ROBUST ESTIMATION TECHNIQUES IN COMPUTER VISION

Size: px
Start display at page:

Download "ROBUST ESTIMATION TECHNIQUES IN COMPUTER VISION"

Transcription

1 ROBUST ESTIMATION TECHNIQUES IN COMPUTER VISION Half-day tutorial at ECCV 14, September 7 Olof Enqvist! Fredrik Kahl! Richard Hartley!

2 Robust Optimization Techniques in Computer Vision! Olof Enqvist! Chalmers University of Technology! Fredrik Kahl! Chalmers University of Technology! Lund University! Richard Hartley! Australian National University! NICTA!

3 Approximate Methods - Fast approximate methods and outlier rejection schemes!

4 +1! -1! +1! -1! A Simple Idea!

5 Approximate Inlier Maximization! 0! For every point - Compute angle intersections - Sort the angles - Compute maximum inliers 0! -1! +1! 1! -1! +1! 0! 1!

6 Fast Outlier Rejection!

7 Useful Observation! Given a solution with N inliers within -error. Then, there exists an N inlier solution with one error-free correspondence and others within -error

8 Upper Bound on Inliers! 0! +1! For every point - Propagate error to other points - Compute angle intersections - Sort the angles - Compute maximum inliers -1! 0! 1! +1! 2! -1! 1!

9 Fast Outlier Rejection! Given lower bound L on number of inliers (i) Assume one correspondence is an inlier (ii) Compute upper bound U with zero error on this correspondence and other correspondences within -error If U < L then contradiction: Correspondence guaranteed to be outlier!

10 Fast Outlier Rejection!

11 ! City-Scale Localization Find corresponding points! up to 99% outliers! L. Svärm, O. Enqvist, M. Oskarsson, F. Kahl,! Accurate Localization and Pose Estimation for Large 3D Models, CVPR 2014.!

12 ! Are we doing something wrong?

13 The Camera Pose Problem

14 The Camera Pose Problem

15 Two Key Ideas! 1. Simplified model 2. Fast outlier rejection

16 Simplified Model! Assumption: - Gravity vector of camera and 3D model known

17 Fast Outlier Rejection! Observation: Given a solution with N inliers within -error * * * * * * * * * * * * * * * Then, there exists an N inlier solution with one error-free correspondence and others within -error

18 Minkowski sum of two sets of vectors A and B is the set Minkowski!

19 Error propagation via Minkowski differences: Error Propagation!

20 Registration Problem! Assumption: - Lower and upper bounds of height

21 Error propagation via Minkowski differences: Error propagation!

22 Fast Outlier Rejection! Algorithm: (i) Assume one correspondence is an inlier (ii) Perform error propagation with Minkowski differences (iii) Compute a solution with zero error on this inlier correspondence (iv) Contradiction?

23 Algorithm! 1. Compute a solution with the approximate method 2. Perform outlier rejection 3. Optimal estimation (optional)

24 Application: City-Scale Localization! up to 99 % outliers!

25 Application: City-Scale Localization! Sattler et al! 2012! Sattler et al! 2011! Sattler et al! 2011! Li et al! 2010! Choudhary et al! 2012! Li et al! 2012! Dubrovnik!

26 Application: City-Scale Localization!

27 ! Other Applications Inter-modal registration Multiview geometry E. Ask, O. Enqvist, L. Svärm, F. Kahl, G. Lippolis, Tractable and Reliable Registration of 2D Point Sets, ECCV 2014.! O. Enqvist, E. Ask, F. Kahl, K. Åström, Robust Fitting for Multiple View Geometry, ECCV 2012.!

28 Branch and Bound - global optimization method by iteratively branching and bounding!

29

30

31

32 Outline! Introduction to branch & bound Registration and geometric matching problems Rotation space search Applications

33 Model: Measurements:

34 Model: Measurements:

35 Model: Measurements:

36 Model: Measurements: - unknown parameters - source points - target points Inlier if

37 Find transformation that minimizes the number of outliers

38 2D-2D Registration! Transformations: Euclidean Parametrization: Residual error: Domain: T. Breuel, Implementation techniques for geometric! branch-and-bound matching methods, CVIU 2003.!

39 2D-2D Registration! Lower bound on the number of outliers. Consider translation only. Suppose there exists in rectangle such that

40 2D-2D Registration! Lower bound. Now also with rotation uncertainty: Suppose there exists in cube such that, then

41 Branch & Bound Algorithm! 1. Initialize a queue with a rectangle domain 2. Execute until no more rectangles - Choose rectangle with best lower bound - Perform branching - Perform bounding on each branch - Update best upper bound - Remove rectangles with lower bound above best upper bound

42 2D-2D Registration!

43 2D-2D Registration! Discussion: Empirical performance often good, though worst-case exponential Can be done optimally in Approximate methods in

44 2D-2D Registration! Related work: Polynomial-time algorithms for truncated L1 and L2 norms E. Ask, O. Enqvist, L. Svärm, F. Kahl, G. Lippolis, Tractable and Reliable Registration of 2D Point Sets, ECCV 2014.!

