文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > Integrating Stereo with Shape-from-Shading derived Orientation Information
侵权投诉

Integrating Stereo with Shape-from-Shading derived Orientation Information

Binocular stereo has been extensively studied for extracting the shape of a scene. The challenge is in matching features between two images of a scene; this is the correspondence problem. Shape from shading (SfS) is another method of extracting shape. This

IntegratingStereowithShape-from-Shading

derivedOrientationInformation

TomS.F.HainesandRichardC.Wilson

DepartmentofComputerScience

UniversityofYork

Heslington,York,UK

thaines,wilson@cs.york.ac.uk

Abstract

Binocularstereohasbeenextensivelystudiedforextractingtheshapeofascene.Thechallengeisinmatchingfeaturesbetweentwoimagesofascene;thisisthecorrespondenceproblem.Shapefromshading(SfS)isanothermethodofextractingshape.Thismodelstheinteractionoflightwiththescenesurface(s)forasingleimage.Thesetwomethodsareverydifferent;stereousessurfacefeaturestodeliveradepth-map,SfSusesshading,albedoandlightinginformationtoinferthedifferentialofthedepth-map.

Inthispaperwedevelopaframeworkfortheintegrationofbothdepthandorientationinformation.Dedicatedalgorithmsareusedforinitialestimates.AGaussian-Markovrandom eldthenrepresentsthedepth-map,GaussianbeliefpropagationisusedtoapproximatetheMAPestimateofthedepth-map.Integratinginformationfrombothstereocorrespondencesandsurfacenormalsallows nesurfacedetailstobeestimated.

1Binocularstereoisalong-standingproblemincomputervision[17].Itenablesthecon-structionof3Dmodelsfromtwo2Dimages,bysolvingthecorrespondenceproblem,wherematchingfeaturesarefoundbetweentwoimagessuchthatthematchedfeaturesareatthesamelocationontheobject.Ifcameracalibrationisthenavailabledepthcanbereconstructedfromsuchmatches.Astandardpreprocessingstepinvolvesrectifyingtheimages,sothattheyrepresenttheimagestakenfromanidealisedhorizontalparallelcamerapair.Givenarecti edimagepairfeaturescanonlymatchfeaturesonthesamescan-line.Inthedensestereoproblemwhereeverypixelisafeatureadisparitymapiscreated,wherethedisparityassignedtoeachpixelistheoffsetalongthex-axistoitsmatchingpixelintheotherimage.

Densestereoalgorithmsmaybedividedintotwosteps.Firstisthecalculationofamatchingcostforeachdisparityateachlocation,representedbythe3DDisparitySpaceImage(DSI).InareaswithstrongcuesaDSIgivesaclearindicationofactualdisparity,butinrelativelyuniformareasitwillnotdistinguishthecorrectdisparityfromincorrectdisparities.Suggestedapproachesincludenormalisedcross-correlation[17]andslidingIntroduction

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email