39
Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

  • View
    219

  • Download
    1

Embed Size (px)

Citation preview

Page 1: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Assignment 2Compute F automatically from image

pair

(putative matches, 8-point, 7-point, iterative, RANSAC, guided matching)

(due by Wednesday 19/03/03)

Page 2: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Rectification and structure computation

class 15

Multiple View GeometryComp 290-089Marc Pollefeys

Page 3: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Multiple View Geometry course schedule(subject to change)

Jan. 7, 9 Intro & motivation Projective 2D Geometry

Jan. 14, 16

(no class) Projective 2D Geometry

Jan. 21, 23

Projective 3D Geometry (no class)

Jan. 28, 30

Parameter Estimation Parameter Estimation

Feb. 4, 6 Algorithm Evaluation Camera Models

Feb. 11, 13

Camera Calibration Single View Geometry

Feb. 18, 20

Epipolar Geometry 3D reconstruction

Feb. 25, 27

Fund. Matrix Comp. Fund. Matrix Comp.

Mar. 4, 6 Structure Comp. Planes & Homographies

Mar. 18, 20

Trifocal Tensor Three View Reconstruction

Mar. 25, 27

Multiple View Geometry

MultipleView Reconstruction

Apr. 1, 3 Bundle adjustment Papers

Apr. 8, 10

Auto-Calibration Papers

Apr. 15, 17

Dynamic SfM Papers

Apr. 22, 24

Cheirality Project Demos

Page 4: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Two-view geometry

Epipolar geometry

3D reconstruction

F-matrix comp.

Structure comp.

Page 5: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Automatic computation of F

(i) Interest points(ii) Putative correspondences(iii) RANSAC (iv) Non-linear re-estimation of F(v) Guided matching(repeat (iv) and (v) until stable)

Page 6: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Select strongest features (e.g. 1000/image)

Feature points

Page 7: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Evaluate ZNCC,SSD,SAD for all features with similar coordinates

Keep mutual best matchesKeep mutual best matches

Still many wrong matches!Still many wrong matches!

10101010 ,,´´, e.g. hhww yyxxyx

?

Feature matching

Page 8: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Step 1. Extract featuresStep 2. Compute a set of potential matchesStep 3. do

Step 3.1 select minimal sample (i.e. 7 matches)

Step 3.2 compute solution(s) for F

Step 3.3 determine inliers

until (#inliers,#samples)<95%

samples#7)1(1

matches#inliers#

#inliers 90%

80%

70% 60%

50%

#samples

5 13 35 106 382

Step 4. Compute F based on all inliersStep 5. Look for additional matchesStep 6. Refine F based on all correct matches

(generate hypothesis)

(verify hypothesis)

RANSAC

Page 9: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

restrict search range to neighborhood of epipolar line (1.5 pixels)

relax disparity restriction (along epipolar line)

Finding more matches: guided matching

Page 10: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

geometric relations between two views is fully

described by recovered 3x3 matrix F

two-view geometry

Page 11: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Image pair rectification

simplify stereo matching by warping the images

Apply projective transformation so that epipolar linescorrespond to horizontal scanlines

e

e

map epipole e to (1,0,0)

try to minimize image distortion

problem when epipole in (or close to) the image

He001

Page 12: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Planar rectification

Bring two views Bring two views to standard stereo setupto standard stereo setup

(moves epipole to )(not possible when in/close to image)

~ image size

(calibrated)(calibrated)

Distortion minimization(uncalibrated)

(standard approach)

Page 13: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)
Page 14: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)
Page 15: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Polar re-parameterization around epipoles

Requires only (oriented) epipolar geometry

Preserve length of epipolar linesChoose so that no pixels are

compressed

original image rectified image

Polar rectification(Pollefeys et al. ICCV’99)

Works for all relative motionsGuarantees minimal image size

Page 16: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

polar rectification: example

Page 17: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

polar rectification: example

Page 18: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Example: Béguinage of Leuven

Does not work with standard Homography-based approaches

Page 19: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Example: Béguinage of Leuven

Page 20: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Stereo matching

• attempt to match every pixel• use additional constraints

Page 21: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Exploiting motion and scene constraints

• Ordering constraint• Uniqueness constraint• Disparity limit• Disparity continuity constraint