45 Branch and Bound on Rotation Space!

46 Epipolar Geometry! Encodes relative displacement between two cameras - Rotation - Translation - 5 degrees of freedom!

47 Epipolar Geometry! Use angular reprojection error: α Find transformation that minimizes the number of outliers:

48

49 3D Rotation Estimation! Consider simpler problem first. Transformations: Rotation Residual error: Domain: R. Hartley, F. Kahl, Global Optimization through! Rotation Space Search, IJCV 2009.!

50

51

52 Isometry of Rotations and Quaternions! Angle between two quaternions is half the angle between the corresponding rotations, defined by All rotations within a deltaneighbourhood of a reference rotation form a circle on the quaternion sphere.

53 Angle-axis representation of Rotations! Flatten out the meridians (longitude lines)! Azimuthal Equidistant Projection! Rotations are represented by a ball of radius pi in 3- dimensional space.!

54 Subdividing and testing rotation space!

55 3D Rotation Estimation! Lower bound. Consider a cube in angle-axis representation with half side-length : Suppose there exists in cube such that :

56 Applications of 3D Rotation Estimation! Vanishing point detection J.-C. Bazin, Y. Seo, C. Demonceaux, P. Vasseur, K. Ikeuchi, I. Kweon, M. Pollefeys,! Globally Optimal Line Clustering and Vanishing Point Estimation, CVPR 2012.!

57 ! Applications of 3D Rotation Estimation Panorama stitching J.-C. Bazin, Y. Seo, M. Pollefeys,! Globally Optimal Consensus Set Maximization through Rotation Search, CVPR 2012! J.-C. Bazin, Y. Seo, R. Hartley, M. Pollefeys,! Globally Optimal Inlier Set Maximization with Unknown Rottion and Focal Length, ECCV 2014!

58 Applications of 3D Rotation Estimation! As a subroutine for 3D-3D registration J. Yang, H. Li, Y. Jia,! Go-ICP: Solving 3D Registration Efficiently and Globally Optimally, ICCV 2013.! A. P. Bustos, T.-J. Chin, D. Suter,! Fast Rotation Search with Stereographic Projections for 3D Registration, CVPR 2014.!

59 As a subroutine for two-view epipolar geometry Applications of 3D Rotation Estimation! O. Enqvist, F. Kahl,! Two-View Geometry Estimation with Outliers, BMVC 2009.! J. Yang, H. Li, Y. Jia,! Optimal Essential Matrix Estimation via Inlier-Set Maximization, ECCV 2014.!

60 Conclusions! - Branch-and-bound practical for small dimensions only - Good bounding functions important - Worst-case performance exponential!

Optimal Relative Pose with Unknown Correspondences

Optimal Relative Pose with Unknown Correspondences Optimal Relative Pose with Unknown Correspondences Johan Fredriksson 1,Viktor Larsson 1, Carl Olsson 1 and Fredrik Kahl 1,2 1 Lund University, Sweden 2 Chalmers University of Technology, Sweden {johanf,

More information

Accurate Localization and Pose Estimation for Large 3D Models

Accurate Localization and Pose Estimation for Large 3D Models Accurate Localization and Pose Estimation for Large 3D Models Linus Svärm 1 Olof Enqvist 2 1 Centre for Mathematical Sciences Lund University, Sweden {linus,magnuso}@maths.lth.se Magnus Oskarsson 1 Fredrik

More information

Fast and Reliable Two-View Translation Estimation

Fast and Reliable Two-View Translation Estimation Fast and Reliable Two-View Translation Estimation Johan Fredriksson 1 1 Centre for Mathematical Sciences Lund University, Sweden johanf@maths.lth.se Olof Enqvist 2 Fredrik Kahl 1,2 2 Department of Signals

More information

City-Scale Localization for Cameras with Known Vertical Direction

City-Scale Localization for Cameras with Known Vertical Direction 1 City-Scale Localization for Cameras with Known Vertical Direction Linus Svärm, Olof Enqvist, Fredrik Kahl, Magnus Oskarsson Abstract We consider the problem of localizing a novel image in a large 3D

More information

Guaranteed Outlier Removal for Rotation Search

Guaranteed Outlier Removal for Rotation Search Guaranteed Outlier Removal for Rotation Search Álvaro Parra Bustos Tat-Jun Chin School of Computer Science, The University of Adelaide, South Australia {aparra, tjchin}@cs.adelaide.edu.au Abstract Rotation

More information

Motion Estimation for Multi-Camera Systems using Global Optimization

Motion Estimation for Multi-Camera Systems using Global Optimization Motion Estimation for Multi-Camera Systems using Global Optimization Jae-Hak Kim, Hongdong Li, Richard Hartley The Australian National University and NICTA {Jae-Hak.Kim, Hongdong.Li, Richard.Hartley}@anu.edu.au

More information

Optimisation in Multiple View Geometry: The L-infinity Way (Part 2)

