EE 7730 Parametric Motion Estimation. Bahadir K. Gunturk2 Parametric (Global) Motion Affine Flow.

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.
Computer Vision TexPoint fonts used in EMF: AAA Niels Chr Overgaard 2010 Lecture 8: Structure from Motion RANSAC Structure from motion problem Structure.
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
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)
Computer Vision Optical Flow
Medical Imaging Mohammad Dawood Department of Computer Science University of Münster Germany.
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.
CSCE 641:Computer Graphics Image Warping/Registration Jinxiang Chai.
Geometric Optimization Problems in Computer Vision.
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
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
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2006 with a lot of slides stolen from Steve Seitz and.
Computational Photography: Image Registration Jinxiang Chai.
Robust estimation Problem: we want to determine the displacement (u,v) between pairs of images. We are given 100 points with a correlation score computed.
Lecture 10: Robust fitting CS4670: Computer Vision Noah Snavely.
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.
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.
Computer Vision - Fitting and Alignment
Advanced Computer Vision Feature-based Alignment Lecturer: Lu Yi & Prof. Fuh CSIE NTU.
Example: line fitting. n=2 Model fitting Measure distances.
Image Stitching Ali Farhadi CSE 576 Several slides from Rick Szeliski, Steve Seitz, Derek Hoiem, and Ira Kemelmacher.
Computing F. Content Background: Projective geometry (2D, 3D), Parameter estimation, Algorithm evaluation. Single View: Camera model, Calibration, Single.
Computer Vision : CISC 4/689 Going Back a little Cameras.ppt.
Medical Image Analysis Dr. Mohammad Dawood Department of Computer Science University of Münster Germany.
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
Computer Vision - Fitting and Alignment (Slides borrowed from various presentations)
Fitting image transformations Prof. Noah Snavely CS1114
Robust Estimation Course web page: vision.cis.udel.edu/~cv April 23, 2003  Lecture 25.
Fitting.
COS 429 PS3: Stitching a Panorama Due November 10 th.
Computer Photography -Scene Fixed 陳立奇.
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.
SIFT Scale-Invariant Feature Transform David Lowe
University of Ioannina
Fitting a transformation: feature-based alignment
CPSC 641: Image Registration
Line Fitting James Hayes.
Exercise Class 11: Robust Tecuniques RANSAC, Hough Transform
A Brief Introduction of RANSAC
Lecture 7: Image alignment
RANSAC and mosaic wrap-up
A special case of calibration
Image Stitching Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi.
Features Readings All is Vanity, by C. Allan Gilbert,
SIFT.
Introduction to Sensor Interpretation
Introduction to Sensor Interpretation
Calibration and homographies
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:

EE 7730 Parametric Motion Estimation

Bahadir K. Gunturk2 Parametric (Global) Motion Affine Flow

Bahadir K. Gunturk3 Parametric (Global) Motion Perspective flow

Bahadir K. Gunturk4

5

6

7

8

EE 7730 RANSAC: RANdom SAmple Consensus

Bahadir K. Gunturk10 Outliers Consider the least squares fit for optical flow: If some of the values are wrong, it will degrade the estimation.

Bahadir K. Gunturk11 Outliers It is best not to include outliers in the estimation. Outliers Best fit is degraded due to the outliers Line Fitting Problem: Given (x1,y1), …, (xN,yN); find the line y=ax+b

Bahadir K. Gunturk12 Robust Estimation Two step process:  Classify data points as outliers or inliers  Use inliers only to fit a model

Bahadir K. Gunturk13 RANSAC Repeat for k times:  Randomly choose n points (the smallest number of points required) from the data.  Estimate the parameters using these points.  For each data point other than these n points: Check if the data point is within a threshold, t, distance of current model; if it is, the data point is consistent with current model. The total number of data points that are consistent is model’s support. If the support is larger than a predetermined number, d, then there is a good fit. Re-estimate the parameters using these inliers. Choose the best fit with the smallest fitting error.

Bahadir K. Gunturk14 RANSAC Two samples and their supports for line-fitting

Bahadir K. Gunturk15 Example Find the perspective parameters from Hartley & Zisserman

Bahadir K. Gunturk16 Example Apply corner detectors to both images from Hartley & Zisserman

Bahadir K. Gunturk17 Example Find the best match within a search window. from Hartley & Zisserman

Bahadir K. Gunturk18 Example Initial match results 188 matched features in left image pointing to locations of corresponding right image features from Hartley & Zisserman

Bahadir K. Gunturk19 Example Inliers and outliers after RANSAC 89 outliers 99 inliers from Hartley & Zisserman

Bahadir K. Gunturk20 Panoramic Image Reconstruction Application: Mosaic construction Find features Match features Fit parametric model