stanford cs223b computer vision, winter 2007 lecture 6 advanced stereo professors sebastian thrun...

Post on 23-Jan-2016

219 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

TRANSCRIPT

Stanford CS223B Computer Vision, Winter 2007

Lecture 6 Advanced Stereo

Professors Sebastian Thrun and Jana Košecká

CAs: Vaibhav Vaish and David Stavens

StereoStereo

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Summary Stereo Epipolar Geometry Fundamental/Essential Matrix

plp

r

P

Ol Orel er

Pl Pr

Epipolar Plane

Epipolar Lines

Epipoles

0lTr Epp

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Correspondence: Where to search?

Search window?

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Stereo Vision 2: Outline Image Rectification Correspondence Active Stereo Dense and Layered Stereo Smoothing With Markov Random Fields

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Rectification Problem: Epipolar lines not parallel to scan lines

plp

r

P

Ol Orel er

Pl Pr

Epipolar Plane

Epipolar Lines

Epipoles

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Rectification Problem: Epipolar lines not parallel to scan lines

plp

r

P

Ol Or

Pl Pr

Epipolar Plane

Epipolar Lines

Epipoles at ininity

Rectified Images

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Epipolar Rectified Stereo Images

Epipolar line

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Epipolar Rectified Images

Source: A. Fusiello, Verona, 2000]

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Example Rectification

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Final Step: Image Normalization

Even when the cameras are identical models, there can be differences in gain and sensitivity.

The cameras do not see exactly the same surfaces, so their overall light levels can differ.

For these reasons and more, it is a good idea to normalize the pixels in each window:

pixel Normalized ),(

),(ˆ

magnitude Window )],([

pixel Average ),(

),(

),(),(

2

),(

),(),(),(

1

yxW

yxWvuyxW

yxWvuyxW

m

mm

m

m

II

IyxIyxI

vuII

vuII

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Stereo Vision 2: Outline Image Rectification Correspondence Active Stereo Dense and Layered Stereo Smoothing With Markov Random Fields

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Correspondence

1P1Oy

x

z

f

2Oy

x

z

1.lp

1,rp

1P

Phantom points

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Correspondence via Correlation

Rectified images

Left Right

scanline

SSD error

disparity

(Same as max-correlation / max-cosine for normalized image patch)

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Images as Vectors

Left Right

LwRw

Each window is a vectorin an m2 dimensionalvector space.Normalization makesthem unit length.

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Image Metrics

Lw)(dwR

2

),(),(

2SSD

)(

)],(ˆ),(ˆ[)(

dww

vduIvuIdC

RL

yxWvuRL

m

(Normalized) Sum of Squared Differences

Normalized Correlation

cos)(

),(ˆ),(ˆ)(),(),(

NC

dww

vduIvuIdC

RL

yxWvuRL

m

)(maxarg)(minarg2* dwwdwwd RLdRLd

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Correspondence Using Correlation

Left Disparity Map

Images courtesy of Point Grey Research

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

LEFT IMAGE

corner line

structure

Correspondence By Features

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Correspondence By Features

RIGHT IMAGE

corner line

structure

Search in the right image… the disparity (dx, dy) is the displacement when the similarity measure is maximum

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Stereo Correspondences

… …Left scan line Right scan line

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Stereo Correspondences

… …Left scanline Right scanline

Match

Match

MatchOcclusion Disocclusion

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Search Over Correspondences

Three cases:–Sequential – cost of match–Occluded – cost of no match–Disoccluded – cost of no match

Left scanline

Right scanline

Occluded Pixels

Disoccluded Pixels

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Scan across grid computing optimal cost for each node given its upper-left neighbors.Backtrack from the terminal to get the optimal path.

Occluded Pixels

Left scanline

Dis-occluded Pixels

Right scanline

Terminal

Stereo Matching with Dynamic Programming

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

DP Algorithm:

V[0,0] = 0

V[i,k] = min { V[i-1,k-1] + m(i,j), c+V[i, k-1], c+V[i-1,k] }d[i,k] = argmin { … }

Occluded Pixels

Left scanline

Dis-occluded Pixels

Right scanline

Terminal

Stereo Matching with Dynamic Programming

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Occluded Pixels

Left scanline

Dis-occluded Pixels

Right scanline

Terminal

Stereo Matching with Dynamic Programming

DP Algorithm:

V[0,0] = 0

V[i,k] = min { V[i-1,k-1] + m(i,j), c+V[i, k-1], c+V[i-1,k] }d[i,k] = argmin { … }

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Find Stereo Alignment

D=[X,Y]repeat until D=[1,1] add D to alignment D = d[D]end

Occluded Pixels

Left scanline

Dis-occluded Pixels

Right scanline

Terminal

Stereo Matching with Dynamic Programming

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Commercial-Grade Stereo Tyzx, a leading stereo camera manufacturer (here strapped on our DARPA Grand Challenge vehicle)

Disparity map

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Dense Stereo Matching: Examples

View extrapolation results

input depth image novel view [Matthies,Szeliski,Kanade’88]

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Dense Stereo Matching Some other view extrapolation results

input depth image novel view

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Dense Stereo Matching Compute certainty map from correlations

input depth map certainty map

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

DP for Correspondence Does this always work? When would it fail?

