Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1...
-
Upload
cory-norris -
Category
Documents
-
view
214 -
download
0
description
Transcript of Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1...
![Page 1: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/1.jpg)
1
Fitting: Voting and the Hough Transform
Thursday, September 17th 2015Devi Parikh
Virginia Tech
Slide credit: Kristen Grauman
Disclaimer: Many slides have been borrowed from Kristen Grauman, who may have borrowed some of them from others. Any time a slide did not already have a credit on it, I have credited it to Kristen. So there is a chance some of these credits are inaccurate.
![Page 2: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/2.jpg)
Announcements• PS1 due last night
• Project proposals– Due September 29th – Look at class webpage for guidelines– Data collection
• PS2 out any time now– Due October 5th
• Slides online
2Slide credit: Adapted by Devi Parikh from Kristen Grauman
![Page 3: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/3.jpg)
Topics overview• Features & filters• Grouping & fitting
– Segmentation and clustering– Hough transform– Deformable contours– Alignment and 2D image transformations
• Multiple views and motion• Recognition• Video processing
3Slide credit: Kristen Grauman
![Page 4: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/4.jpg)
Topics overview• Features & filters• Grouping & fitting
– Segmentation and clustering– Hough transform– Deformable contours– Alignment and 2D image transformations
• Multiple views and motion• Recognition• Video processing
4Slide credit: Kristen Grauman
![Page 5: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/5.jpg)
Outline• What are grouping problems in vision?
• Inspiration from human perception– Gestalt properties
• Bottom-up segmentation via clustering– Algorithms:
• Mode finding and mean shift: k-means, mean-shift• Graph-based: normalized cuts
– Features: color, texture, …• Quantization for texture summaries
5Slide credit: Kristen Grauman
![Page 6: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/6.jpg)
q
Images as graphs
• Fully-connected graph– node (vertex) for every pixel– link between every pair of pixels, p,q– affinity weight wpq for each link (edge)
• wpq measures similarity– similarity is inversely proportional to difference (in color
and position…)
p
wpq
w
Source: Steve Seitz6
![Page 7: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/7.jpg)
Measuring affinity• One possibility:
Small sigma: group only nearby points
Large sigma: group distant points
Kristen Grauman
7
![Page 8: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/8.jpg)
Example: weighted graphs
Dimension of data points : d = 2Number of data points : N = 4
• Suppose we have a 4-pixel image
(i.e., a 2 x 2 matrix)
• Each pixel described by 2 features
Feature dimension 1
Feat
ure
dim
ensi
on 2
Kristen Grauman
8
![Page 9: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/9.jpg)
for i=1:Nfor j=1:N
D(i,j) = ||xi- xj||2
endend
0.24
0.01
0.47
D(1,:)=
D(:,1)=
0.24 0.01 0.47(0)
Example: weighted graphsComputing the distance matrix:
Kristen Grauman
9
![Page 10: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/10.jpg)
for i=1:Nfor j=1:N
D(i,j) = ||xi- xj||2
endend
D(1,:)=
D(:,1)=
0.24 0.01 0.47(0)
0.15
0.24
0.29(0) 0.29 0.150.24
Example: weighted graphsComputing the distance matrix:
Kristen Grauman
10
![Page 11: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/11.jpg)
for i=1:Nfor j=1:N
D(i,j) = ||xi- xj||2
endend
N x N matrix
Example: weighted graphsComputing the distance matrix:
Kristen Grauman
11
![Page 12: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/12.jpg)
for i=1:N for j=1:N D(i,j) = ||xi- xj||2
endend
for i=1:N for j=i+1:N A(i,j) = exp(-1/(2*σ^2)*||xi- xj||2); A(j,i) = A(i,j); endend
D ADistancesaffinitiesExample: weighted graphs
Kristen Grauman
12
![Page 13: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/13.jpg)
D=
Scale parameter σ affects affinity
Distance matrix
Affinity matrix with increasing σ:
Kristen Grauman13
![Page 14: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/14.jpg)
Visualizing a shuffled affinity matrix
If we permute the order of the vertices as they are referred to in the affinity matrix, we see different patterns:
Kristen Grauman
14
![Page 15: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/15.jpg)
Measuring affinity
σ=.1 σ=.2 σ=1
σ=.2
Data points
Affinity matrices
15Slide credit: Kristen Grauman
![Page 16: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/16.jpg)
Measuring affinity
40 data points 40 x 40 affinity matrix A
2}
Points x1…x10
Points x31…x40
x1
.
