1
|
- Project 2 code & artifact due Friday
- Midterm out tomorrow (check your email), due next Fri
|
2
|
- 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
|
- 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
|
|
10
|
|
11
|
- Determine Pixel Correspondence
- Pairs of points that correspond to same scene point
|
12
|
|
13
|
- 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
|
- 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
|
|
16
|
- Smaller window
- Larger window
|
17
|
- Data from University of Tsukuba
- Similar results on other images without ground truth
|
18
|
|
19
|
|
20
|
|
21
|
|
22
|
|
23
|
- http://research.microsoft.com/users/larryz/videoviewinterpolation.htm
|
24
|
- Used for robot navigation (and other tasks)
- Several software-based real-time stereo techniques have been developed
(most based on simple discrete search)
|
25
|
- Steps
- Calibrate cameras
- Rectify images
- Compute disparity
- Estimate depth
|
26
|
- Project “structured” light patterns onto the object
- simplifies the correspondence problem
|
27
|
|
28
|
- 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
|
|
30
|
|
31
|
|
32
|
|
33
|
|
34
|
|