CSc83029 – 3-D Computer Vision/ Ioannis Stamos 3-D Computational Vision CSc 83029 Optical Flow & Motion The Factorization Method.

Slides:



Advertisements
Similar presentations
Andrew Cosand ECE CVRR CSE
Advertisements

Two-View Geometry CS Sastry and Yang
Computer Vision Optical Flow
CSc D Computer Vision – Ioannis Stamos 3-D Computer Vision CSc Camera Calibration.
Camera calibration and epipolar geometry
Structure from motion.
3D Computer Vision and Video Computing 3D Vision Topic 4 of Part II Visual Motion CSc I6716 Fall 2011 Cover Image/video credits: Rick Szeliski, MSR Zhigang.
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
Optical Flow Methods 2007/8/9.
Structure from motion. Multiple-view geometry questions Scene geometry (structure): Given 2D point matches in two or more images, where are the corresponding.
Uncalibrated Geometry & Stratification Sastry and Yang
Multiple-view Reconstruction from Points and Lines
3D Computer Vision and Video Computing 3D Vision Topic 5 of Part II Visual Motion CSc I6716 Fall 2006 Cover Image/video credits: Rick Szeliski, MSR Zhigang.
Uncalibrated Epipolar - Calibration
3D Computer Vision and Video Computing 3D Vision Lecture 16 Visual Motion (I) CSC Capstone Fall 2004 Zhigang Zhu, NAC 8/203A
Previously Two view geometry: epipolar geometry Stereo vision: 3D reconstruction epipolar lines Baseline O O’ epipolar plane.
Motion Computing in Image Analysis
Visual motion Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys.
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
Motion Field and Optical Flow. Outline Motion Field and Optical Flow Definition, Example, Relation Optical Flow Constraint Equation Assumptions & Derivation,
COMP 290 Computer Vision - Spring Motion II - Estimation of Motion field / 3-D construction from motion Yongjik Kim.
3D Rigid/Nonrigid RegistrationRegistration 1)Known features, correspondences, transformation model – feature basedfeature based 2)Specific motion type,
3D Motion Estimation. 3D model construction Video Manipulation.
Camera parameters Extrinisic parameters define location and orientation of camera reference frame with respect to world frame Intrinsic parameters define.
3D Computer Vision and Video Computing 3D Vision Topic 8 of Part 2 Visual Motion (II) CSC I6716 Spring 2004 Zhigang Zhu, NAC 8/203A
Optical flow (motion vector) computation Course: Computer Graphics and Image Processing Semester:Fall 2002 Presenter:Nilesh Ghubade
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
The Brightness Constraint
1-1 Measuring image motion velocity field “local” motion detectors only measure component of motion perpendicular to moving edge “aperture problem” 2D.
The Measurement of Visual Motion P. Anandan Microsoft Research.
Computer Vision, Robert Pless Lecture 11 our goal is to understand the process of multi-camera vision. Last time, we studies the “Essential” and “Fundamental”
Uses of Motion 3D shape reconstruction Segment objects based on motion cues Recognize events and activities Improve video quality Track objects Correct.
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #16.
3D Computer Vision and Video Computing 3D Vision Lecture 6. Visual Motion CSc80000 Section 2 Spring 2005 Zhigang Zhu, Rm 4439 Cover Image/video credits:
Affine Structure from Motion
3D Imaging Motion.
Raquel A. Romano 1 Scientific Computing Seminar May 12, 2004 Projective Geometry for Computer Vision Projective Geometry for Computer Vision Raquel A.
EECS 274 Computer Vision Affine Structure from Motion.
Optical Flow. Distribution of apparent velocities of movement of brightness pattern in an image.
1 Motion Analysis using Optical flow CIS601 Longin Jan Latecki Fall 2003 CIS Dept of Temple University.
CS332 Visual Processing Department of Computer Science Wellesley College Analysis of Motion Recovering 3-D structure from motion.
Miguel Tavares Coimbra
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
Reconstruction from Two Calibrated Views Two-View Geometry
Uncalibrated reconstruction Calibration with a rig Uncalibrated epipolar geometry Ambiguities in image formation Stratified reconstruction Autocalibration.
Motion / Optical Flow II Estimation of Motion Field Avneesh Sud.
Optical flow and keypoint tracking Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys.
Structure from Motion. For now, static scene and moving cameraFor now, static scene and moving camera – Equivalently, rigidly moving scene and static.
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
Lec 26: Fundamental Matrix CS4670 / 5670: Computer Vision Kavita Bala.
MOTION Model. Road Map Motion Model Non Parametric Motion Field : Algorithms 1.Optical flow field estimation. 2.Block based motion estimation. 3.Pel –recursive.
11/25/03 3D Model Acquisition by Tracking 2D Wireframes Presenter: Jing Han Shiau M. Brown, T. Drummond and R. Cipolla Department of Engineering University.
René Vidal and Xiaodong Fan Center for Imaging Science
3D Vision Topic 4 of Part II Visual Motion CSc I6716 Fall 2009
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
The Brightness Constraint
Image Primitives and Correspondence
3D Motion Estimation.
Structure from motion Input: Output: (Tomasi and Kanade)
The Brightness Constraint
3D Vision Topic 5 of Part II Visual Motion CSc I6716 Fall 2007
The Brightness Constraint
3D Vision Topic 5 of Part II Visual Motion CSc I6716 Fall 2005
Uncalibrated Geometry & Stratification
George Mason University
Optical flow Computer Vision Spring 2019, Lecture 21
3D Vision Topic 5 of Part II Visual Motion CSc I6716 Spring 2008
3D Vision Lecture 5. Visual Motion CSc83300 Spring 2006
Structure from motion Input: Output: (Tomasi and Kanade)
Presentation transcript:

CSc83029 – 3-D Computer Vision/ Ioannis Stamos 3-D Computational Vision CSc Optical Flow & Motion The Factorization Method

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Optical Flow & Motion  Finding the movement of scene objects from time-varying images.  Motion Field  Optical Flow  Computing Optical Flow

CSc83029 – 3-D Computer Vision/ Ioannis Stamos

Computing Time-to-Impact τ L l(t) v f D0D0 D 0 -vt l(t)=f L/D(t)

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Computing Time-to-Impact τ L l(t) v f D0D0 D 0 -vt l(t)=f L/D(t) l(t) / l’(t) = τ Quantities measured from image sequence.

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Sudden change in viewing position/direction: Hard to compute motion field/optical flow.

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Views from a sequence of spatially close viewpoints: Motion Field/ Optical Flow

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Sub problems of Motion Analysis  Correspondence.  Reconstruction.  Segmentation.

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Motion Field 2-D vector field of velocities of image points, induced by relative motion between the viewing camera and the observed points. P V dt v dt p f Image plane Scene Point Velocity V=dr o /dt Image Velocity v =dr i /dt roro riri

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Motion Field 2-D vector field of velocities of image points, induced by relative motion between the viewing camera and the observed points. P V dt v dt p f Image plane roro riri Perspective projection Velocity of point P as a function of translation and rotation Motion field equations

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Motion Field 2-D vector field of velocities of image points, induced by relative motion between the viewing camera and the observed points => SUM of 2 COMPONENTS:

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Motion Field 2-D vector field of velocities of image points, induced by relative motion between the viewing camera and the observed points => SUM of 2 COMPONENTS: +

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Special Case 1: Pure Translation 2-D vector field of velocities of image points, induced by relative motion between the viewing camera and the observed points => SUM of 2 COMPONENTS: +

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Pure Translation: Radial Motion Field p0=(x0,y0)

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Pure Translation: Radial Motion Field 1.Tz < 0 : FOCUS OF EXPANSION. 2.Tz > 0: FOCUS OF CONTRACTION. 3.Tz = 0: PARALLEL MOTION FIELD. 4.Vanishing point (epipole) p0. p0=(x0,y0)

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Special Case 2: Moving Plane n P Plane moves: n,d are functions of time. Motion field=?

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Special Case 2: Moving Plane n P Plane moves: n,d are functions of time. Motion field=?

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Special Case 2: Moving Plane n P Plane moves: n,d are functions of time. Motion field=? Motion field: quadratic polynomial in (x,y,f) at any time t. The same motion field can be produced by 2 different planes undergoing 2 different 3-D motions.