Optimisation in Multiple View Geometry: The L-infinity Way (Part 2) Optimisation in Multiple View Geometry: The L-infinity Way (Part 2) Tat-Jun Chin The University of Adelaide CVPR 2018 Tutorial Tat-Jun Chin (The University of Adelaide) Optimisation in Multiple View Geometry

More information

Structure from Motion. Introduction to Computer Vision CSE 152 Lecture 10

Structure from Motion. Introduction to Computer Vision CSE 152 Lecture 10 Structure from Motion CSE 152 Lecture 10 Announcements Homework 3 is due May 9, 11:59 PM Reading: Chapter 8: Structure from Motion Optional: Multiple View Geometry in Computer Vision, 2nd edition, Hartley

More information

arxiv: v1 [cs.cv] 18 Sep 2017

arxiv: v1 [cs.cv] 18 Sep 2017 Direct Pose Estimation with a Monocular Camera Darius Burschka and Elmar Mair arxiv:1709.05815v1 [cs.cv] 18 Sep 2017 Department of Informatics Technische Universität München, Germany {burschka elmar.mair}@mytum.de

More information

Go-ICP: Solving 3D Registration Efficiently and Globally Optimally

Go-ICP: Solving 3D Registration Efficiently and Globally Optimally Go-: Solving 3D Registration Efficiently and Globally Optimally Jiaolong Yang 1,2, Hongdong Li 2, Yunde Jia 1 1 Beijing Lab of Intelligent Information Technology, Beijing Institute of Technology 2 Australian

More information

Two View Geometry Estimation with Outliers

Two View Geometry Estimation with Outliers ENQVIST, KAHL: TWO VIEW GEOMETRY ESTIMATION WITH OUTLIERS 1 Two View Geometry Estimation with Outliers Olof Enqvist www.maths.lth.se/vision/people/olofe Fredrik Kahl www.maths.lth.se/vision/people/fredrik

More information

Global Optimization through Rotation Space Search

Global Optimization through Rotation Space Search Global Optimization through Rotation Space Search Richard I. Hartley Australian National University and National ICT Australia Fredrik Kahl Centre for Mathematical Sciences Lund University, Sweden. Abstract

More information

Visual Odometry for Non-Overlapping Views Using Second-Order Cone Programming

Visual Odometry for Non-Overlapping Views Using Second-Order Cone Programming Visual Odometry for Non-Overlapping Views Using Second-Order Cone Programming Jae-Hak Kim 1, Richard Hartley 1, Jan-Michael Frahm 2 and Marc Pollefeys 2 1 Research School of Information Sciences and Engineering

More information

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 263

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 263 Index 3D reconstruction, 125 5+1-point algorithm, 284 5-point algorithm, 270 7-point algorithm, 265 8-point algorithm, 263 affine point, 45 affine transformation, 57 affine transformation group, 57 affine

More information

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 253

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 253 Index 3D reconstruction, 123 5+1-point algorithm, 274 5-point algorithm, 260 7-point algorithm, 255 8-point algorithm, 253 affine point, 43 affine transformation, 55 affine transformation group, 55 affine

More information

Para-catadioptric Camera Auto Calibration from Epipolar Geometry

Para-catadioptric Camera Auto Calibration from Epipolar Geometry Para-catadioptric Camera Auto Calibration from Epipolar Geometry Branislav Mičušík and Tomáš Pajdla Center for Machine Perception http://cmp.felk.cvut.cz Department of Cybernetics Faculty of Electrical

More information

Robust Rotation Search in Computer Vision

Robust Rotation Search in Computer Vision Doctoral Thesis Robust Rotation Search in Computer Vision Author: Álvaro Joaquín Parra Bustos Supervisors: Dr. Tat-Jun CHIN Prof. David SUTER A thesis submitted in fulfilment of the requirements for the

More information

SELF-CALIBRATION OF CENTRAL CAMERAS BY MINIMIZING ANGULAR ERROR

SELF-CALIBRATION OF CENTRAL CAMERAS BY MINIMIZING ANGULAR ERROR SELF-CALIBRATION OF CENTRAL CAMERAS BY MINIMIZING ANGULAR ERROR Juho Kannala, Sami S. Brandt and Janne Heikkilä Machine Vision Group, University of Oulu, Finland {jkannala, sbrandt, jth}@ee.oulu.fi Keywords:

More information

Vision par ordinateur

Vision par ordinateur Epipolar geometry π Vision par ordinateur Underlying structure in set of matches for rigid scenes l T 1 l 2 C1 m1 l1 e1 M L2 L1 e2 Géométrie épipolaire Fundamental matrix (x rank 2 matrix) m2 C2 l2 Frédéric

More information

calibrated coordinates Linear transformation pixel coordinates

calibrated coordinates Linear transformation pixel coordinates 1 calibrated coordinates Linear transformation pixel coordinates 2 Calibration with a rig Uncalibrated epipolar geometry Ambiguities in image formation Stratified reconstruction Autocalibration with partial

