Evaluating Multi-scale Over-segment and Its Contribution to Real Scene Stereo Matching by High-Order MRFs

The paper is to propose a framework to qualitatively and quantitatively evaluate five of state-of-the-art over-segment approaches. Moreover upon over-segments evaluation, an efficient approach is developed for dense stereo matching through robust higher-order MRFs and graph cut based optimization, w...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiran Xie, Rui Cao, Hanyang Tong, Sheng Liu, Nianjun Liu
Format: Conference Proceeding
Language:English
Subjects:
Brightness
Image segmentation
Partitioning algorithms
Pixel
Robustness
Shape
Stereo vision
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 240
container_issue
container_start_page 235
container_title
container_volume
creator Yiran Xie
Rui Cao
Hanyang Tong
Sheng Liu
Nianjun Liu
description The paper is to propose a framework to qualitatively and quantitatively evaluate five of state-of-the-art over-segment approaches. Moreover upon over-segments evaluation, an efficient approach is developed for dense stereo matching through robust higher-order MRFs and graph cut based optimization, which combines the conventional data and smoothness terms with the robust higher-order potential term. The experimental results on real-scene data sets clearly demonstrate that our over-segment-based higher-order stereo matching approach outperforms conventional stereo matching algorithms, as well as how over-segments improve the stereo matching process.
doi_str_mv 10.1109/DICTA.2010.50
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5692570</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5692570</ieee_id><sourcerecordid>5692570</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-1dc5b44bd5d8e39763bfa7178ab203d0e9d3ce90b2d49cf71a748a4846e9a5753</originalsourceid><addsrcrecordid>eNotjEtrAjEYAFNKocV67KmX_IG1eW6So2y1Coqg3iXZfKsp625JsoL_vvYxl2Eug9ALJRNKiXl7X1b76YSRW0tyh8ZGaaJKIwVTlN__NhVMCK1pyR7ROKVPckMyJUr9hMLsYtvB5tAd8XpocyhSbVvAmwvEIsHxDF3GtvN4mROu-i7H4IYc-g7nHm_BtnhXQwd4lyFCj9c216efl7viRTieik30EPF6O0_P6KGxbYLxv0doP5_tq0Wx2nwsq-mqCIbkgvpaOiGcl14DN6rkrrGKKm0dI9wTMJ7XYIhjXpi6UdQqoa3QogRjpZJ8hF7_tgEADl8xnG28HmRpmFSEfwPlvlg5</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Evaluating Multi-scale Over-segment and Its Contribution to Real Scene Stereo Matching by High-Order MRFs</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Yiran Xie ; Rui Cao ; Hanyang Tong ; Sheng Liu ; Nianjun Liu</creator><creatorcontrib>Yiran Xie ; Rui Cao ; Hanyang Tong ; Sheng Liu ; Nianjun Liu</creatorcontrib><description>The paper is to propose a framework to qualitatively and quantitatively evaluate five of state-of-the-art over-segment approaches. Moreover upon over-segments evaluation, an efficient approach is developed for dense stereo matching through robust higher-order MRFs and graph cut based optimization, which combines the conventional data and smoothness terms with the robust higher-order potential term. The experimental results on real-scene data sets clearly demonstrate that our over-segment-based higher-order stereo matching approach outperforms conventional stereo matching algorithms, as well as how over-segments improve the stereo matching process.</description><identifier>ISBN: 9781424488162</identifier><identifier>ISBN: 1424488168</identifier><identifier>EISBN: 9780769542713</identifier><identifier>EISBN: 0769542719</identifier><identifier>DOI: 10.1109/DICTA.2010.50</identifier><language>eng</language><publisher>IEEE</publisher><subject>Brightness ; Image segmentation ; Partitioning algorithms ; Pixel ; Robustness ; Shape ; Stereo vision</subject><ispartof>2010 International Conference on Digital Image Computing: Techniques and Applications, 2010, p.235-240</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/5692570$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5692570$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yiran Xie</creatorcontrib><creatorcontrib>Rui Cao</creatorcontrib><creatorcontrib>Hanyang Tong</creatorcontrib><creatorcontrib>Sheng Liu</creatorcontrib><creatorcontrib>Nianjun Liu</creatorcontrib><title>Evaluating Multi-scale Over-segment and Its Contribution to Real Scene Stereo Matching by High-Order MRFs</title><title>2010 International Conference on Digital Image Computing: Techniques and Applications</title><addtitle>dicta</addtitle><description>The paper is to propose a framework to qualitatively and quantitatively evaluate five of state-of-the-art over-segment approaches. Moreover upon over-segments evaluation, an efficient approach is developed for dense stereo matching through robust higher-order MRFs and graph cut based optimization, which combines the conventional data and smoothness terms with the robust higher-order potential term. The experimental results on real-scene data sets clearly demonstrate that our over-segment-based higher-order stereo matching approach outperforms conventional stereo matching algorithms, as well as how over-segments improve the stereo matching process.