b522347d3f3794ad2ae3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Cameras</topic><topic>Image edge detection</topic><topic>Kalman filters</topic><topic>Roads</topic><topic>Sensors</topic><topic>Support vector machines</topic><topic>Three-dimensional displays</topic><toplevel>online_resources</toplevel><creatorcontrib>Enzweiler, Markus</creatorcontrib><creatorcontrib>Greiner, Pierre</creatorcontrib><creatorcontrib>Knoppel, Carsten</creatorcontrib><creatorcontrib>Franke, Uwe</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/IET 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>Enzweiler, Markus</au><au>Greiner, Pierre</au><au>Knoppel, Carsten</au><au>Franke, Uwe</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Towards multi-cue urban curb recognition</atitle><btitle>2013 IEEE Intelligent Vehicles Symposium (IV)</btitle><stitle>IVS</stitle><date>2013-06</date><risdate>2013</risdate><spage>902</spage><epage>907</epage><pages>902-907</pages><issn>1931-0587</issn><eissn>2642-7214</eissn><eisbn>1467327549</eisbn><eisbn>9781467327541</eisbn><eisbn>9781467327558</eisbn><eisbn>1467327557</eisbn><abstract>This paper presents a multi-cue approach to curb recognition in urban traffic. We propose a novel texture-based curb classifier using local receptive field (LRF) features in conjunction with a multi-layer neural network. This classification module operates on both intensity images and on three-dimensional height profile data derived from stereo vision. We integrate the proposed multi-cue curb classifier as an additional measurement module into a state-of-the-art Kaiman filter-based urban lane recognition system. Our experiments involve a challenging real-world dataset captured in urban traffic with manually labeled ground-truth. We quantify the benefit of the proposed multi-cue curb classifier in terms of the improvement in curb localization accuracy of the integrated system. Our results indicate a 25% reduction of the average curb localization error at real-time processing speeds.</abstract><pub>IEEE</pub><doi>10.1109/IVS.2013.6629581</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1931-0587
ispartof 2013 IEEE Intelligent Vehicles Symposium (IV), 2013, p.902-907
issn 1931-0587
2642-7214
language eng
recordid cdi_ieee_primary_6629581
source IEEE Xplore All Conference Series
subjects Cameras
Image edge detection
Kalman filters
Roads
Sensors
Support vector machines
Three-dimensional displays
title Towards multi-cue urban curb recognition
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T15%3A58%3A26IST&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=Towards%20multi-cue%20urban%20curb%20recognition&rft.btitle=2013%20IEEE%20Intelligent%20Vehicles%20Symposium%20(IV)&rft.au=Enzweiler,%20Markus&rft.date=2013-06&rft.spage=902&rft.epage=907&rft.pages=902-907&rft.issn=1931-0587&rft.eissn=2642-7214&rft_id=info:doi/10.1109/IVS.2013.6629581&rft.eisbn=1467327549&rft.eisbn_list=9781467327541&rft.eisbn_list=9781467327558&rft.eisbn_list=1467327557&rft_dat=%3Cieee_CHZPO%3E6629581%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-168b0bb89733e7d6b07f418430a60dbb02b5dfe7d091b522347d3f3794ad2ae3%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=6629581&rfr_iscdi=true