13D Computer Visionand Video Computing3D Vision3D VisionCSc I6716Fall 2011Topic 4 of Part II Visual MotionCover Image/video credits: Rick Szeliski, MSRZhigang Zhu, City College of New York [email protected] Computer Visionand Video ComputingOutline of Motion Outline of Motion Problems and Applications The importance of visual motion Problem Statement The Motion Field of Rigid MotionBasics–Notations and EquationsBasics Notations and Equations Three Important Special Cases: Translation, Rotation and Moving Plane Motion Parallax Optical Flow Optical flow equation and the aperture problem Estimating optical flow 3D motion & structure from optical flow Feature-based ApproachTwo-frame algorithmTwoframe algorithm Multi-frame algorithm Structure from motion – Factorization method Advanced Topics Spatio-Temporal Image and Epipolar Plane Image Video Mosaicing and Panorama Generation Motion-based Segmentation and Layered Representation23D Computer Visionand Video ComputingThe Importance of Visual MotionThe Importance of Visual Motion Structure from Motion Apparent motion is a strong visual clue for 3D reconstruction More than a multi-camera stereo system Recognition by motion (only) Biological visual systems use visual motion to infer properties of 3D world with little a priori knowledge of it Blurred image sequence Visual Motion = Video ! [Go to CVPR 2004-2010 Sites for Workshops]Video Coding and Compression: MPEG 1 2 4 7Video Coding and Compression: MPEG 1, 2, 4, 7… Video Mosaicing and Layered Representation for IBR Surveillance (Human Tracking and Traffic Monitoring) HCI using Human Gesture (video camera) Image-based Rendering …3D Computer Visionand Video ComputingBlurred SequenceBlurred SequenceRecognition by Actions: Recognize object from motion even if we cannot distinguish it in any images …An up-sampling from images of resolution 15x20 pixels From: James W. Davis. MIT Media Lab33D Computer Visionand Video ComputingProblem StatementProblem Statement Two Subproblems Correspondence: Which elements of a frame correspond to which elements in the next frame?RttiGi b f d d iblReconstruction :Given a number of correspondences, and possibly the knowledge of the camera’s intrinsic parameters, how to recovery the 3-D motion and structure of the observed world Main Difference between Motion and Stereo Correspondence: the disparities between consecutive frames are much smaller due to dense temporal sampling Reconstruction: the visual motion could be caused by multiple motions ( instead of a single 3D rigid transformation) The Third Subproblem, and Fourth…. Motion Segmentation: what are the regions the the image plane corresponding to different moving objects? Motion Understanding: lip reading, gesture, expression, event…3D Computer Visionand Video ComputingApproachesApproaches Two Subproblems Correspondence:Differential Methods->dense measure (optical flow)Differential Methods >dense measure (optical flow) Matching Methods -> sparse measure Reconstruction : More difficult than stereo since Motion (3D transformation betw. Frames) as well as structure needs to be recovered Small baseline causes large errors The Third Subprobleme d Subp ob e Motion Segmentation: Chicken and Egg problem Which should be solved first? Matching or Segmentation Segmentation for matching elements Matching for Segmentation43D Computer Visionand Video ComputingThe Motion Field of Rigid ObjectsThe Motion Field of Rigid Objects Motion: 3D Motion ( R, T): camera motion (static scene) or single object motionor single object motion Only one rigid, relative motion between the camera and the scene (object) Image motion field: 2D vector field of velocities of the image points induced by the relative motion. Data: Image sequence Many framesy captured at time t=0, 1, 2, … Basics: only consider two consecutive frames We consider a reference frame and its consecutive frame Image motion field can be viewed disparity map of the two frames captured at two consecutive camera locations ( assuming we have a moving camera)3D Computer Visionand Video ComputingThe Motion Field of Rigid ObjectsThe Motion Field of Rigid Objects Notations P = (X,Y,Z)T: 3-D point in the camera reference frame p = (x,y,f)T: the projection of the scene point in the pinhole cameraPpZfpp Relative motion between P and the camera T= (Tx,Ty,Tz)T: translation component of the motion xyz: the angular velocity Note:How to connect this with stereo geometryPωTV PVHow to connect this with stereo geometry (with R, T)? Image velocity v= ?pOXfZYv53D Computer Visionand Video ComputingThe Motion Field of Rigid ObjectsThe Motion Field of Rigid Objects Notations P = (X,Y,Z)T: 3-D point in the camera reference frame p = (x,y,f)T: the projection of the scene point in the pinhole cameraPpZfpoint in the pinhole camera Relative motion between P and the camera T= (Tx,Ty,Tz)T: translation component of the motion xyz: the angular velocityNote:PωTV PTVPP000xyxzyzNote: How to connect this with stereo geometry (with R, T)?TPP 111xyxzyzcoscoscossinsinsincossinsincossincoscossincoscossinsinsinsincoscossinsinsinsincoscoscosR3D Computer Visionand Video ComputingBasic Equations of Motion FieldBasic Equations of Motion Field Notes: Take the time derivative of both sides of the projection equation)(2PVvzVZZf The motion field is the sum of two components Translational part Rotational part Assume known intrinsic parametersPpZfPωTVzyxzyxyxTTTyfxfZfxxyfyfyfxxyfvv001)(12222Rotation part: no depth informationTranslation part: depth Z63D Computer Visionand Video ComputingMotion Field vs. DisparityMotion
View Full Document