More information

Iterative Reweighted Least Squares

Iterative Reweighted Least Squares Iterative Reweighted Least Squares ECCV, Sept 7, 2014 120 120 120 What point minimizes the distance to the three points of a triangle? Exercise: find this point using ruler and compass construction. Toricelli

More information

3D Reconstruction from Scene Knowledge

3D Reconstruction from Scene Knowledge Multiple-View Reconstruction from Scene Knowledge 3D Reconstruction from Scene Knowledge SYMMETRY & MULTIPLE-VIEW GEOMETRY Fundamental types of symmetry Equivalent views Symmetry based reconstruction MUTIPLE-VIEW

More information

Fast Rotation Search with Stereographic Projections for 3D Registration

Fast Rotation Search with Stereographic Projections for 3D Registration Fast Rotation Search with Stereographic Proections for 3D Registration Álvaro Parra Bustos, Tat-Jun Chin and David Suter School of Computer Science, The University of Adelaide {aparra, tchin, dsuter}@cs.adelaide.edu.au

More information

Image stitching. Digital Visual Effects Yung-Yu Chuang. with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac

Image stitching. Digital Visual Effects Yung-Yu Chuang. with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac Image stitching Digital Visual Effects Yung-Yu Chuang with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac Image stitching Stitching = alignment + blending geometrical registration

More information

Optimal Essential Matrix Estimation via Inlier-Set Maximization

Optimal Essential Matrix Estimation via Inlier-Set Maximization Optimal Essential Matrix Estimation via Inlier-Set Maximization Jiaolong Yang 1,2, Hongdong Li 2, and Yunde Jia 1 1 Beijing Laboratory of Intelligent Information Technology, Beijing Institute of Technology,

More information

3D Modeling using multiple images Exam January 2008

3D Modeling using multiple images Exam January 2008 3D Modeling using multiple images Exam January 2008 All documents are allowed. Answers should be justified. The different sections below are independant. 1 3D Reconstruction A Robust Approche Consider

More information

Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration

Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration 1 Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration Jiaolong Yang, Hongdong Li, Dylan Campbell, and Yunde Jia arxiv:165.3344v1 [cs.cv] 11 May 216 Abstract The Iterative Closest Point

More information

Instance-level recognition part 2

Instance-level recognition part 2 Visual Recognition and Machine Learning Summer School Paris 2011 Instance-level recognition part 2 Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique,

More information

P2Π: A Minimal Solution for Registration of 3D Points to 3D Planes

P2Π: A Minimal Solution for Registration of 3D Points to 3D Planes P2Π: A Minimal Solution for Registration of 3D Points to 3D Planes Srikumar Ramalingam, Yuichi Taguchi, Tim K. Marks, and Oncel Tuzel Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA

More information

EE795: Computer Vision and Intelligent Systems

EE795: Computer Vision and Intelligent Systems EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 10 130221 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Canny Edge Detector Hough Transform Feature-Based

More information

Exercise session using MATLAB: Quasiconvex Optimixation

Exercise session using MATLAB: Quasiconvex Optimixation Optimization in Computer Vision, May 2008 Exercise session using MATLAB: Quasiconvex Optimixation Overview In this laboratory session you are going to use matlab to study structure and motion estimation

More information

A New Minimal Solution to the Relative Pose of a Calibrated Stereo Camera with Small Field of View Overlap

A New Minimal Solution to the Relative Pose of a Calibrated Stereo Camera with Small Field of View Overlap A New Minimal Solution to the Relative Pose of a Calibrated Stereo Camera with Small Field of View Overlap Brian Clipp 1, Christopher Zach 1, Jan-Michael Frahm 1 and Marc Pollefeys 2 1 Department of Computer

More information

An Iterative 5-pt Algorithm for Fast and Robust Essential Matrix Estimation

An Iterative 5-pt Algorithm for Fast and Robust Essential Matrix Estimation LUI, DRUMMOND: ITERATIVE 5-PT ALGORITHM 1 An Iterative 5-pt Algorithm for Fast and Robust Essential Matrix Estimation Vincent Lui Tom Drummond Department of Electrical & Computer Systems Engineering Monash

More information

Parameter estimation. Christiano Gava Gabriele Bleser

Parameter estimation. Christiano Gava Gabriele Bleser Parameter estimation Christiano Gava Christiano.Gava@dfki.de Gabriele Bleser gabriele.bleser@dfki.de Introduction Previous lectures: P-matrix 2D projective transformations Estimation (direct linear transform)

More information

Semantic Match Consistency for Long-Term Visual Localization - Supplementary Material

Semantic Match Consistency for Long-Term Visual Localization - Supplementary Material Semantic Match Consistency for Long-Term Visual Localization - Supplementary Material Carl Toft 1, Erik Stenborg 1, Lars Hammarstrand 1, Lucas Brynte 1, Marc Pollefeys 2,3, Torsten Sattler 2, Fredrik Kahl

More information

On-line Convex Optimization based Solution for Mapping in VSLAM

On-line Convex Optimization based Solution for Mapping in VSLAM On-line Convex Optimization based Solution for Mapping in VSLAM by Abdul Hafeez, Shivudu Bhuvanagiri, Madhava Krishna, C.V.Jawahar in IROS-2008 (Intelligent Robots and Systems) Report No: IIIT/TR/2008/178