• Epipolar constraint Epipolar constraint (through rectification)

Page 22: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Ordering constraint

11 22 33 4,54,5 66 11 2,32,3 44 55 66

2211 33 4,54,5 6611

2,32,3

44

55

66

surface slicesurface slice surface as a pathsurface as a path

occlusion right

occlusion left

Page 23: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Uniqueness constraint

• In an image pair each pixel has at most one corresponding pixel• In general one corresponding pixel• In case of occlusion there is none

Page 24: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Disparity constraint

surface slicesurface slice surface as a pathsurface as a path

bounding box

dispa

rity b

and

use reconsructed features to determine bounding box

constantdisparitysurfaces

Page 25: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Disparity continuity constraint

• Assume piecewise continuous surface

piecewise continuous disparity• In general disparity changes

continuously• discontinuities at occluding

boundaries

Page 26: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Stereo matching

Optimal path(dynamic programming )

Similarity measure(SSD or NCC)

Constraints• epipolar

• ordering

• uniqueness

• disparity limit

• disparity gradient limit

Trade-off

• Matching cost (data)

• Discontinuities (prior)

(Cox et al. CVGIP’96; Koch’96; Falkenhagen´97; Van Meerbergen,Vergauwen,Pollefeys,VanGool IJCV‘02)

Page 27: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Hierarchical stereo matching

Dow

nsam

plin

g

(Gau

ssia

n p

yra

mid

)

Dis

pari

ty p

rop

ag

ati

on

Allows faster computation

Deals with large disparity ranges

(Falkenhagen´97;Van Meerbergen,Vergauwen,Pollefeys,VanGool IJCV‘02)

Page 28: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Disparity map

image I(x,y) image I´(x´,y´)Disparity map D(x,y)

(x´,y´)=(x+D(x,y),y)

Page 29: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Example: reconstruct image from neighboring

images

Page 30: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Multi-view depth fusion

• Compute depth for every pixel of reference image• Triangulation• Use multiple views• Up- and down

sequence• Use Kalman filter

(Koch, Pollefeys and Van Gool. ECCV‘98)

Allows to compute robust texture

Page 31: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Point reconstruction

PXx XP'x'

Page 32: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

linear triangulation

XP'x'PXx

0XP'x

0XpXp0XpXp0XpXp

1T2T

2T3T

1T3T

yxyx

2T3T

1T3T

2T3T

1T3T

p'p''p'p''pppp

A

yxyx

0AX

homogeneous

1X

)1,,,( ZYX

inhomogeneous

invariance?

e)(HX)(AH-1

algebraic error yes, constraint no (except for affine)

Page 33: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

geometric error

0x̂F'x̂ subject to )'x̂,(x')x̂(x, T22 dd

X̂P''x̂ and X̂Px̂ subject toly equivalentor

possibility to compute using LM (for 2 or more points)

or directly (for 2 points)

Page 34: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Geometric error

Reconstruct matches in projective frame by minimizing the reprojection error

(see Hartley&Sturm,CVIU´97)Non-iterative optimal solution

Page 35: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Optimal 3D point in epipolar plane

Given an epipolar plane, find best 3D point for (x1,x2)

x1

x2

l1 l2

l1x1

x2l2

x1´

x2´

Select closest points (x1´,x2´) on epipolar lines

Obtain 3D point through exact triangulationGuarantees minimal reprojection error (given this epipolar plane)

Page 36: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Optimal epipolar plane

• Reconstruct matches in projective frame by minimizing the reprojection error

• Non-iterative methodDetermine the epipolar plane for reconstruction

Reconstruct optimal point from selected epipolar plane

222

211 XP,xXP,x dd

(Hartley and Sturm, CVIU´97)

222

211 αl,xαl,x DD

(polynomial of degree 6check all minima, incl ∞)

m1

m2

l1 l2

3DOF

1DOF

Page 37: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Reconstruction uncertainty

consider angle between rays

Page 38: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Line reconstruction

P'l'Pl

T

T

L

doesn‘t work for epipolar plane

Page 39: Assignment 2 Compute F automatically from image pair (putative matches, 8-point, 7-point, iterative, RANSAC, guided matching) (due by Wednesday 19/03/03)

Next class: Scene and plane homographies