– Failure Example 1– Failure Example 2– Failure Example 3– Failure Example 4

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Correspondence Problem 1 Ambiguities

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Correspondence Problem 2 Multiple occluding objects

Figure fromForsyth & Ponce

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Correspondence Problem 3 Correspondence fail for smooth surfaces (edge =

occlusion boundary, poorly localized)

There is currently no good solution to this correspondence problem

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Correspondence Problem 4

Regions without texture Highly Specular surfaces Translucent objects

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Some Stereo Results

Side view

Top view

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

More Stereo Results

Side view

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

A True Challenge!

http://www.well.com/user/jimg/stereo/stereo_list.html

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Stereo Vision 2: Outline Image Rectification Correspondence Active Stereo Dense and Layered Stereo Smoothing With Markov Random Fields

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

How can We Improve Stereo?

Space-time stereo scanneruses unstructured light to aidin correspondence

Result: Dense 3D mesh (noisy)

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Active Stereo: Adding Texture to Scene

By James Davis, Honda Research,

Now UCSC

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

rect

ified

Active Stereo (Structured Light)

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Structured Light: 3-D Result

3D Snapshot

By James Davis, Honda Research

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Time of Flight Sensor: Shutter

http://www.3dvsystems.com

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Time of Flight Sensor: Shutter

http://www.3dvsystems.com

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Time of Flight Sensor: Shutter

http://www.3dvsystems.com

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Time of Flight Sensor: Shutter

http://www.3dvsystems.com

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Time of Flight Sensor: Shutter

http://www.3dvsystems.com

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Scanning Laser Range Finders

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Scanning Laser Results

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Scanning Laser Results

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Stereo Vision 2: Outline Image Rectification Correspondence Active Stereo Dense and Layered Stereo Smoothing With Markov Random Fields

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Layered Stereo Assign pixel to different “layers” (objects, sprites)

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Layered Stereo

Track each layer from frame to frame, compute plane eqn. and composite mosaic

Re-compute pixel assignment by comparing original images to sprites

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Layered Stereo Re-synthesize original or novel images from

collection of sprites

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Layered Stereo Advantages:

– can represent occluded regions– can represent transparent and border (mixed) pixels

(sprites have alpha value per pixel)– works on texture-less interior regions

Limitations:– fails for high depth-complexity scenes

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Fitting Planar Surfaces (with EM)

******

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Expectation Maximization 3D Model:

},,,{ 21 J

3, jjj Planar surface in 3D

jijij zz ),dist(

Distance point-surfacesurface

surface normal a

y

x

z

displacement b

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Mixture Measurement Model Case 1: Measurement zi caused by plane j

2

2)(

2

1

22

1)|(

jij z

ji ezp

2

2max

2ln

2

1

2max

*2

11)|(

z

i ez

zp

§ Case 2: Measurement zi caused by something else

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Measurement Model with Correspondences

J

j

jijj

zc

zc

Ji eccczp 12

2

2

2max

*

)(

2ln

2

1

2*12

1),,,,|(

correspondence variables C:

}

J

jj

j

cc

cc

1*

*

1

}1,0{,

1

)(

2ln

2

1

2

12

2

2

2max

*

2

1),|(

i

zc

zc

J

j

jijiji

eCZp

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Expected Log-Likelihood Function

1

)(

2ln

2

1

2

12

2

2

2max

*

2

1),|(

i

zc

zc

J

j

jijiji

eCZp

i

J

j

jijij

ic

zcE

zcE

J

CZpE

12

2

2

2max

*

2

)(][

2

1

2ln][

2

1

2)1(

1ln

)|,(ln

…after some simple math

mapping with known data association

probabilistic data association

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

The EM Algorithm

E-step: given plane params, compute

M-step: given expectations, compute

i

J

j

jijijc

zcECZpE

12

2)(][const)|,(ln

][ ijcE

},{ jja

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Choosing the “Right” Number of Planes: AIC

J=2 J=3 J=5J=0 J=1 J=4

increased data likelihood

increased prior probability

)(log)|(log)|(log JpJdpconstdJp

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Determining Number of Surfaces

J =1

First model component

*

*

J =1

E-Step

*

*

J =3

Add model components

J =3

E-Step

J =3

M-step

J =1

Prune model

J =3

Add model components

J =3

E/M Steps

*J =2

Prune model

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Layered Stereo Resulting sprite collection

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Layered Stereo

Estimated depth map

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Example (here with laser range finder)

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Example (here with laser range finder)

Another Example

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Stereo Vision 2: Outline Image Rectification Correspondence Active Stereo Dense and Layered Stereo Smoothing With Markov Random Fields

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Motivation and Goals

James Diebel

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Motivation and Goals

James Diebel

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Network of Constraints (Markov Random Field)

Vertex Node

Edge Node

Face Node

Vertex Node

Edge Node

Face Node

Vertex Node

Edge Node

Face Node

DirectionsDirectionsDirections

James Diebel

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

MRF Approach to Smoothing Potential function: contains a sensor-model term

and a surface prior

The edge potential is important! Minimize by conjugate gradient

– Optimize systems with tens of thousands of parameters in just a couple seconds

– Time to converge is O(N), between 0.7 sec (25,000 nodes in the MRF) and 25 sec (900,000 nodes)

j

ji

iiiT

ii nnxxxx 2100 1

Diebel/Thrun, 2006

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Possible Edge Potential Functions

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Results: Smoothing

James Diebel

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Results: Smoothing

James Diebel

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Results: Smoothing

James Diebel

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Results: Smoothing

James Diebel

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Movies…

Movies in Windows Media Player

Sebastian Thrun and Jana Košecká CS223B Computer Vision, Winter 2007

Summary Image Rectification Correspondence Active Stereo Dense and Layered Stereo Smoothing With Markov Random Fields

top related