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Motion Parallax The relative motion field of two instantaneously coincident points does not depend on the rotational component of the motion… p0

CSc83029 – 3-D Computer Vision/ Ioannis Stamos The notion of Optical Flow Optical Flow: Estimation of the motion field from a sequence of images.

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Optical Flow

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Optical Flow Image brightness constancy equation: E(x,y,t)=E(x+uδt, y+vδt, t+δt) or tt+δt (x,y) (x+uδt,y+vδt) u=δx/δt v=δy/δt

CSc83029 – 3-D Computer Vision/ Ioannis Stamos The Aperture Problem Image brightness constancy equation: E(x,y,t)=E(x+uδt, y+vδt, t+δt) Aperture problem 1 constraint 2 unknowns The component of the motion field in the direction orthogonal to the spatial image gradient is not constrained by the image brightness constancy equation.

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Optical Flow At each point we know dE/dx dE/dy and dE/dt. How can we obtain dx/dt and dy/dt?

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Computing Optical Flow Assumption: The motion field is well approximated by a constant vector field within any small patch of the image plane. Each provides one constraint Solution is

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Computing Optical Flow Assumption: The motion field is well approximated by a constant vector field within any small patch of the image plane. Minimize Q

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Computing Optical Flow Assumption: The motion field is well approximated by a constant vector field within any small patch of the image plane. Minimize Q =>Solve the linear system

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Computing Optical Flow global approach Minimize the error in the image brightness constancy constraint. [Schunck and Horn 81]

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Computing Optical Flow global approach Minimize the error in the image brightness constancy constraint. Minimize the deviation from smoothness of the motion vectors. [Schunck and Horn 81]

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Computing Optical Flow global approach Minimize the error in the image brightness constancy constraint. Minimize the deviation from smoothness of the motion vectors. Find solution by minimizing where lambda weights the smoothness term. [Schunck and Horn 81]

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Optical Flow

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Optical Flow

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Optical Flow

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Optical Flow

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Optical Flow Solve for the 8 unknowns a, b, c, d, e, f, g and h. If the scene is planar the motion Is described by Using

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Tracking Rigid Bodies B B Random Sampling Algorithm Step 1: Find corners Step 2: Search for correspondence Step 3: Randomly choose small set of matches. Step 4: Estimate F matrix Step 5: Find total number of matches close to epipolar lines Step 6: Go to step 3 Step 7: Choose F with largest number of matches

CSc83029 – 3-D Computer Vision/ Ioannis Stamos

1. Use multiple image stream to compute the information about camera motion and 3D structure of the scene 2. Tracking image features over time Tracked Features Structure and Motion Recovery from Video Original sequence From Jana Kosecka

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Structure and Motion Recovery from Video Computed model 3D coordinates of the feature points Original picture From Jana Kosecka

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Factorization Method FRAMES: i=1…N kiki jiji i

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Factorization Method kiki jiji i Pj FRAMES: i=1…N World Points: j=1…n (x ij,y ij )

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Factorization Method World Reference Frame kiki jiji i Pj FRAMES: i=1…N World Points: j=1…n (x ij,y ij ) Y X Z Ti

CSc83029 – 3-D Computer Vision/ Ioannis Stamos World Reference Frame kiki jiji i Pj FRAMES: i=1…N World Points: j=1…n (x ij,y ij ) Y X Z Ti ASSUMPTIONS: The camera model is orthographic! The positions of n image points have been tracked.

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Measurement Matrix 2*N (Frames) n points per frame 2*N (Frames) n points per frame Registered Measurement Matrix

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Factorization Method World Reference Frame kiki jiji i FRAMES: i=1…N World Points: j=1…n Y X Z Ti Pj 3D Centroid 2D Centroid

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Rank Theorem 2*N (Frames) n points per frame R: “Rotation Matrix” S: Shape Matrix

CSc83029 – 3-D Computer Vision/ Ioannis Stamos Rank Theorem 2*N (Frames) n points per frame R: “Rotation Matrix” S: Shape Matrix Rank of is 3.

CSc83029 – 3-D Computer Vision/ Ioannis Stamos The algorithm 2*N (Frames) n points per frame Decompose into R and S. Is the decomposition unique? Translation estimation?

CSc83029 – 3-D Computer Vision/ Ioannis Stamos