More information

arxiv: v1 [cs.cv] 28 Sep 2018

arxiv: v1 [cs.cv] 28 Sep 2018 Camera Pose Estimation from Sequence of Calibrated Images arxiv:1809.11066v1 [cs.cv] 28 Sep 2018 Jacek Komorowski 1 and Przemyslaw Rokita 2 1 Maria Curie-Sklodowska University, Institute of Computer Science,

More information

Two Efficient Algorithms for Outlier Removal in Multi-view Geometry Using L Norm

Two Efficient Algorithms for Outlier Removal in Multi-view Geometry Using L Norm Two Efficient Algorithms for Outlier Removal in Multi-view Geometry Using L Norm Yuchao Dai 1, Mingyi He 1 Hongdong Li 3, 1 School of Electronics and Information, Northwestern Polytechnical University

More information

Minimal Solutions for Generic Imaging Models

Minimal Solutions for Generic Imaging Models Minimal Solutions for Generic Imaging Models Srikumar Ramalingam Peter Sturm Oxford Brookes University, UK INRIA Grenoble Rhône-Alpes, France Abstract A generic imaging model refers to a non-parametric

More information

RANSAC and some HOUGH transform

RANSAC and some HOUGH transform RANSAC and some HOUGH transform Thank you for the slides. They come mostly from the following source Dan Huttenlocher Cornell U Matching and Fitting Recognition and matching are closely related to fitting

More information

Instance-level recognition II.

Instance-level recognition II. Reconnaissance d objets et vision artificielle 2010 Instance-level recognition II. Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique, Ecole Normale

More information

Summary Page Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems

Summary Page Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems Summary Page Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems Is this a system paper or a regular paper? This is a regular paper. What is the main contribution in terms of theory,

More information

CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry

CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry Some material taken from: David Lowe, UBC Jiri Matas, CMP Prague http://cmp.felk.cvut.cz/~matas/papers/presentations/matas_beyondransac_cvprac05.ppt

More information

Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence

Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence Dylan Campbell,2, Lars Petersson,2, Laurent Kneip and Hongdong Li 2 Australian National University* Data6

More information

Estimation of Camera Pose with Respect to Terrestrial LiDAR Data

Estimation of Camera Pose with Respect to Terrestrial LiDAR Data Estimation of Camera Pose with Respect to Terrestrial LiDAR Data Wei Guan Suya You Guan Pang Computer Science Department University of Southern California, Los Angeles, USA Abstract In this paper, we present

More information

Camera Pose Voting for Large-Scale Image-Based Localization

Camera Pose Voting for Large-Scale Image-Based Localization Camera Pose Voting for Large-Scale Image-Based Localization Bernhard Zeisl Torsten Sattler Marc Pollefeys Department of Computer Science, ETH Zurich, Switzerland {bernhard.zeisl,torsten.sattler,marc.pollefeys}@inf.ethz.ch

More information

Introduction to Computer Vision

Introduction to Computer Vision Introduction to Computer Vision Michael J. Black Nov 2009 Perspective projection and affine motion Goals Today Perspective projection 3D motion Wed Projects Friday Regularization and robust statistics

More information

Image Stitching. Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi

Image Stitching. Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi Image Stitching Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi Combine two or more overlapping images to make one larger image Add example Slide credit: Vaibhav Vaish

More information

Pose Estimation with Unknown Focal Length using Points, Directions and Lines

Pose Estimation with Unknown Focal Length using Points, Directions and Lines 3 IEEE International Conference on Computer Vision Pose Estimation with Unknown Focal Length using Points, Directions and Lines Yubin Kuang, Kalle Åström Centre for Mathematical Sciences Lund University

More information

Comments on Consistent Depth Maps Recovery from a Video Sequence

Comments on Consistent Depth Maps Recovery from a Video Sequence Comments on Consistent Depth Maps Recovery from a Video Sequence N.P. van der Aa D.S. Grootendorst B.F. Böggemann R.T. Tan Technical Report UU-CS-2011-014 May 2011 Department of Information and Computing

More information

Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems

Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems Brian Clipp 1, Jae-Hak Kim 2, Jan-Michael Frahm 1, Marc Pollefeys 3 and Richard Hartley 2 1 Department of Computer Science 2 Research

More information

CS6670: Computer Vision

CS6670: Computer Vision CS6670: Computer Vision Noah Snavely Lecture 7: Image Alignment and Panoramas What s inside your fridge? http://www.cs.washington.edu/education/courses/cse590ss/01wi/ Projection matrix intrinsics projection

More information

Learning-based Localization

Learning-based Localization Learning-based Localization Eric Brachmann ECCV 2018 Tutorial on Visual Localization - Feature-based vs. Learned Approaches Torsten Sattler, Eric Brachmann Roadmap Machine Learning Basics [10min] Convolutional

