CS223B-L7-Stereo

CS223B-L7-Stereo - Stanford CS223B Computer Vision, Winter...

Info iconThis preview shows pages 1–19. Sign up to view the full content.

View Full Document Right Arrow Icon
Stanford CS223B Computer Vision, Winter 2008/09 Lecture 7 Stereo Professor Sebastian Thrun CAs: Ethan Dreyfuss, Young Min Kim, Alex Teichman
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Vocabulary Quiz Baseline Epipole Fundamental Matrix Essential Matrix Stereo Rectification Sprites
Background image of page 2
Sebastian Thrun Stanford University CS223B Computer Vision CS223b 3 Why Stereo Vision? 2D images project 3D points into 2D O P’=Q’ P Q center of projection
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Stereo Vision: Illustration http://www.well.com/user/jimg/stereo/stereo_list.html
Background image of page 4
Sebastian Thrun Stanford University CS223B Computer Vision Stereo Example (Stanley Robot) Disparity map
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Stereo Example Credit: Ben Wegbreit
Background image of page 6
Sebastian Thrun Stanford University CS223B Computer Vision CS223b 7 Autostereograms Depth perception from one image Viewing trick the brain by focusing at the plane behind - match can be established perception of 3D
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Stereo Vision: Outline Basic Equations Correspondence Epipolar Geometry Image Rectification Layered Stereo Smoothing
Background image of page 8
Sebastian Thrun Stanford University CS223B Computer Vision Pinhole Camera Model Image plane Focal length f Center of projection
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Pinhole Camera Model Image plane ) , , ( Z Y X P = f - O y x z ( x , y ) = ( f X Z , f Y Z ) ( x , y )
Background image of page 10
Sebastian Thrun Stanford University CS223B Computer Vision Basic Stereo Derivations ) , , ( 1 Z Y X P = 1 O y x z f - 2 O y x z B B f x x Z , , , of function a as for expression Derive 2 1 x 1 - x 2
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Basic Stereo Derivations ) , , ( 1 Z Y X P = 1 O y x z f - 2 O y x z 2 1 1 1 1 1 1 2 1 1 1 , x x B f Z Z B f x Z B X f x Z X f x - = - = + - = - = B x 1 x 2
Background image of page 12
Sebastian Thrun Stanford University CS223B Computer Vision Stereo Vision: Outline Basic Equations Correspondence Epipolar Geometry Image Rectification Layered Stereo Smoothing
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Correspondence 1 P 1 O y x z f - 2 O y x z 1 . l p 1 , r p 1 P Phantom points
Background image of page 14
Sebastian Thrun Stanford University CS223B Computer Vision Correspondence via Correlation Rectified images Left Right scanline SSD error disparity (Same as max-correlation / max-cosine for normalized image patch)
Background image of page 15

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Images as Vectors Left Right L w R w Each window is a vector in an m 2 dimensional vector space. Normalization makes them unit length.
Background image of page 16
Sebastian Thrun Stanford University CS223B Computer Vision Correspondence Metrics L w ) ( d w R 2 ) , ( ) , ( 2 SSD ) ( )] , ( ˆ ) , ( ˆ [ ) ( d w w v d u I v u I d C R L y x W v u R L m - = - - = (Normalized) Sum of Squared Differences Normalized Correlation θ cos ) ( ) , ( ˆ ) , ( ˆ ) ( ) , ( ) , ( NC = = - = d w w v d u I v u I d C R L y x W v u R L m ) ( max arg ) ( min arg 2 * d w w d w w d R L d R L d = - =
Background image of page 17

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Correspondence Using Correlation Left Disparity Map Images courtesy of Point Grey Research
Background image of page 18
Image of page 19
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/24/2010 for the course CS 223B taught by Professor Thrun,s during the Winter '09 term at Stanford.

Page1 / 88

CS223B-L7-Stereo - Stanford CS223B Computer Vision, Winter...

This preview shows document pages 1 - 19. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online