lec10_graphcuts

lec10_graphcuts - CS6670:ComputerVision NoahSnavely

Info iconThis preview shows pages 1–20. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture 10: Stereo and Graph Cuts CS6670: Computer Vision Noah Snavely
Background image of page 1

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

View Full DocumentRight Arrow Icon
Announcements Project 2 out, due Wednesday, October 14 Artifact due Friday, October 16 Questions?
Background image of page 2
Readings Szeliski, Chapter 11.2 – 11.5
Background image of page 3

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

View Full DocumentRight Arrow Icon
What we’ve learned so far = * Image filtering Edge detection Cameras Image transformations
Background image of page 4
Feature detection and matching
Background image of page 5

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

View Full DocumentRight Arrow Icon
Panoramas
Background image of page 6
Magic: ghost removal M. Uyttendaele, A. Eden, and R. Szeliski. Eliminating ghosting and exposure artifacts in image mosaics . In Proceedings of the Interational Conference on Computer Vision and Pattern Recognition, volume 2, pages 509 ‐‐ 516, Kauai, Hawaii, December 2001.
Background image of page 7

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

View Full DocumentRight Arrow Icon
Magic: ghost removal M. Uyttendaele, A. Eden, and R. Szeliski. Eliminating ghosting and exposure artifacts in image mosaics . In Proceedings of the Interational Conference on Computer Vision and Pattern Recognition, volume 2, pages 509 ‐‐ 516, Kauai, Hawaii, December 2001.
Background image of page 8
Optical flow
Background image of page 9

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

View Full DocumentRight Arrow Icon
Your basic stereo algorithm For each epipolar line For each pixel in the left image compare with every pixel on same epipolar line in right image pick pixel with minimum match cost Improvement: match windows
Background image of page 10
Stereo results Ground truth Scene
Background image of page 11

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

View Full DocumentRight Arrow Icon
Results with window search Window based matching (best window size) Ground truth problems in areas of uniform texture
Background image of page 12
Can we do better? What defines a good stereo correspondence? 1. Match quality Want each pixel to find a good match in the other image 2. Smoothness two adjacent pixels should (usually) move about the same amount
Background image of page 13

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

View Full DocumentRight Arrow Icon
Stereo as energy minimization Find disparities d that minimize an energy function Simple pixel / window matching SSD distance between windows I ( x , y ) and J ( x , y + d ( x , y )) =
Background image of page 14
Stereo as energy minimization I ( x , y ) J ( x , y ) y = 141 C ( x , y , d ); the disparity space image (DSI) x d
Background image of page 15

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

View Full DocumentRight Arrow Icon
Stereo as energy minimization y = 141 x d Simple pixel / window matching: choose the minimum of each column in the DSI independently:
Background image of page 16
Stereo as energy minimization Better objective function match cost smoothness cost Want each pixel to find a good match in the other image Adjacent pixels should (usually) move about the same amount
Background image of page 17

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

View Full DocumentRight Arrow Icon
Stereo as energy minimization match cost: smoothness cost: 4 connected neighborhood 8 connected neighborhood : set of neighboring pixels
Background image of page 18
Smoothness cost “Potts model” L 1 distance last time: looked at quadratic and truncated quadratic models for V
Background image of page 19

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

View Full DocumentRight Arrow Icon
Image of page 20
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 09/27/2010 for the course CS 667 at Cornell.

Page1 / 53

lec10_graphcuts - CS6670:ComputerVision NoahSnavely

This preview shows document pages 1 - 20. Sign up to view the full document.

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