More information

Step-by-Step Model Buidling

Step-by-Step Model Buidling Step-by-Step Model Buidling Review Feature selection Feature selection Feature correspondence Camera Calibration Euclidean Reconstruction Landing Augmented Reality Vision Based Control Sparse Structure

More information

CSE 252B: Computer Vision II

CSE 252B: Computer Vision II CSE 252B: Computer Vision II Lecturer: Serge Belongie Scribes: Jeremy Pollock and Neil Alldrin LECTURE 14 Robust Feature Matching 14.1. Introduction Last lecture we learned how to find interest points

More information

Optimal Algorithms in Multiview Geometry

Optimal Algorithms in Multiview Geometry Optimal Algorithms in Multiview Geometry Richard Hartley 1 and Fredrik Kahl 2 1 Research School of Information Sciences and Engineering, The Australian National University National ICT Australia (NICTA)

More information

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter

More information

Generalized Principal Component Analysis CVPR 2007

Generalized Principal Component Analysis CVPR 2007 Generalized Principal Component Analysis Tutorial @ CVPR 2007 Yi Ma ECE Department University of Illinois Urbana Champaign René Vidal Center for Imaging Science Institute for Computational Medicine Johns

More information

Feature Transfer and Matching in Disparate Stereo Views through the use of Plane Homographies

Feature Transfer and Matching in Disparate Stereo Views through the use of Plane Homographies Feature Transfer and Matching in Disparate Stereo Views through the use of Plane Homographies M. Lourakis, S. Tzurbakis, A. Argyros, S. Orphanoudakis Computer Vision and Robotics Lab (CVRL) Institute of

More information

Model Fitting. Introduction to Computer Vision CSE 152 Lecture 11

Model Fitting. Introduction to Computer Vision CSE 152 Lecture 11 Model Fitting CSE 152 Lecture 11 Announcements Homework 3 is due May 9, 11:59 PM Reading: Chapter 10: Grouping and Model Fitting What to do with edges? Segment linked edge chains into curve features (e.g.,

More information

Fast and stable algebraic solution to L 2 three-view triangulation

Fast and stable algebraic solution to L 2 three-view triangulation Fast and stable algebraic solution to L 2 three-view triangulation Zuzana Kukelova, Tomas Pajdla Czech Technical University, Faculty of Electrical Engineering, Karlovo namesti 13, Prague, Czech Republic

More information

Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image - Supplementary Material -

Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image - Supplementary Material - Uncertainty-Driven 6D Pose Estimation of s and Scenes from a Single RGB Image - Supplementary Material - Eric Brachmann*, Frank Michel, Alexander Krull, Michael Ying Yang, Stefan Gumhold, Carsten Rother

More information

Stereo and Epipolar geometry

Stereo and Epipolar geometry Previously Image Primitives (feature points, lines, contours) Today: Stereo and Epipolar geometry How to match primitives between two (multiple) views) Goals: 3D reconstruction, recognition Jana Kosecka

More information

Globally Optimal Manhattan Frame Estimation in Real-time

Globally Optimal Manhattan Frame Estimation in Real-time Globally Optimal Manhattan Frame Estimation in Real-time Kyungdon Joo Tae-Hyun Oh Junsik Kim In So Kweon Robotics and Computer Vision Lab., KAIST, South Korea {kdjoo369, thoh.kaist.ac.kr, mibastro}@gmail.com,

More information

CHAPTER 3. Single-view Geometry. 1. Consequences of Projection

CHAPTER 3. Single-view Geometry. 1. Consequences of Projection CHAPTER 3 Single-view Geometry When we open an eye or take a photograph, we see only a flattened, two-dimensional projection of the physical underlying scene. The consequences are numerous and startling.

More information

Camera Registration in a 3D City Model. Min Ding CS294-6 Final Presentation Dec 13, 2006

Camera Registration in a 3D City Model. Min Ding CS294-6 Final Presentation Dec 13, 2006 Camera Registration in a 3D City Model Min Ding CS294-6 Final Presentation Dec 13, 2006 Goal: Reconstruct 3D city model usable for virtual walk- and fly-throughs Virtual reality Urban planning Simulation

More information

An L Approach to Structure and Motion Problems in 1D-Vision

An L Approach to Structure and Motion Problems in 1D-Vision An L Approach to Structure and Motion Problems in D-Vision Kalle Åström, Olof Enquist, Carl Olsson, Fredrik Kahl Centre for Mathematical Sciences, Lund University, Sweden P.O. Box 8, SE- Lund, Sweden (kalle,olofe,calle,fredrik)@maths.lth.se

More information

Unit 3 Multiple View Geometry

Unit 3 Multiple View Geometry Unit 3 Multiple View Geometry Relations between images of a scene Recovering the cameras Recovering the scene structure http://www.robots.ox.ac.uk/~vgg/hzbook/hzbook1.html 3D structure from images Recover

More information

A Factorization Method for Structure from Planar Motion

A Factorization Method for Structure from Planar Motion A Factorization Method for Structure from Planar Motion Jian Li and Rama Chellappa Center for Automation Research (CfAR) and Department of Electrical and Computer Engineering University of Maryland, College

