Structure from images
description
Transcript of Structure from images
Structure from images
Calibration
Review: Pinhole Camera
Review: Perspective Projection
Review: Perspective Projection
Points go to Points Lines go to Lines Planes go to whole
image or Half-planes
Polygons go to Polygons
Review: Intrinsic Camera Parameters
X
Y
Z C
Image plane
Focal plane
M
m
CCC ZYX ,,
u
v
i
j
I
JJkjIki
v
u
II vu ,
fvu CC ,,
101000000
0
0
C
C
C
v
unew
new
ZYX
vfuf
SVU
vv
uu
fkffkf
Review: Extrinsic Parameters
X
Y
Z C
Image plane
Focal plane
M
m
CCC ZYX ,,
u
v
i
j
I
JJkjIki
v
u
II vu ,
fvu CC ,,Z
Y
X
WWW ZYX ,,
By Rigid Body Transformation:
WC
W
W
W
C
C
C
DMMZYX
TRZYX
110
131
1333
Alper Yilmaz, CAP5415, Fall 2004
8
Estimating Camera Parameters
11, yx 111 ,, ZYX
222 ,, ZYX 333 ,, ZYX
NNN ZYX ,,
22 , yx 33 , yx
NN yx ,
Shape From Images
Perspective cues
Perspective cues
Perspective cues
Ames Room
Ames Room
Video
Recovering 3D from images What cues in the image provide 3D
information?
Shading
Visual cues
Merle Norman Cosmetics, Los Angeles
Visual cues Shading
Texture
The Visual Cliff, by William Vandivert, 1960
Visual cues
From The Art of Photography, Canon
Shading
Texture
Focus
Visual cues Shading
Texture
Focus
Motion
Julesz: had huge impact because it showed that recognition not needed for stereo.
Shape From Multiple Views
Multi-View GeometryRelates
• 3D World Points
• Camera Centers
• Camera Orientations
Multi-View GeometryRelates
• 3D World Points
• Camera Centers
• Camera Orientations
• Camera Intrinsic Parameters
• Image Points
Stereoscene point
optical center
image plane
Stereo
Basic Principle: Triangulation• Gives reconstruction as intersection of two rays
• Requires – calibration– point correspondence
Stereo Constraints
p p’ ?
Given p in left image, where can the corresponding point p’in right image be?
Stereo Constraints
X1
Y1
Z1O1
Image plane
Focal plane
M
p p’Y2
X2
Z2O2
Epipolar Line
Epipole
Epipolar Constraint
From Geometry to Algebra
O O’
P
pp’
From Geometry to Algebra
O O’
P
pp’
Linear Constraint:Should be able to express as matrix multiplication.
The Essential Matrix
Correspondence
Pin Hole Camera Model
ZXfx
Basic Stereo Derivations
Derive expression for Z as a function of x1, x2, f and B
Basic Stereo Derivations
ZXfx 1 Z
BfxZ
BXfx
12
21 xxfBZ
Basic Stereo Derivations
Disparity: 21 xxd
dfBZ
We can always achieve this geometry with image rectification
Image Reprojection reproject image planes onto
common plane parallel to line between optical centers (Seitz)
Rectification example
Correspondence: Epipolar constraint.
Correspondence Problem Two classes of algorithms:
Correlation-based algorithms Produce a DENSE set of correspondences
Feature-based algorithms Produce a SPARSE set of correspondences
Correspondence: Photometric constraint Same world point has same intensity in
both images. Lambertian fronto-parallel Issues:
Noise Specularity Foreshortening
Using these constraints we can use matching for stereo
For each epipolar lineFor each pixel in the left image
• compare with every pixel on same epipolar line in right image• pick pixel with minimum match cost• This will never work, so:
Improvement: match windows
Comparing Windows: =?
f g
Mostpopular
For each window, match to closest window on epipolar line in other image.
It is closely related to the SSD:
Maximize Cross correlation
Minimize Sum of Squared Differences
Matching cost
disparity
Left Right
scanline
Correspondence search
• Slide a window along the right scanline and compare contents of that window with the reference window in the left image
• Matching cost: SSD or normalized correlation
Left Right
scanline
Correspondence search
SSD
Left Right
scanline
Correspondence search
Norm. corr
Effect of window size
W = 3 W = 20
• Smaller window+ More detail– More noise
• Larger window+ Smoother disparity maps– Less detail– Fails near boundaries
Stereo results
Ground truthScene
Data from University of Tsukuba
(Seitz)
Results with window correlation
Window-based matching(best window size)
Ground truth
(Seitz)
Results with better method
State of the art methodBoykov et al., Fast Approximate Energy Minimization via Graph Cuts,
International Conference on Computer Vision, September 1999.
Ground truth
(Seitz)
Failures of correspondence search
Textureless surfaces Occlusions, repetition
Non-Lambertian surfaces, specularities
How can we improve window-based matching?
So far, matches are independent for each point
What constraints or priors can we add?
Stereo constraints/priors• Uniqueness
For any point in one image, there should be at most one matching point in the other image
Stereo constraints/priors• Uniqueness
For any point in one image, there should be at most one matching point in the other image
• Ordering Corresponding points should be in the same order in both views
Ordering constraint doesn’t hold
Priors and constraints
• Uniqueness For any point in one image, there should be at most one
matching point in the other image• Ordering
Corresponding points should be in the same order in both views
• Smoothness We expect disparity values to change slowly (for the
most part)
Stereo matching as energy minimizationI1 I2 D
• Energy functions of this form can be minimized using graph cutsY. Boykov, O. Veksler, and R. Zabih, Fast Approximate Energy Minimization via Graph Cuts, PAMI 2001
W1(i ) W2(i+D(i )) D(i )
)(),;( smooth21data DEIIDEE 2
,neighborssmooth )()(
ji
jDiDE 221data ))(()(
i
iDiWiWE
Examples
bread toy apple
Szeliski
Active stereo with structured light
Project “structured” light patterns onto the object simplifies the correspondence problem
camera 2
camera 1
projector
camera 1
projector
Li Zhang’s one-shot stereo
Active stereo with structured light
L. Zhang, B. Curless, and S. M. Seitz. Rapid Shape Acquisition Using Color Structured Light and Multi-pass Dynamic Programming. 3DPVT 2002
Kinect
https://www.youtube.com/watch?v=dTKlNGSH9Po
The third view can be used for verification
Beyond two-view stereo