Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.

Slides:



Advertisements
Similar presentations
Motion Estimation I What affects the induced image motion? Camera motion Object motion Scene structure.
Advertisements

MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
Two-View Geometry CS Sastry and Yang
Jan-Michael Frahm, Enrique Dunn Spring 2012
Two-view geometry.
Computer Vision Optical Flow
Camera calibration and epipolar geometry
Image alignment Image from
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 Estimation I What affects the induced image motion? Camera motion Object motion Scene structure.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
Epipolar geometry. (i)Correspondence geometry: Given an image point x in the first view, how does this constrain the position of the corresponding point.
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
Feature matching and tracking Class 5 Read Section 4.1 of course notes Read Shi and Tomasi’s paper on.
Multiple-view Reconstruction from Points and Lines
CSc83029 – 3-D Computer Vision/ Ioannis Stamos 3-D Computational Vision CSc Optical Flow & Motion The Factorization Method.
Previously Two view geometry: epipolar geometry Stereo vision: 3D reconstruction epipolar lines Baseline O O’ epipolar plane.
Optical Flow Estimation
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
COMP 290 Computer Vision - Spring Motion II - Estimation of Motion field / 3-D construction from motion Yongjik Kim.
Matching Compare region of image to region of image. –We talked about this for stereo. –Important for motion. Epipolar constraint unknown. But motion small.
3D Motion Estimation. 3D model construction Video Manipulation.
Optical Flow Digital Photography CSE558, Spring 2003 Richard Szeliski (notes cribbed from P. Anandan)
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
Structure Computation. How to compute the position of a point in 3- space given its image in two views and the camera matrices of those two views Use.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
A plane-plus-parallax algorithm Basic Model: When FOV is not very large and the camera motion has a small rotation, the 2D displacement (u,v) of an image.
Optical flow Combination of slides from Rick Szeliski, Steve Seitz, Alyosha Efros and Bill Freeman.
Multi-view geometry. Multi-view geometry problems Structure: Given projections of the same 3D point in two or more images, compute the 3D coordinates.
Automatic Camera Calibration
Computer vision: models, learning and inference
CSC 589 Lecture 22 Image Alignment and least square methods Bei Xiao American University April 13.
Lecture 11 Stereo Reconstruction I Lecture 11 Stereo Reconstruction I Mata kuliah: T Computer Vision Tahun: 2010.
Final Exam Review CS485/685 Computer Vision Prof. Bebis.
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Projective cameras Motivation Elements of Projective Geometry Projective structure from motion Planches : –
The Brightness Constraint
The Measurement of Visual Motion P. Anandan Microsoft Research.
Image stitching Digital Visual Effects Yung-Yu Chuang with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac.
EECS 274 Computer Vision Motion Estimation.
Multiview Geometry and Stereopsis. Inputs: two images of a scene (taken from 2 viewpoints). Output: Depth map. Inputs: multiple images of a scene. Output:
Uses of Motion 3D shape reconstruction Segment objects based on motion cues Recognize events and activities Improve video quality Track objects Correct.
© 2005 Martin Bujňák, Martin Bujňák Supervisor : RNDr.
3D Imaging Motion.
Two-view geometry. Epipolar Plane – plane containing baseline (1D family) Epipoles = intersections of baseline with image planes = projections of the.
EECS 274 Computer Vision Affine Structure from Motion.
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Newton's method Wikpedia page
Motion Estimation I What affects the induced image motion?
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
MASKS © 2004 Invitation to 3D vision Uncalibrated Camera Chapter 6 Reconstruction from Two Uncalibrated Views Modified by L A Rønningen Oct 2008.
Uncalibrated reconstruction Calibration with a rig Uncalibrated epipolar geometry Ambiguities in image formation Stratified reconstruction Autocalibration.
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Newton's method Wikpedia page
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
Estimating Parametric and Layered Motion
Motion and Optical Flow
René Vidal and Xiaodong Fan Center for Imaging Science
3D Vision Topic 4 of Part II Visual Motion CSc I6716 Fall 2009
The Brightness Constraint
3D Motion Estimation.
Epipolar geometry.
3D Photography: Epipolar geometry
Structure from motion Input: Output: (Tomasi and Kanade)
The Brightness Constraint
The Brightness Constraint
Uncalibrated Geometry & Stratification
Filtering Things to take away from this lecture An image as a function
Chapter 11: Stereopsis Stereopsis: Fusing the pictures taken by two cameras and exploiting the difference (or disparity) between them to obtain the depth.
Structure from motion Input: Output: (Tomasi and Kanade)
Presentation transcript:

Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in 2 unknowns (u,v). Insufficient info. Another constraint: Global Motion Model Constraint

