Announcements

Project 3 code & artifact due Tuesday

Final project proposals due noon Wed (by email)

One-page writeup (from project web page), specifying:

Your team members

Project goals. Be specific. Describe the input and output.

Brief description of your approach. If you are implementing or extending a previous method, give the reference and web link to the paper.

Will you be using helper code (e.g., available online) or will you implement it all yourself?

Evaluation method. How will you test it? Which test cases will you use?

Breakdown--what will each team-member do? Ideally, everyone should do something imaging/vision related (it's not good for one team member to focus purely on user-interface, for instance).

Special equipment that will be needed. We may be able to help with cameras, tripods, etc.

Stereo

Readings

Szeliski, Chapter 10 (through 10.5)

Slide 3

Slide 4

Slide 5

Slide 6

Slide 7

Anaglyphs online

I used to maintain of list of sites, but too hard to keep up to date. Instead, see wikipedia page:

http://en.wikipedia.org/wiki/Anaglyph_image

Stereo

Stereo correspondence

Determine Pixel Correspondence

Pairs of points that correspond to same scene point

Fundamental matrix

Let p be a point in left image, p’ in right image

Epipolar relation

p maps to epipolar line l’

p’ maps to epipolar line l

Epipolar mapping described by a 3x3 matrix F

It follows that

Fundamental matrix

This matrix F is called

the “Essential Matrix”

when image intrinsic parameters are known

the “Fundamental Matrix”

more generally (uncalibrated case)

Can solve for F from point correspondences

Each (p, p’) pair gives one linear equation in entries of F

8 points give enough to solve for F (8-point algorithm)

see Marc Pollefey’s notes for a nice tutorial

Stereo image rectification

Stereo image rectification

reproject image planes onto a common

plane parallel to the line between optical centers

pixel motion is horizontal after this transformation

two homographies (3x3 transform), one for each input image reprojection

C. Loop and Z. Zhang. Computing Rectifying Homographies for Stereo Vision. IEEE Conf. Computer Vision and Pattern Recognition, 1999.

Stereo matching algorithms

Match Pixels in Conjugate Epipolar Lines

Assume brightness constancy

This is a tough problem

Numerous approaches

A good survey and evaluation: http://www.middlebury.edu/stereo/

Your basic stereo algorithm

Window size

Smaller window

Larger window

Stereo results

Data from University of Tsukuba

Similar results on other images without ground truth

Results with window search

Better methods exist...

Stereo as energy minimization

Depth from disparity

Video View Interpolation

http://research.microsoft.com/users/larryz/videoviewinterpolation.htm

Real-time stereo

Used for robot navigation (and other tasks)

Several software-based real-time stereo techniques have been developed (most based on simple discrete search)

Stereo reconstruction pipeline

Steps

Calibrate cameras

Rectify images

Compute disparity

Estimate depth

Active stereo with structured light

Project “structured” light patterns onto the object

simplifies the correspondence problem

Active stereo with structured light

Laser scanning

Optical triangulation

Project a single stripe of laser light

Scan it across the surface of the object

This is a very precise version of structured light scanning

Laser scanned models

Spacetime Stereo


Project 3 code & artifact due Tuesday
Final project proposals due noon Wed (by email)
	One-page writeup (from project web page), specifying:
		Your team members
		Project goals. Be specific. Describe the input and output.
		Brief description of your approach. If you are implementing or extending a previous method, give the reference and web link to the paper.
		Will you be using helper code (e.g., available online) or will you implement it all yourself?
		Evaluation method. How will you test it? Which test cases will you use?
		Breakdown--what will each team-member do? Ideally, everyone should do something imaging/vision related (it's not good for one team member to focus purely on user-interface, for instance).
		Special equipment that will be needed. We may be able to help with cameras, tripods, etc.


	I used to maintain of list of sites, but too hard to keep up to date. Instead, see wikipedia page:

	http://en.wikipedia.org/wiki/Anaglyph_image


	Determine Pixel Correspondence
		Pairs of points that correspond to same scene point


	Let p be a point in left image, p’ in right image



	Epipolar relation
		p maps to epipolar line l’
		p’ maps to epipolar line l
	Epipolar mapping described by a 3x3 matrix F



	It follows that


This matrix F is called
	the “Essential Matrix”
		when image intrinsic parameters are known
	the “Fundamental Matrix”
		more generally (uncalibrated case)

Can solve for F from point correspondences
	Each (p, p’) pair gives one linear equation in entries of F


	8 points give enough to solve for F (8-point algorithm)
	see Marc Pollefey’s notes for a nice tutorial


	reproject image planes onto a common
	plane parallel to the line between optical centers
	pixel motion is horizontal after this transformation
	two homographies (3x3 transform), one for each input image reprojection
	C. Loop and Z. Zhang. Computing Rectifying Homographies for Stereo Vision. IEEE Conf. Computer Vision and Pattern Recognition, 1999.


Match Pixels in Conjugate Epipolar Lines
	Assume brightness constancy
	This is a tough problem
	Numerous approaches
		A good survey and evaluation: http://www.middlebury.edu/stereo/


		Data from University of Tsukuba
		Similar results on other images without ground truth


	http://research.microsoft.com/users/larryz/videoviewinterpolation.htm


	Used for robot navigation (and other tasks)
		Several software-based real-time stereo techniques have been developed (most based on simple discrete search)


	Steps
		Calibrate cameras
		Rectify images
		Compute disparity
		Estimate depth


	Project “structured” light patterns onto the object
		simplifies the correspondence problem


	Optical triangulation
		Project a single stripe of laser light
		Scan it across the surface of the object
		This is a very precise version of structured light scanning