3D VisionStereo VisionA Stereo PairMore Images…Slide 5Slide 6Slide 7Slide 8Lecture OutlineStereo GeometryA Simple Stereo SystemDisparity EquationDisparity vs. BaselineDepth AccuracyStereo with Converging CamerasSlide 16Slide 17Slide 18Slide 19Slide 20Slide 21Parameters of a Stereo SystemEpipolar GeometrySlide 24Essential MatrixSlide 26Fundamental MatrixSlide 28Computing F: The Eight-point AlgorithmLocating the Epipoles from FStereo RectificationSlide 32Slide 33Slide 34Next3D Computer Visionand Video Computing3D Vision3D VisionTopic 7 of Part 2Stereo Vision (I)CSC I6716Spring 2004Zhigang Zhu, NAC 8/203Ahttp://www - cs.engr.ccny.cuny.edu /~zhu/VisionCourse-2004.html3D Computer Visionand Video ComputingStereo VisionStereo VisionProblemInfer 3D structure of a scene from two or more images taken from different viewpointsTwo primary Sub-problemsCorrespondence problem (stereo match) -> disparity mapSimilarity instead of identityOcclusion problem: some parts of the scene are visible only in one eyeReconstruction problem -> 3DWhat we need to know about the cameras’ parametersOften a stereo calibration problemLectures on Stereo VisionStereo Geometry – Epipolar Geometry (*) Correspondence Problem (*) – Two classes of approaches3D Reconstruction Problems – Three approaches3D Computer Visionand Video ComputingA Stereo PairA Stereo PairProblemsCorrespondence problem (stereo match) -> disparity mapReconstruction problem -> 3DCMU CIL Stereo Dataset : Castle sequencehttp://www-2.cs.cmu.edu/afs/cs/project/cil/ftp/html/cil-ster.html?3D?3D Computer Visionand Video ComputingMore Images…More Images…ProblemsCorrespondence problem (stereo match) -> disparity mapReconstruction problem -> 3D3D Computer Visionand Video ComputingMore Images…More Images…ProblemsCorrespondence problem (stereo match) -> disparity mapReconstruction problem -> 3D3D Computer Visionand Video ComputingMore Images…More Images…ProblemsCorrespondence problem (stereo match) -> disparity mapReconstruction problem -> 3D3D Computer Visionand Video ComputingMore Images…More Images…ProblemsCorrespondence problem (stereo match) -> disparity mapReconstruction problem -> 3D3D Computer Visionand Video ComputingMore Images…More Images…ProblemsCorrespondence problem (stereo match) -> disparity mapReconstruction problem -> 3D3D Computer Visionand Video ComputingLecture OutlineLecture OutlineA Simple Stereo Vision SystemDisparity Equation Depth ResolutionFixated Stereo SystemZero-disparity HoropterEpipolar GeometryEpipolar lines – Where to search correspondencesEpipolar Plane, Epipolar Lines and Epipoleshttp://www.ai.sri.com/~luong/research/Meta3DViewer/EpipolarGeo.htmlEssential Matrix and Fundamental MatrixComputing E & F by the Eight-Point AlgorithmComputing the EpipolesStereo Rectification3D Computer Visionand Video ComputingStereo GeometryStereo GeometryConverging Axes – Usual setup of human eyesDepth obtained by triangulationCorrespondence problem: pl and pr correspond to the left and right projections of P, respectively.Object pointCentralProjectionRaysVergence AngleplprP(X,Y,Z)3D Computer Visionand Video ComputingA Simple Stereo SystemA Simple Stereo SystemZw=0 LEFT CAMERALeft image:referenceRight image:targetRIGHT CAMERAElevation ZwdisparityDepth Zbaseline3D Computer Visionand Video ComputingDisparity EquationDisparity EquationP(X,Y,Z)pl(xl,yl)Optical Center Olf = focal lengthImage planeLEFT CAMERAB = BaselineDepthStereo system with parallel optical axesf = focal lengthOptical Center Orpr(xr,yr)Image planeRIGHT CAMERAdxBfDZ Disparity: dx = xr - xl3D Computer Visionand Video ComputingDisparity vs. BaselineDisparity vs. BaselineP(X,Y,Z)pl(xl,yl)Optical Center Olf = focal lengthImage planeLEFT CAMERAB = BaselineDepthf = focal lengthOptical Center Orpr(xr,yr)Image planeRIGHT CAMERAdxBfDZ Disparity dx = xr - xl Stereo system with parallel optical axes3D Computer Visionand Video ComputingDepth AccuracyDepth AccuracyGiven the same image localization errorAngle of cones in the figureDepth Accuracy (Depth Resolution) vs. BaselineDepth Error 1/B (Baseline length)PROS of Longer baseline, better depth estimationCONSsmaller common FOVCorrespondence harder due to occlusionDepth Accuracy (Depth Resolution) vs. DepthDisparity (>0) 1/ DepthDepth Error Depth2Nearer the point, better the depth estimationAn Examplef = 16 x 512/8 pixels, B = 0.5 mDepth error vs. depthZ2Two viewpointsZ2>Z1Z1Z1OlOr)(Z 2dxfBZ)(ZZ dxfBZAbsolute errorRelative error3D Computer Visionand Video ComputingStereo with Converging CamerasStereo with Converging CamerasStereo with Parallel Axes Short baselinelarge common FOVlarge depth errorLong baselinesmall depth errorsmall common FOVMore occlusion problemsTwo optical axes intersect at the Fixation Pointconverging angle The common FOV IncreasesFOVLeft right3D Computer Visionand Video ComputingStereo with Converging CamerasStereo with Converging CamerasStereo with Parallel Axes Short baselinelarge common FOVlarge depth errorLong baselinesmall depth errorsmall common FOVMore occlusion problemsTwo optical axes intersect at the Fixation Pointconverging angle The common FOV IncreasesFOVLeft right3D Computer Visionand Video ComputingStereo with Converging CamerasStereo with Converging CamerasTwo optical axes intersect at the Fixation Pointconverging angle The common FOV IncreasesDisparity propertiesDisparity uses angle instead of distanceZero disparity at fixation pointand the Zero-disparity horopterDisparity increases with the distance of objects from the fixation points>0 : outside of the horopter<0 : inside the horopterDepth Accuracy vs. DepthDepth Error Depth2Nearer the point, better the depth estimationFOVLeft rightFixation point3D Computer Visionand Video ComputingStereo with Converging CamerasStereo with Converging CamerasTwo optical axes intersect at the Fixation Pointconverging angle The common FOV IncreasesDisparity propertiesDisparity uses angle instead of distanceZero disparity at fixation pointand the Zero-disparity horopterDisparity increases with the distance of objects from the fixation points>0 :
View Full Document