Camera induced image motion = + Independent motions = 3D Camera motion + 3D Scene structure + Independent motions The 2D/3D Dichotomy Image motion = 2D techniques 3D techniques Singularities in “2D scenes” Do not model “3D scenes”  Requires prior model selection

Global Motion Models 2D Models: Affine Quadratic Homography (Planar projective transform) 3D Models: Rotation, Translation, 1/Depth Instantaneous camera motion models Essential/Fundamental Matrix Plane+Parallax  Relevant when camera is translating, scene is near, with depth variations.  Relevant for: *Airborne video (distant scene) * Remote Surveillance (distant scene) * Camera on tripod (pure Zoom/Rotation) * 2D Models are easier to estimate than 3D models (much fewer unknowns  numerically more stable). * 2D models provide dense correspondences.

Example: Affine Motion Substituting into the B.C. Equation: Each pixel provides 1 linear constraint in 6 global unknowns (minimum 6 pixels necessary) Least Square Minimization (over all pixels): Every pixel contributes  Confidence-weighted regression

Example: Affine Motion Differentiating w.r.t. a 1, …, a 6 and equating to zero  6 linear equations in 6 unknowns: Summation is over all the pixels in the image!

image I image J JwJw warp refine + Pyramid of image JPyramid of image I image I image J Coarse-to-Fine Estimation u=10 pixels u=5 pixels u=2.5 pixels u=1.25 pixels ==> small u and v... Parameter propagation:

Quadratic – instantaneous approximation to planar motion Other 2D Motion Models Projective – exact planar motion (Homography H)

Panoramic Mosaic Image Original video clip Generated Mosaic image Alignment accuracy (between a pair of frames): error < 0.1 pixel

Original Outliers Original Synthesized Video Removal

ORIGINAL ENHANCED Video Enhancement

Direct Methods: Methods for motion and/or shape estimation, which recover the unknown parameters directly from measurable image quantities at each pixel in the image. Minimization step: Direct methods: Error measure based on dense measurable image quantities (Confidence-weighted regression; Exploits all available information) Feature-based methods: Error measure based on distances of a sparse set of distinct feature matches (SIFT, HOG,...)

Benefits of Direct Methods High subpixel accuracy. Simultaneously estimate matches + transformation  Do not need distinct features for image alignment: Strong locking property.

Limitations Limited search range (up to ~10% of the image size). Brightness constancy assumption.

Video Indexing and Editing

The 2D/3D Dichotomy Image motion = Camera induced motion = + Independent motions = Camera motion + Scene structure + Independent motions 2D techniques 3D techniques Singularities in “2D scenes” Do not model “3D scenes” Source of dichotomy: Camera-centric models (R,T,Z)

The Plane+Parallax Decomposition Original SequencePlane-Stabilized Sequence The residual parallax lies on a radial (epipolar) field: epipole

Benefits of the P+P Decomposition Eliminates effects of rotation Eliminates changes in camera calibration parameters / zoom Camera parameters: Need to estimate only the epipole. (i.e., 2 unknowns) Image displacements: Constrained to lie on radial lines (i.e., reduces to a 1D search problem)  A result of aligning an existing structure in the image. 1. Reduces the search space:

Remove global component which dilutes information ! Translation or pure rotation ??? Benefits of the P+P Decomposition 2. Scene-Centered Representation: Focus on relevant portion of info

Benefits of the P+P Decomposition 2. Scene-Centered Representation: Shape = Fluctuations relative to a planar surface in the scene STAB_RUG SEQ

- fewer bits, progressive encoding Benefits of the P+P Decomposition 2. Scene-Centered Representation: Shape = Fluctuations relative to a planar surface in the scene Height vs. Depth (e.g., obstacle avoidance) A compact representation global (100) component local [-3..+3] component total distance [ ] camera center scene Appropriate units for shape

Start with 2D estimation (homography). 3D info builds on top of 2D info. 3. Stratified 2D-3D Representation: Avoids a-priori model selection. Benefits of the P+P Decomposition

Original sequencePlane-aligned sequenceRecovered shape Dense 3D Reconstruction (Plane+Parallax)

Original sequence Plane-aligned sequence Recovered shape

Original sequence Plane-aligned sequence Recovered shape Dense 3D Reconstruction (Plane+Parallax)

Brightness Constancy constraint P+P Correspondence Estimation The intersection of the two line constraints uniquely defines the displacement. 1. Eliminating Aperture Problem Epipolar line epipole p

other epipolar line Epipolar line Multi-Frame vs. 2-Frame Estimation The two line constraints are parallel ==> do NOT intersect 1. Eliminating Aperture Problem p another epipole Brightness Constancy constraint The other epipole resolves the ambiguity !