More information

Computer Vision I - Algorithms and Applications: Multi-View 3D reconstruction

Computer Vision I - Algorithms and Applications: Multi-View 3D reconstruction Computer Vision I - Algorithms and Applications: Multi-View 3D reconstruction Carsten Rother 09/12/2013 Computer Vision I: Multi-View 3D reconstruction Roadmap this lecture Computer Vision I: Multi-View

More information

Simultaneous Pose, Focal Length and 2D-to-3D Correspondences from Noisy Observations

Simultaneous Pose, Focal Length and 2D-to-3D Correspondences from Noisy Observations PENATE-SANCHEZ ET AL.: BMVC AUTHOR GUIDELINES 1 Simultaneous Pose, Focal Length and 2D-to-3D Correspondences from Noisy Observations Adrian Penate-Sanchez apenate@iri.upc.edu Eduard Serradell eserradell@iri.upc.edu

More information

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University. 3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction

More information

Structure from motion

Structure from motion Structure from motion Structure from motion Given a set of corresponding points in two or more images, compute the camera parameters and the 3D point coordinates?? R 1,t 1 R 2,t R 2 3,t 3 Camera 1 Camera

More information

Instance-level recognition

Instance-level recognition Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction

More information

RANSAC: RANdom Sampling And Consensus

RANSAC: RANdom Sampling And Consensus CS231-M RANSAC: RANdom Sampling And Consensus Roland Angst rangst@stanford.edu www.stanford.edu/~rangst CS231-M 2014-04-30 1 The Need for RANSAC Why do I need RANSAC? I know robust statistics! Robust Statistics

More information

Practical Camera Auto Calibration using Semidefinite Programming

Practical Camera Auto Calibration using Semidefinite Programming Practical Camera Auto Calibration using Semidefinite Programming Motilal Agrawal SRI International 333 Ravenswood Ave. Menlo Park, CA 94025 agrawal@ai.sri.com Abstract We describe a novel approach to the

More information

Homographies and RANSAC

Homographies and RANSAC Homographies and RANSAC Computer vision 6.869 Bill Freeman and Antonio Torralba March 30, 2011 Homographies and RANSAC Homographies RANSAC Building panoramas Phototourism 2 Depth-based ambiguity of position

More information

Instance-level recognition

Instance-level recognition Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction

More information

Critical Configurations For Radial Distortion Self-Calibration

Critical Configurations For Radial Distortion Self-Calibration Critical Configurations For Radial Distortion Self-Calibration Changchang Wu Google Inc. Abstract In this paper, we study the configurations of motion and structure that lead to inherent ambiguities in

More information

Instance-level recognition I. - Camera geometry and image alignment

Instance-level recognition I. - Camera geometry and image alignment Reconnaissance d objets et vision artificielle 2011 Instance-level recognition I. - Camera geometry and image alignment Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire

More information

Rectification for Any Epipolar Geometry

Rectification for Any Epipolar Geometry Rectification for Any Epipolar Geometry Daniel Oram Advanced Interfaces Group Department of Computer Science University of Manchester Mancester, M13, UK oramd@cs.man.ac.uk Abstract This paper proposes

More information

Generic and Real-Time Structure from Motion

Generic and Real-Time Structure from Motion Generic and Real-Time Structure from Motion E. Mouragnon 1,2, M. Lhuillier 1, M. Dhome 1, F. Dekeyser 2 and P. Sayd 2 1 LASMEA UMR 6602, Université Blaise Pascal/CNRS, 63177 Aubière Cedex, France 2 CEA,

More information

Planar Scene Modeling from Quasiconvex Subproblems

Planar Scene Modeling from Quasiconvex Subproblems Planar Scene Modeling from Quasiconvex Subproblems by Visesh Chari, Anil Kumar Nelakantji, Chetan Jakkoju, C V Jawahar in ACCV 29 (Asian Conference on Computer Vision) Report No: IIIT/TR/29/228 Centre

More information

CS 231A Computer Vision (Winter 2014) Problem Set 3

CS 231A Computer Vision (Winter 2014) Problem Set 3 CS 231A Computer Vision (Winter 2014) Problem Set 3 Due: Feb. 18 th, 2015 (11:59pm) 1 Single Object Recognition Via SIFT (45 points) In his 2004 SIFT paper, David Lowe demonstrates impressive object recognition

More information

Part II: OUTLINE. Visualizing Quaternions. Part II: Visualizing Quaternion Geometry. The Spherical Projection Trick: Visualizing unit vectors.

