Computer Vision TexPoint fonts used in EMF: AAA Niels Chr Overgaard 2010 Lecture 8: Structure from Motion RANSAC Structure from motion problem Structure.

Slides:

Advertisements

Similar presentations

The fundamental matrix F

Advertisements

Summary of Friday A homography transforms one 3d plane to another 3d plane, under perspective projections. Those planes can be camera imaging planes or.

MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.

Image alignment Image from

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

Robust Estimator 學生 : 范育瑋老師 : 王聖智. Outline Introduction LS-Least Squares LMS-Least Median Squares RANSAC- Random Sample Consequence MLESAC-Maximum likelihood.

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.

Lecture 21: Multiple-view geometry and structure from motion

Geometric Optimization Problems in Computer Vision.

Multiple View Geometry Marc Pollefeys University of North Carolina at Chapel Hill Modified by Philippos Mordohai.

Lecture 10: Cameras CS4670: Computer Vision Noah Snavely Source: S. Lazebnik.

Triangulation and Multi-View Geometry Class 9 Read notes Section 3.3, , 5.1 (if interested, read Triggs’s paper on MVG using tensor notation, see.

Fitting a Model to Data Reading: 15.1,

Structure from Motion : Who’s afraid of a couple typos? Work based on that of Hartley by Josh Wills.

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

Robust Statistics Robust Statistics Why do we use the norms we do? Henrik Aanæs IMM,DTU A good general reference is: Robust Statistics:

Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2006 with a lot of slides stolen from Steve Seitz and.

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.

Feature Matching and RANSAC : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and Rick Szeliski.

CSE 473/573 RANSAC & Least Squares Devansh Arpit.

Robust fitting Prof. Noah Snavely CS1114

Automatic Camera Calibration

Image Stitching Ali Farhadi CSE 455

CSE 185 Introduction to Computer Vision

Chapter 6 Feature-based alignment Advanced Computer Vision.

Advanced Computer Vision Feature-based Alignment Lecturer: Lu Yi & Prof. Fuh CSIE NTU.

Structure from Motion Course web page: vision.cis.udel.edu/~cv April 25, 2003  Lecture 26.

Example: line fitting. n=2 Model fitting Measure distances.

Random Thoughts 2012 (COMP 066) Jan-Michael Frahm Jared Heinly.

Computer Vision : CISC 4/689 Going Back a little Cameras.ppt.

RANSAC Robust model estimation from data contaminated by outliers Ondřej Chum.

EECS 274 Computer Vision Model Fitting. Fitting Choose a parametric object/some objects to represent a set of points Three main questions: –what object.

Geometric Transformations

Feature Matching. Feature Space Outlier Rejection.

Fitting image transformations Prof. Noah Snavely CS1114

776 Computer Vision Jan-Michael Frahm Spring 2012.

Robust Estimation Course web page: vision.cis.udel.edu/~cv April 23, 2003  Lecture 25.

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.

776 Computer Vision Jan-Michael Frahm Spring 2012.

Fitting a transformation: feature-based alignment

CENG 789 – Digital Geometry Processing 10- Least-Squares Solutions

Exercise Class 11: Robust Tecuniques RANSAC, Hough Transform

A Brief Introduction of RANSAC

Lecture 7: Image alignment

RANSAC and mosaic wrap-up

Homography From Wikipedia In the field of computer vision, any

A special case of calibration

Features Readings All is Vanity, by C. Allan Gilbert,

Feature Matching and RANSAC

Segmentation by fitting a model: robust estimators and RANSAC

CENG 789 – Digital Geometry Processing 11- Least-Squares Solutions

Computational Photography

Calibration and homographies

Back to equations of geometric transformations

CS5760: Computer Vision Lecture 9: RANSAC Noah Snavely

CS5760: Computer Vision Lecture 9: RANSAC Noah Snavely

Image Stitching Linda Shapiro ECE/CSE 576.

Image Stitching Linda Shapiro ECE P 596.

Presentation transcript:

Computer Vision TexPoint fonts used in EMF: AAA Niels Chr Overgaard 2010 Lecture 8: Structure from Motion RANSAC Structure from motion problem Structure estimation Motion estimation Structure and motion estimation Goal: To understand the general ideas and Some of the methods. Read: Forsyth & Ponce Chapter:

Datorseende vt-10Föreläsning 8 RANSAC Random sampling concensus RANSAC - is a general probabilistic method for model estimation given noisy and contaminated data. Example: Line fitting (15 noisy + 5 outliers) TheoryPractice

Datorseende vt-10Föreläsning 8 RANSAC – algorithm (outline) 1.Input: S = data points n = sample size k = number of iterations t = threshold for godness of fit ( d = sufficient number of inliers (optional) ) 2.Loop: repeat k times Pick n-sample at random from S Fit model to sample Count #inliers (i.e. points in S fitting the model within threshold t) Store sample and inliers if better than the previous one. ( Stop if #inliers > d (optional) ) 3.Finalization: Fit model to the inliers of the best sample obtained.

Datorseende vt-10Föreläsning 8 Example: line fitting (again) Recall our situation: 20 points given, 5 outliers: Sample size: n = 2. Number of iterations: k>6 (we use k=7) Threshold for goodness of fit: d=0.5 (wrt. scale in figure)

Datorseende vt-10Föreläsning 8 The first iteration:

Datorseende vt-10Föreläsning 8 The following 6 iterations:

Datorseende vt-10Föreläsning 8 The final line estimation: Notice: Exhaustive search for the line with most inliers requires 190 iterations!

Datorseende vt-10Föreläsning 8

RANSAC : How many iterations? Let w denote (#inliers)/(#data points). n = the sample size (n=2 for lines, n=4 for plane homographies) k iterations. The probability that a random n-sample is correct: The probability that k random n-sample contains at least one outlier each: Choose k so large that the fraction of failures is smaller than a given tolerance z.

Sampel storlek Andelen outliers N 5%10%20%25%30%40%50% från Hartley & Zisserman RANSAC: k for p=1-z=0.99

Datorseende vt-10Föreläsning 8 x Bildplan Kamera- centrum X

Datorseende vt-10Föreläsning 8 The Structure from Motion Problem Many cameras (images) Many scene points Estimate all of them! Let us see how this is done in principle

Datorseende vt-10Föreläsning 8

3D-modell Exempel: Punkter Bilder Följda punkter

Datorseende vt-10Föreläsning 8 Exempel: Linjer och kägelsnitt Bilder 3D-modell

Datorseende vt-10Föreläsning 8

X