Geometric Optimization Problems in Computer Vision.

Slides:



Advertisements
Similar presentations
The fundamental matrix F
Advertisements

The Trifocal Tensor Multiple View Geometry. Scene planes and homographies plane induces homography between two views.
Computing 3-view Geometry Class 18
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
Robot Vision SS 2005 Matthias Rüther 1 ROBOT VISION Lesson 3: Projective Geometry Matthias Rüther Slides courtesy of Marc Pollefeys Department of Computer.
Chapter 6 Feature-based alignment Advanced Computer Vision.
776 Computer Vision Jared Heinly Spring 2014 (slides borrowed from Jan-Michael Frahm, Svetlana Lazebnik, and others)
Mosaics con’t CSE 455, Winter 2010 February 10, 2010.
Multiple View Geometry
L15:Microarray analysis (Classification) The Biological Problem Two conditions that need to be differentiated, (Have different treatments). EX: ALL (Acute.
Methods For Nonlinear Least-Square Problems
Fitting. We’ve learned how to detect edges, corners, blobs. Now what? We would like to form a higher-level, more compact representation of the features.
Computing F Class 8 Read notes Section 4.2. C1C1 C2C2 l2l2  l1l1 e1e1 e2e2 Fundamental matrix (3x3 rank 2 matrix) 1.Computable from corresponding points.
Multiple View Geometry Marc Pollefeys University of North Carolina at Chapel Hill Modified by Philippos Mordohai.
Data Modeling and Least Squares Fitting 2 COS 323.
Fitting a Model to Data Reading: 15.1,
CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry Some material taken from:  David Lowe, UBC  Jiri Matas, CMP Prague
Independent Motion Estimation Luv Kohli COMP Multiple View Geometry May 7, 2003.
Fitting. Choose a parametric object/some objects to represent a set of tokens Most interesting case is when criterion is not local –can’t tell whether.
Lecture 8: Image Alignment and RANSAC
1 Final exam of Comp300a Venue: LG1 Time: 8h30—10h30, 31 May 2003, Sat. Content: everything in these slides + projective geometry before midterm Bring:
Computational Photography: Image Registration Jinxiang Chai.
Lecture 10: Robust fitting CS4670: Computer Vision Noah Snavely.
Random Sample Consensus: A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography Martin A. Fischler, Robert C. Bolles.
1Jana Kosecka, CS 223b EM and RANSAC EM and RANSAC.
Computing transformations Prof. Noah Snavely CS1114
Fitting.
CSE 473/573 RANSAC & Least Squares Devansh Arpit.
כמה מהתעשייה? מבנה הקורס השתנה Computer vision.
Fitting and Registration
Robust fitting Prof. Noah Snavely CS1114
CSE 185 Introduction to Computer Vision
Chapter 6 Feature-based alignment Advanced Computer Vision.
Computer Vision - Fitting and Alignment
Advanced Computer Vision Feature-based Alignment Lecturer: Lu Yi & Prof. Fuh CSIE NTU.
Fitting and Registration Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 02/14/12.
Example: line fitting. n=2 Model fitting Measure distances.
CSCE 643 Computer Vision: Structure from Motion
3D Reconstruction Jeff Boody. Goals ● Reconstruct 3D models from a sequence of at least two images ● No prior knowledge of the camera or scene ● Use the.
Random Thoughts 2012 (COMP 066) Jan-Michael Frahm Jared Heinly.
1 Stereo vision and two-view geometry The goal of a stereo system is to get 3D information A stereo system consists at least of two ‘converging’ cameras.
Model Fitting Computer Vision CS 143, Brown James Hays 10/03/11 Slides from Silvio Savarese, Svetlana Lazebnik, and Derek Hoiem.
18 th August 2006 International Conference on Pattern Recognition 2006 Epipolar Geometry from Two Correspondences Michal Perďoch, Jiří Matas, Ondřej Chum.
RANSAC Robust model estimation from data contaminated by outliers Ondřej Chum.
EECS 274 Computer Vision Geometric Camera Calibration.
Geometric Transformations
1 Comparative Survey on Fundamental Matrix Estimation Computer Vision and Robotics Group Institute of Informatics and Applications University of Girona.
Computer Vision - Fitting and Alignment (Slides borrowed from various presentations)
Data Modeling Patrice Koehl Department of Biological Sciences National University of Singapore
Fitting image transformations Prof. Noah Snavely CS1114
CS 2750: Machine Learning Linear Regression Prof. Adriana Kovashka University of Pittsburgh February 10, 2016.
Robust Estimation Course web page: vision.cis.udel.edu/~cv April 23, 2003  Lecture 25.
Fitting.
EE 7730 Parametric Motion Estimation. Bahadir K. Gunturk2 Parametric (Global) Motion Affine Flow.
Invariant Local Features Image content is transformed into local feature coordinates that are invariant to translation, rotation, scale, and other imaging.
Grouping and Segmentation. Sometimes edge detectors find the boundary pretty well.
25 Years of RANSAC 25 Years of RANSAC Ondřej Chum
CENG 789 – Digital Geometry Processing 10- Least-Squares Solutions
A Brief Introduction of RANSAC
Homography From Wikipedia In the field of computer vision, any
CS 2750: Machine Learning Linear Regression
A special case of calibration
3D Photography: Epipolar geometry
Object recognition Prof. Graeme Bailey
Segmentation by fitting a model: robust estimators and RANSAC
CENG 789 – Digital Geometry Processing 11- Least-Squares Solutions
Calibration and homographies
CS5760: Computer Vision Lecture 9: RANSAC Noah Snavely
Parameter estimation class 6
CS5760: Computer Vision Lecture 9: RANSAC Noah Snavely
Presentation transcript:

Geometric Optimization Problems in Computer Vision

X x1 x2 x3

Computation of the Fundamental Matrix

b Ax Span(A) O

1D Gauss-Newton (Newton) iteration.

1D Gauss-Newton (Newton) iteration (failure)

x0x0 x1x1 x2x2 First step minimizes on line. Second step minimizes function in the plane.

X0X0

Subdivision search

Gradient Descent

Conjugate Gradient

Newton

Levenberg-Marquardt

Gauss-Newton (without line search)

Conjugate gradient Gradient descent Newton Model 1

Conjugate gradientGauss-NewtonGradient descent LevenbergNewton Model 2

Conjugate gradientGauss-NewtonGradient descent LevenbergNewton Model 3

Conjugate gradientGauss-NewtonGradient descent LevenbergNewton Model 4

Conjugate gradientGauss-NewtonGradient descent LevenbergNewton Model 5

Conjugate gradientGauss-NewtonGradient descent LevenbergNewton Model 6

Bundle-adjustment

Robust line estimation - RANSAC Fit a line to 2D data containing outliers There are two problems 1.a line fit which minimizes perpendicular distance 2.a classification into inliers (valid points) and outliers Solution: use robust statistical estimation algorithm RANSAC (RANdom Sample Consensus) [Fishler & Bolles, 1981]

Repeat 1.Select random sample of 2 points 2.Compute the line through these points 3.Measure support (number of points within threshold distance of the line) Choose the line with the largest number of inliers –Compute least squares fit of line to inliers (regression) RANSAC robust line estimation

Repeat 1.Select random sample of 7 correspondences 2.Compute F (1 or 3 solutions) 3.Measure support (number of inliers within threshold distance of epipolar line) Choose the F with the largest number of inliers Algorithm summary – RANSAC robust F estimation

Correlation matching results Many wrong matches (10-50%), but enough to compute F

Correspondences consistent with epipolar geometry

Computed epipolar geometry

h