Notes
Slide Show
Outline
1
Announcements
    • Project 2 code & artifact due Friday
    • Midterm out tomorrow (check your email), due next Fri


2
Stereo
  • 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.
3
 
4
 
5
 
6
 
7
 
8
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


9
Stereo
10
Stereo
11
Stereo correspondence
  • Determine Pixel Correspondence
    • Pairs of points that correspond to same scene point
12
Stereo image rectification
13
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.
14
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/
15
Your basic stereo algorithm
16
Window size
    • Smaller window
    • Larger window
17
Stereo results
    • Data from University of Tsukuba
    • Similar results on other images without ground truth
18
Results with window search
19
Better methods exist...
20
Stereo as energy minimization
21
Stereo as energy minimization
22
Depth from disparity
23
Video View Interpolation
  • http://research.microsoft.com/users/larryz/videoviewinterpolation.htm
24
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)
25
Stereo reconstruction pipeline
  • Steps
    • Calibrate cameras
    • Rectify images
    • Compute disparity
    • Estimate depth
26
Active stereo with structured light
  • Project “structured” light patterns onto the object
    • simplifies the correspondence problem
27
Active stereo with structured light
28
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
29
Laser scanned models
30
Laser scanned models
31
Laser scanned models
32
Laser scanned models
33
Laser scanned models
34
Spacetime Stereo