lec17 - Announcements Stereo Vision Wrapup Intro...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
1 CSE152, Spring 2011 Intro Computer Vision Stereo Vision Wrapup & Intro Recognition Introduction to Computer Vision CSE 152 Lecture 17 CSE152, Spring 2011 Intro Computer Vision Announcements • HW3 due date postpone to Thursday • HW4 to posted by Thursday, due next Friday. • Order of material– we’ll first cover recognition so that you’re prepared for assignment. Then return to motion. • Final Exam: Tuesday 6/7 8:00-11:00 AM, Here CSE152, Spring 2011 Intro Computer Vision Rectification CSE152, Spring 2011 Intro Computer Vision Rectification Given a pair of images, transform both images so that epipolar lines are scan lines. CSE152, Spring 2011 Intro Computer Vision Using epipolar & constant Brightness constraints for stereo matching 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 This will never work, so: Improvement: match windows (Seitz) CSE152, Spring 2011 Intro Computer Vision Correspondence Search Algorithm For i = 1:nrows for j=1:ncols best(i,j) = -1 for k = mindisparity:maxdisparity c = Match_Metric(I 1 (i,j),I 2 (i,j+k),winsize) if (c > best(i,j)) best(i,j) = c disparities(i,j) = k end end end end O(nrows * ncols * disparities * winx * winy)
Background image of page 1

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

View Full Document Right Arrow Icon
2 CSE152, Spring 2011 Intro Computer Vision Match Metric Summary MATCH METRIC DEFINITION Normalized Cross-Correlation (NCC) Sum of Squared Dif erences (SSD) Normalized SSD Sum of Absolute Dif erences (SAD) Zero Mean SAD Rank Census These two are actually the same CSE152, Spring 2011 Intro Computer Vision Stereo results Ground truth Disparity Map Scene – Data from University of Tsukuba (Seitz) CSE152, Spring 2011 Intro Computer Vision Results with window correlation Window-based matching (best window size) Ground truth (Seitz) CSE152, Spring 2011 Intro Computer Vision Results with better method Near State of the art method Boykov et al., Fast Approximate Energy Minimization via Graph Cuts , International Conference on Computer Vision, September 1999. Ground truth (Seitz) CSE152, Spring 2011 Intro Computer Vision Some Issues • Window size • Window shape • Lighting • Ambiguity • Ordering • Half occluded regions CSE152, Spring 2011 Intro Computer Vision Window size W = 3 W = 20 Better results with adaptive window T. Kanade and M. Okutomi, A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment ,, Proc. International Conference on Robotics and
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.
  • Spring '08
  • staff
  • Depth perception, Stereoscopy, Binocular disparity, Correspondence problem, International Journal of Computer Vision

{[ snackBarMessage ]}

Page1 / 7

lec17 - Announcements Stereo Vision Wrapup Intro...

This preview shows document pages 1 - 3. Sign up to view the full document.

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