3D road curb extraction from image sequence for automobile parking assist system

We extract 3D curb from video sequence, using a single camera equipped with fish-eye lens and located at the front/rear of the vehicle. The challenge in extracting curbs from images lies in their small size and their lack of texture. We show that by appropriately exploiting appearance features, 3D g...

Full description

Saved in:
Bibliographic Details
Main Authors: Prinet, Veronique, JinSong Wang, JongHo Lee, Wettergreen, David
Format: Conference Proceeding
Language:English
Subjects:
Advanced Driving Assist Systems
Cameras
Computer Vision
Feature extraction
Image edge detection
Roads
Support vector machines
Three-dimensional displays
Vehicles
Video Processing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 3851
container_issue
container_start_page 3847
container_title
container_volume
creator Prinet, Veronique
JinSong Wang
JongHo Lee
Wettergreen, David
description We extract 3D curb from video sequence, using a single camera equipped with fish-eye lens and located at the front/rear of the vehicle. The challenge in extracting curbs from images lies in their small size and their lack of texture. We show that by appropriately exploiting appearance features, 3D geometry, and temporal information, one can reliably detect and localize the curbs in the 3D scene. The main underlying assumption of our model is that the road surface is flat and that the curb is approximately orthogonal to the road plane. We collected nine videos with ground truth, under day-time sunny weather condition, up to 2m range. Our experimental results compare favorably wrt the current the state-of-the-art on our database -90% precision rate in average and over 85% accuracy in curb height estimation.
doi_str_mv 10.1109/ICIP.2016.7533080
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_7533080</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7533080</ieee_id><sourcerecordid>7533080</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-1af8ed68eb1e53f43fde144e2b0974cdb0f1e2975bd68ea09ec5f53452210fef3</originalsourceid><addsrcrecordid>eNotkM1KAzEURqMgWGsfQNzkBWbMzc9kspRR60DBLnRdMjM3JdppapIB-_ZW7OpsDoePj5A7YCUAMw9t065LzqAqtRKC1eyCLIyuQVZaGFNBdUlmXNRQ1Eqaa3KT0idjJ1_AjKzFE43BDrSfYkfxJ0fbZx_21MUwUj_aLdKE3xPue6QuRGqnHMbQ-R3Sg41ffr-lNiWfMk3HlHG8JVfO7hIuzpyTj5fn9-a1WL0t2-ZxVXjQKhdgXY1DVWMHqISTwg0IUiLvmNGyHzrmALnRqvuTLDPYK6eEVJwDc-jEnNz_dz0ibg7xNDUeN-cDxC-7mVBa</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>3D road curb extraction from image sequence for automobile parking assist system</title><source>IEEE Xplore All Conference Series</source><creator>Prinet, Veronique ; JinSong Wang ; JongHo Lee ; Wettergreen, David</creator><creatorcontrib>Prinet, Veronique ; JinSong Wang ; JongHo Lee ; Wettergreen, David</creatorcontrib><description>We extract 3D curb from video sequence, using a single camera equipped with fish-eye lens and located at the front/rear of the vehicle. The challenge in extracting curbs from images lies in their small size and their lack of texture. We show that by appropriately exploiting appearance features, 3D geometry, and temporal information, one can reliably detect and localize the curbs in the 3D scene. The main underlying assumption of our model is that the road surface is flat and that the curb is approximately orthogonal to the road plane. We collected nine videos with ground truth, under day-time sunny weather condition, up to 2m range. Our experimental results compare favorably wrt the current the state-of-the-art on our database -90% precision rate in average and over 85% accuracy in curb height estimation.</description><identifier>EISSN: 2381-8549</identifier><identifier>EISBN: 9781467399616</identifier><identifier>EISBN: 1467399612</identifier><identifier>DOI: 10.1109/ICIP.2016.7533080</identifier><language>eng</language><publisher>IEEE</publisher><subject>Advanced Driving Assist Systems ; Cameras ; Computer Vision ; Feature extraction ; Image edge detection ; Roads ; Support vector machines ; Three-dimensional displays ; Vehicles ; Video Processing</subject><ispartof>2016 IEEE International Conference on Image Processing (ICIP), 2016, p.3847-3851</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/7533080$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,27904,54533,54910</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7533080$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Prinet, Veronique</creatorcontrib><creatorcontrib>JinSong Wang</creatorcontrib><creatorcontrib>JongHo Lee</creatorcontrib><creatorcontrib>Wettergreen, David</creatorcontrib><title>3D road curb extraction from image sequence for automobile parking assist system</title><title>2016 IEEE International Conference on Image Processing (ICIP)</title><addtitle>ICIP</addtitle><description>We extract 3D curb from video sequence, using a single camera equipped with fish-eye lens and located at the front/rear of the vehicle. The challenge in extracting curbs from images lies in their small size and their lack of texture. We show that by appropriately exploiting appearance features, 3D geometry, and temporal information, one can reliably detect and localize the curbs in the 3D scene. The main underlying assumption of our model is that the road surface is flat and that the curb is approximately orthogonal to the road plane. We collected nine videos with ground truth, under day-time sunny weather condition, up to 2m range. Our experimental results compare favorably wrt the current the state-of-the-art on our database -90% precision rate in average and over 85% accuracy in curb height estimation.