Part II: OUTLINE. Visualizing Quaternions. Part II: Visualizing Quaternion Geometry. The Spherical Projection Trick: Visualizing unit vectors. Visualizing Quaternions Part II: Visualizing Quaternion Geometry Andrew J. Hanson Indiana University Part II: OUTLINE The Spherical Projection Trick: Visualizing unit vectors. Quaternion Frames Quaternion

More information

Lecture 9: Epipolar Geometry

Lecture 9: Epipolar Geometry Lecture 9: Epipolar Geometry Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Why is stereo useful? Epipolar constraints Essential and fundamental matrix Estimating F (Problem Set 2

More information

A simple method for interactive 3D reconstruction and camera calibration from a single view

A simple method for interactive 3D reconstruction and camera calibration from a single view A simple method for interactive 3D reconstruction and camera calibration from a single view Akash M Kushal Vikas Bansal Subhashis Banerjee Department of Computer Science and Engineering Indian Institute

More information

Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search

Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search Yinlong Liu 1,2 [0000 0002 6468 8233], Chen Wang 1,2 [0000 0003 2922 5345], Zhijian Song 1,2

More information

3D Hyperbolic Tiling and Horosphere Cross Section

3D Hyperbolic Tiling and Horosphere Cross Section 3D Hyperbolic Tiling and Horosphere Cross Section Vladimir Bulatov, Shapeways Joint AMS/MAA meeting San Diego, January 10, 2018 Inversive Geometry Convenient container to work with 3 dimensional hyperbolic

More information

Large Scale 3D Reconstruction by Structure from Motion

Large Scale 3D Reconstruction by Structure from Motion Large Scale 3D Reconstruction by Structure from Motion Devin Guillory Ziang Xie CS 331B 7 October 2013 Overview Rome wasn t built in a day Overview of SfM Building Rome in a Day Building Rome on a Cloudless

More information

Fitting. Fitting. Slides S. Lazebnik Harris Corners Pkwy, Charlotte, NC

Fitting. Fitting. Slides S. Lazebnik Harris Corners Pkwy, Charlotte, NC 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 in the image by grouping multiple features according

More information

CS231A Midterm Review. Friday 5/6/2016

CS231A Midterm Review. Friday 5/6/2016 CS231A Midterm Review Friday 5/6/2016 Outline General Logistics Camera Models Non-perspective cameras Calibration Single View Metrology Epipolar Geometry Structure from Motion Active Stereo and Volumetric

More information

Personal Navigation and Indoor Mapping: Performance Characterization of Kinect Sensor-based Trajectory Recovery

Personal Navigation and Indoor Mapping: Performance Characterization of Kinect Sensor-based Trajectory Recovery Personal Navigation and Indoor Mapping: Performance Characterization of Kinect Sensor-based Trajectory Recovery 1 Charles TOTH, 1 Dorota BRZEZINSKA, USA 2 Allison KEALY, Australia, 3 Guenther RETSCHER,

More information

Surface Registration. Gianpaolo Palma

Surface Registration. Gianpaolo Palma Surface Registration Gianpaolo Palma The problem 3D scanning generates multiple range images Each contain 3D points for different parts of the model in the local coordinates of the scanner Find a rigid

More information

An Original Approach for Automatic Plane Extraction by Omnidirectional Vision

An Original Approach for Automatic Plane Extraction by Omnidirectional Vision The 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems October 18-22, 2010, Taipei, Taiwan An Original Approach for Automatic Plane Extraction by Omnidirectional Vision Jean-Charles

More information

Answer Key: Three-Dimensional Cross Sections

Answer Key: Three-Dimensional Cross Sections Geometry A Unit Answer Key: Three-Dimensional Cross Sections Name Date Objectives In this lesson, you will: visualize three-dimensional objects from different perspectives be able to create a projection

More information

Today s lecture. Image Alignment and Stitching. Readings. Motion models

Today s lecture. Image Alignment and Stitching. Readings. Motion models Today s lecture Image Alignment and Stitching Computer Vision CSE576, Spring 2005 Richard Szeliski Image alignment and stitching motion models cylindrical and spherical warping point-based alignment global

More information

Multiple View Geometry in Computer Vision Second Edition

Multiple View Geometry in Computer Vision Second Edition Multiple View Geometry in Computer Vision Second Edition Richard Hartley Australian National University, Canberra, Australia Andrew Zisserman University of Oxford, UK CAMBRIDGE UNIVERSITY PRESS Contents

More information

L minimization in geometric reconstruction problems. Abstract. 1 The triangulation problem. Richard Hartley 1,2 and Frederik Schaffalitzky 2,3

L minimization in geometric reconstruction problems. Abstract. 1 The triangulation problem. Richard Hartley 1,2 and Frederik Schaffalitzky 2,3 L minimization in geometric reconstruction problems Richard Hartley 1,2 and Frederik Schaffalitzky 2,3 1 National ICT Australia 2 The Australian National University 3 Oxford University Abstract We investigate

More information

Visual Odometry. Features, Tracking, Essential Matrix, and RANSAC. Stephan Weiss Computer Vision Group NASA-JPL / CalTech

Visual Odometry. Features, Tracking, Essential Matrix, and RANSAC. Stephan Weiss Computer Vision Group NASA-JPL / CalTech Visual Odometry Features, Tracking, Essential Matrix, and RANSAC Stephan Weiss Computer Vision Group NASA-JPL / CalTech Stephan.Weiss@ieee.org (c) 2013. Government sponsorship acknowledged. Outline The

More information