</description><subject>Brightness</subject><subject>Image segmentation</subject><subject>Partitioning algorithms</subject><subject>Pixel</subject><subject>Robustness</subject><subject>Shape</subject><subject>Stereo vision</subject><isbn>9781424488162</isbn><isbn>1424488168</isbn><isbn>9780769542713</isbn><isbn>0769542719</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjEtrAjEYAFNKocV67KmX_IG1eW6So2y1Coqg3iXZfKsp625JsoL_vvYxl2Eug9ALJRNKiXl7X1b76YSRW0tyh8ZGaaJKIwVTlN__NhVMCK1pyR7ROKVPckMyJUr9hMLsYtvB5tAd8XpocyhSbVvAmwvEIsHxDF3GtvN4mROu-i7H4IYc-g7nHm_BtnhXQwd4lyFCj9c216efl7viRTieik30EPF6O0_P6KGxbYLxv0doP5_tq0Wx2nwsq-mqCIbkgvpaOiGcl14DN6rkrrGKKm0dI9wTMJ7XYIhjXpi6UdQqoa3QogRjpZJ8hF7_tgEADl8xnG28HmRpmFSEfwPlvlg5</recordid><startdate>201012</startdate><enddate>201012</enddate><creator>Yiran Xie</creator><creator>Rui Cao</creator><creator>Hanyang Tong</creator><creator>Sheng Liu</creator><creator>Nianjun Liu</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201012</creationdate><title>Evaluating Multi-scale Over-segment and Its Contribution to Real Scene Stereo Matching by High-Order MRFs</title><author>Yiran Xie ; Rui Cao ; Hanyang Tong ; Sheng Liu ; Nianjun Liu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-1dc5b44bd5d8e39763bfa7178ab203d0e9d3ce90b2d49cf71a748a4846e9a5753</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Brightness</topic><topic>Image segmentation</topic><topic>Partitioning algorithms</topic><topic>Pixel</topic><topic>Robustness</topic><topic>Shape</topic><topic>Stereo vision</topic><toplevel>online_resources</toplevel><creatorcontrib>Yiran Xie</creatorcontrib><creatorcontrib>Rui Cao</creatorcontrib><creatorcontrib>Hanyang Tong</creatorcontrib><creatorcontrib>Sheng Liu</creatorcontrib><creatorcontrib>Nianjun 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</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>Yiran Xie</au><au>Rui Cao</au><au>Hanyang Tong</au><au>Sheng Liu</au><au>Nianjun Liu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Evaluating Multi-scale Over-segment and Its Contribution to Real Scene Stereo Matching by High-Order MRFs</atitle><btitle>2010 International Conference on Digital Image Computing: Techniques and Applications</btitle><stitle>dicta</stitle><date>2010-12</date><risdate>2010</risdate><spage>235</spage><epage>240</epage><pages>235-240</pages><isbn>9781424488162</isbn><isbn>1424488168</isbn><eisbn>9780769542713</eisbn><eisbn>0769542719</eisbn><abstract>The paper is to propose a framework to qualitatively and quantitatively evaluate five of state-of-the-art over-segment approaches. Moreover upon over-segments evaluation, an efficient approach is developed for dense stereo matching through robust higher-order MRFs and graph cut based optimization, which combines the conventional data and smoothness terms with the robust higher-order potential term. The experimental results on real-scene data sets clearly demonstrate that our over-segment-based higher-order stereo matching approach outperforms conventional stereo matching algorithms, as well as how over-segments improve the stereo matching process.</abstract><pub>IEEE</pub><doi>10.1109/DICTA.2010.50</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9781424488162
ispartof 2010 International Conference on Digital Image Computing: Techniques and Applications, 2010, p.235-240
issn
language eng
recordid cdi_ieee_primary_5692570
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Brightness
Image segmentation
Partitioning algorithms
Pixel
Robustness
Shape
Stereo vision
title Evaluating Multi-scale Over-segment and Its Contribution to Real Scene Stereo Matching by High-Order MRFs
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T05%3A33%3A00IST&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=Evaluating%20Multi-scale%20Over-segment%20and%20Its%20Contribution%20to%20Real%20Scene%20Stereo%20Matching%20by%20High-Order%20MRFs&rft.btitle=2010%20International%20Conference%20on%20Digital%20Image%20Computing:%20Techniques%20and%20Applications&rft.au=Yiran%20Xie&rft.date=2010-12&rft.spage=235&rft.epage=240&rft.pages=235-240&rft.isbn=9781424488162&rft.isbn_list=1424488168&rft_id=info:doi/10.1109/DICTA.2010.50&rft.eisbn=9780769542713&rft.eisbn_list=0769542719&rft_dat=%3Cieee_6IE%3E5692570%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-1dc5b44bd5d8e39763bfa7178ab203d0e9d3ce90b2d49cf71a748a4846e9a5753%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=5692570&rfr_iscdi=true