</description><subject>Advanced Driving Assist Systems</subject><subject>Cameras</subject><subject>Computer Vision</subject><subject>Feature extraction</subject><subject>Image edge detection</subject><subject>Roads</subject><subject>Support vector machines</subject><subject>Three-dimensional displays</subject><subject>Vehicles</subject><subject>Video Processing</subject><issn>2381-8549</issn><isbn>9781467399616</isbn><isbn>1467399612</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2016</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotkM1KAzEURqMgWGsfQNzkBWbMzc9kspRR60DBLnRdMjM3JdppapIB-_ZW7OpsDoePj5A7YCUAMw9t065LzqAqtRKC1eyCLIyuQVZaGFNBdUlmXNRQ1Eqaa3KT0idjJ1_AjKzFE43BDrSfYkfxJ0fbZx_21MUwUj_aLdKE3xPue6QuRGqnHMbQ-R3Sg41ffr-lNiWfMk3HlHG8JVfO7hIuzpyTj5fn9-a1WL0t2-ZxVXjQKhdgXY1DVWMHqISTwg0IUiLvmNGyHzrmALnRqvuTLDPYK6eEVJwDc-jEnNz_dz0ibg7xNDUeN-cDxC-7mVBa</recordid><startdate>201609</startdate><enddate>201609</enddate><creator>Prinet, Veronique</creator><creator>JinSong Wang</creator><creator>JongHo Lee</creator><creator>Wettergreen, David</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201609</creationdate><title>3D road curb extraction from image sequence for automobile parking assist system</title><author>Prinet, Veronique ; JinSong Wang ; JongHo Lee ; Wettergreen, David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-1af8ed68eb1e53f43fde144e2b0974cdb0f1e2975bd68ea09ec5f53452210fef3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Advanced Driving Assist Systems</topic><topic>Cameras</topic><topic>Computer Vision</topic><topic>Feature extraction</topic><topic>Image edge detection</topic><topic>Roads</topic><topic>Support vector machines</topic><topic>Three-dimensional displays</topic><topic>Vehicles</topic><topic>Video Processing</topic><toplevel>online_resources</toplevel><creatorcontrib>Prinet, Veronique</creatorcontrib><creatorcontrib>JinSong Wang</creatorcontrib><creatorcontrib>JongHo Lee</creatorcontrib><creatorcontrib>Wettergreen, David</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 (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Prinet, Veronique</au><au>JinSong Wang</au><au>JongHo Lee</au><au>Wettergreen, David</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>3D road curb extraction from image sequence for automobile parking assist system</atitle><btitle>2016 IEEE International Conference on Image Processing (ICIP)</btitle><stitle>ICIP</stitle><date>2016-09</date><risdate>2016</risdate><spage>3847</spage><epage>3851</epage><pages>3847-3851</pages><eissn>2381-8549</eissn><eisbn>9781467399616</eisbn><eisbn>1467399612</eisbn><abstract>We extract 3D curb from video sequence, using a single camera equipped with fish-eye lens and located at the front/rear of the vehicle. The challenge in extracting curbs from images lies in their small size and their lack of texture. We show that by appropriately exploiting appearance features, 3D geometry, and temporal information, one can reliably detect and localize the curbs in the 3D scene. The main underlying assumption of our model is that the road surface is flat and that the curb is approximately orthogonal to the road plane. We collected nine videos with ground truth, under day-time sunny weather condition, up to 2m range. Our experimental results compare favorably wrt the current the state-of-the-art on our database -90% precision rate in average and over 85% accuracy in curb height estimation.</abstract><pub>IEEE</pub><doi>10.1109/ICIP.2016.7533080</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2381-8549
ispartof 2016 IEEE International Conference on Image Processing (ICIP), 2016, p.3847-3851
issn 2381-8549
language eng
recordid cdi_ieee_primary_7533080
source IEEE Xplore All Conference Series
subjects Advanced Driving Assist Systems
Cameras
Computer Vision
Feature extraction
Image edge detection
Roads
Support vector machines
Three-dimensional displays
Vehicles
Video Processing
title 3D road curb extraction from image sequence for automobile parking assist system
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T17%3A08%3A58IST&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=3D%20road%20curb%20extraction%20from%20image%20sequence%20for%20automobile%20parking%20assist%20system&rft.btitle=2016%20IEEE%20International%20Conference%20on%20Image%20Processing%20(ICIP)&rft.au=Prinet,%20Veronique&rft.date=2016-09&rft.spage=3847&rft.epage=3851&rft.pages=3847-3851&rft.eissn=2381-8549&rft_id=info:doi/10.1109/ICIP.2016.7533080&rft.eisbn=9781467399616&rft.eisbn_list=1467399612&rft_dat=%3Cieee_CHZPO%3E7533080%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-1af8ed68eb1e53f43fde144e2b0974cdb0f1e2975bd68ea09ec5f53452210fef3%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=7533080&rfr_iscdi=true