Presentation is loading. Please wait.

Presentation is loading. Please wait.

Geometric Transformations

Similar presentations


Presentation on theme: "Geometric Transformations"— Presentation transcript:

1 Geometric Transformations
EE 7700 Geometric Transformations

2 Geometric Transformation
translation Rotation matrix scale Scale matrix rotation & scale Rigid flow Bahadir K. Gunturk

3 Affine Flow Bahadir K. Gunturk

4 Perspective Flow Bahadir K. Gunturk

5 Bahadir K. Gunturk

6 Bahadir K. Gunturk

7 Bahadir K. Gunturk

8 RANSAC: RANdom SAmple Consensus
EE 7730 RANSAC: RANdom SAmple Consensus

9 Outliers Consider the least squares fit for optical flow:
If some of the values are wrong, it will degrade the estimation. Bahadir K. Gunturk

10 Outliers It is best not to include outliers in the estimation.
Line Fitting Problem: Given (x1,y1), …, (xN,yN); find the line y=ax+b Outliers Best fit is degraded due to the outliers Bahadir K. Gunturk

11 Robust Estimation Two step process:
Classify data points as outliers or inliers Use inliers only to fit a model Bahadir K. Gunturk

12 RANSAC Repeat for k times:
Randomly choose n points (the smallest number of points required) from the data. Estimate the parameters using these points. For each data point other than these n points: Check if the data point is within a threshold, t, distance of current model; if it is, the data point is consistent with current model. The total number of data points that are consistent is model’s support. If the support is larger than a predetermined number, d, then there is a good fit. Re-estimate the parameters using these inliers. Choose the best fit with the smallest fitting error. Bahadir K. Gunturk

13 RANSAC Two samples and their supports for line-fitting
Bahadir K. Gunturk

14 Example Find the perspective parameters Bahadir K. Gunturk
from Hartley & Zisserman Bahadir K. Gunturk

15 Example Apply corner detectors to both images Bahadir K. Gunturk
from Hartley & Zisserman Bahadir K. Gunturk

16 Example Find the best match within a search window. Bahadir K. Gunturk
from Hartley & Zisserman Bahadir K. Gunturk

17 Example Initial match results
from Hartley & Zisserman 188 matched features in left image pointing to locations of corresponding right image features Bahadir K. Gunturk

18 Example Inliers and outliers after RANSAC 89 outliers 99 inliers
from Hartley & Zisserman 89 outliers 99 inliers Bahadir K. Gunturk

19 Panoramic Image Reconstruction
Find features Match features Fit parametric model Application: Mosaic construction Bahadir K. Gunturk

20 EE7730 Stereo Vision

21 Pinhole Camera Bahadir K. Gunturk

22 Review: Perspective Projection
Bahadir K. Gunturk

23 Stereo p p’ p p’ scene point image plane optical center
Bahadir K. Gunturk

24 Stereo Constraints M Image plane Epipolar Line Y1 p p’ Y2 X2 O1 Z1 X1
Epipole Focal plane Bahadir K. Gunturk

25 From Geometry to Algebra
P p p’ All vectors shown lie on the same plane. Bahadir K. Gunturk

26 From Geometry to Algebra
P p p’ Bahadir K. Gunturk

27 Matrix form of cross product
a=axi+ayj+azk a×b=|a||b|sin(η)u b=bxi+byj+bzk Bahadir K. Gunturk

28 The Essential Matrix Essential matrix Bahadir K. Gunturk

29 A Simple Stereo System Right image: Left image: target reference
LEFT CAMERA RIGHT CAMERA baseline Elevation Zw disparity Depth Z Right image: target Left image: reference Zw=0 Bahadir K. Gunturk

30 Parallel Cameras P Z xl xr f pl pr Ol Or Disparity: T
T is the stereo baseline Bahadir K. Gunturk

31 Stereo View Left View Right View Bahadir K. Gunturk Disparity

32 Correlation Approach LEFT IMAGE (xl, yl) (0). Essential Equation represents actually the epipolar plane in either the left or the right image (1). Epipolar line in the right image given pl (Epl)Tpr=0 zr = fr extension of the equations in pr = (xr,yr,fr) (2). Epipolar line in the left image given pr (prTE) pl=0 zl = fl For Each point (xl, yl) in the left image, define a window centered at the point Bahadir K. Gunturk

33 Correlation Approach RIGHT IMAGE (xl, yl) (0). Essential Equation represents actually the epipolar plane in either the left or the right image (1). Epipolar line in the right image given pl (Epl)Tpr=0 zr = fr extension of the equations in pr = (xr,yr,fr) (2). Epipolar line in the left image given pr (prTE) pl=0 zl = fl … search its corresponding point within a search region in the right image Bahadir K. Gunturk

34 Correlation Approach RIGHT IMAGE (xr, yr) dx (xl, yl) (0). Essential Equation represents actually the epipolar plane in either the left or the right image (1). Epipolar line in the right image given pl (Epl)Tpr=0 zr = fr extension of the equations in pr = (xr,yr,fr) (2). Epipolar line in the left image given pr (prTE) pl=0 zl = fl … the disparity (dx, dy) is the displacement when the correlation is maximum Bahadir K. Gunturk

35 Stereo results Data from University of Tsukuba Scene Ground truth
(Seitz) Bahadir K. Gunturk

36 Results with window correlation
Estimated depth of field Ground truth (Seitz) Bahadir K. Gunturk

37 Results with better method
A state of the art method Boykov et al., Fast Approximate Energy Minimization via Graph Cuts, International Conference on Computer Vision, September 1999. Ground truth Bahadir K. Gunturk (Seitz)

38 Applications courtesy of Sportvision First-down line
Bahadir K. Gunturk

39 Applications courtesy of Princeton Video Image Virtual advertising
Bahadir K. Gunturk


Download ppt "Geometric Transformations"

Similar presentations


Ads by Google