Stereo

Guest Lecture by Li Zhang

http://www.cs.washington.edu/homes/lizhang/

Last lecture: new images from images

This lecture: 3D structures from images

How might we do this automatically?

What cues in the image provide 3D information?

Readings

Trucco & Verri, Chapter 7

Read through 7.1, 7.2.1, 7.2.2, 7.3.1, 7.3.2, 7.3.7 and 7.4, 7.4.1. The rest is optional.

Visual cues

Shading

Visual cues

Shading

Texture

Visual cues

Shading

Texture

Focus

Visual cues

Shading

Texture

Focus

Motion

Slide 9

Slide 10

Slide 11

Slide 12

Slide 13

Stereograms online

UCR stereographs

http://www.cmp.ucr.edu/site/exhibitions/stereo/

The Art of Stereo Photography

http://www.photostuff.co.uk/stereo.htm

History of Stereo Photography

http://www.rpi.edu/~ruiz/stereo_history/text/historystereog.html

Double Exposure

http://home.centurytel.net/s3dcor/index.html

Stereo Photography

http://www.shortcourses.com/book01/chapter09.htm

3D Photography links

http://www.studyweb.com/links/5243.html

National Stereoscopic Association

http://204.248.144.203/3dLibrary/welcome.html

Books on Stereo Photography

http://userwww.sfsu.edu/~hl/3d.biblio.html

Stereo

Stereo correspondence

Determine Pixel Correspondence

Pairs of points that correspond to same scene point

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...

Depth from disparity

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


	Guest Lecture by Li Zhang
	http://www.cs.washington.edu/homes/lizhang/


How might we do this automatically?
	What cues in the image provide 3D information?


Readings
	Trucco & Verri, Chapter 7
		Read through 7.1, 7.2.1, 7.2.2, 7.3.1, 7.3.2, 7.3.7 and 7.4, 7.4.1. The rest is optional.


	UCR stereographs
		http://www.cmp.ucr.edu/site/exhibitions/stereo/
	The Art of Stereo Photography
		http://www.photostuff.co.uk/stereo.htm
	History of Stereo Photography
		http://www.rpi.edu/~ruiz/stereo_history/text/historystereog.html
	Double Exposure
		http://home.centurytel.net/s3dcor/index.html
	Stereo Photography
		http://www.shortcourses.com/book01/chapter09.htm
	3D Photography links
		http://www.studyweb.com/links/5243.html
	National Stereoscopic Association
		http://204.248.144.203/3dLibrary/welcome.html
	Books on Stereo Photography
		http://userwww.sfsu.edu/~hl/3d.biblio.html


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


	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


	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