资源描述：
《基于区域间协同优化的立体匹配算法》由会员上传分享，免费在线阅读，更多相关内容在行业资料-天天文库。
1、Seediscussions,stats,andauthorprofilesforthispublicationat:https://www.researchgate.net/publication/4351129RegionbasedstereomatchingalgorithmusingcooperativeoptimizationConferencePaperinProceedings/CVPR,IEEEComputerSocietyConferenceonComputerVisionandPatternRecognition
2、.IEEEComputerSocietyConferenceonComputerVisionandPatternRecognition·July2008DOI:10.1109/CVPR.2008.4587456 · Source:IEEEXploreCITATIONSREADS2302952authors,including:ZengfuWangUniversityofScienceandTechnologyofChina152PUBLICATIONS1,309CITATIONSSEEPROFILESomeoftheauthorso
3、fthispublicationarealsoworkingontheserelatedprojects:ITERprojectViewprojectAllcontentfollowingthispagewasuploadedbyZengfuWangon10January2016.Theuserhasrequestedenhancementofthedownloadedfile.第35卷第5期自动化学报Vol.35,No.52009年5月ACTAAUTOMATICASINICAMay,2009基于区域间协同优化的立体匹配算法郑志刚1
4、汪增福1摘要提出了一种基于分割区域间协同优化的立体匹配算法.该算法以图像区域为匹配基元,利用区域的彩色特征以及相邻区域间应满足的平滑和遮挡关系定义了区域的匹配能量函数,并引入区域之间的合作竞争机制,通过协同优化使所定义的匹配能量极小化,从而得到比较理想的视差结果.算法首先对参考图像进行分割,利用相关法得到各分割区域的初始匹配;然后用平面模型对各区域的视差进行拟合,得到各区域的视差平面参数;最后,基于协同优化的思想,采用局部优化的方法对各区域的视差平面参数进行迭代优化,直至得到比较合理的视差图为止.采用Middleburytestse
5、t进行的实验结果表明,该方法在性能上可以和目前最好的立体匹配算法相媲美,得到的视差结果接近于真实视差.关键词立体匹配,图像分割,协同优化,平面拟合,均值偏移中图分类号TP391ARegionBasedStereoMatchingAlgorithmUsingCooperativeOptimization11ZHENGZhi-GangWANGZeng-FuAbstractThispaperpresentsastereomatchingalgorithmbasedoninter-regionalcooperativeoptimizatio
6、n.Thisalgorithmusesregionsasmatchingprimitivesandde¯nesthecorrespondingregioncostfunctionsformatchingbyutilizingthecolorstatisticsofregionsandtheconstraintsonsmoothnessandocclusionbetweenadjacentregions.Inordertoobtainamorereasonabledisparitymap,acooperativeoptimizatio
7、nprocedureisemployedtominimizethematchingcostsofallregionsbyintroducingthecooperativeandcompetitivemechanismbetweenregions.Firstly,acolorbasedsegmentationmethodisusedtosegmentthereferenceimageintoregionswithhomogeneouscolor.Secondly,alocalwindow-basedmatchingmethodisus
8、edtodeterminetheinitialdisparityestimatesofeachimagepoint.Andthen,aplane¯ttingtechniqueisappliedtoobtaintheparameters