.
.x40
x1 . . . x40
1. What do the blocks signify?
2. What does the symmetry of the matrix signify?
3. How would the matrix change with larger value of σ?16Slide credit: Kristen Grauman
![Page 17: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/17.jpg)
Putting it together
σ=.1 σ=.2 σ=1
Data points
Affinity matrices
Points x1…x10
Points x31…x40
2} Kristen Grauman
17
![Page 18: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/18.jpg)
Segmentation by Graph Cuts
• Break Graph into Segments– Want to delete links that cross between
segments– Easiest to break links that have low
similarity (low weight)• similar pixels should be in the same segments• dissimilar pixels should be in different segments
w
A B C
Source: Steve Seitz
q
p
wpq
18
![Page 19: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/19.jpg)
Cuts in a graph: Min cut
• Link Cut– set of links whose removal makes a graph
disconnected– cost of a cut:
A B
Find minimum cut• gives you a segmentation• fast algorithms exist for doing this
Source: Steve Seitz
BqAp
qpwBAcut,
,),(
19
![Page 20: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/20.jpg)
Minimum cut• Problem with minimum cut:
Weight of cut proportional to number of edges in the cut; tends to produce small, isolated components.
[Shi & Malik, 2000 PAMI]20
Slide credit: Kristen Grauman
![Page 21: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/21.jpg)
Cuts in a graph: Normalized cut
A B
Normalized Cut• fix bias of Min Cut by normalizing for size of segments:
assoc(A,V) = sum of weights of all edges that touch A
• Ncut value small when we get two clusters with many edges with high weights, and few edges of low weight between them
• Approximate solution for minimizing the Ncut value : generalized eigenvalue problem.
Source: Steve Seitz
),(),(
),(),(
VBassocBAcut
VAassocBAcut
J. Shi and J. Malik, Normalized Cuts and Image Segmentation, CVPR, 1997
21
![Page 22: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/22.jpg)
Example results
22Slide credit: Kristen Grauman
![Page 23: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/23.jpg)
Results: Berkeley Segmentation Engine
http://www.cs.berkeley.edu/~fowlkes/BSE/ 23
Slide credit: Kristen Grauman
![Page 24: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/24.jpg)
Normalized cuts: pros and consPros:• Generic framework, flexible to choice of function that
computes weights (“affinities”) between nodes• Does not require model of the data distribution
Cons:• Time complexity can be high
– Dense, highly connected graphs many affinity computations– Solving eigenvalue problem
• Preference for balanced partitions
Kristen Grauman
24
![Page 25: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/25.jpg)
Summary• Segmentation to find object boundaries or mid-
level regions, tokens.• Bottom-up segmentation via clustering
– General choices -- features, affinity functions, and clustering algorithms
• Grouping also useful for quantization, can create new feature summaries– Texton histograms for texture within local region
• Example clustering methods– K-means– Mean shift– Graph cut, normalized cuts 25
Slide credit: Kristen Grauman
![Page 26: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/26.jpg)
Now: Fitting• Want to associate a model with observed features
[Fig from Marszalek & Schmid, 2007]
For example, the model could be a line, a circle, or an arbitrary shape.
Kristen Grauman
26
![Page 27: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/27.jpg)
Fitting: Main idea• Choose a parametric model to represent a
set of features• Membership criterion is not local
• Can’t tell whether a point belongs to a given model just by looking at that point
• Three main questions:• What model represents this set of features best?• Which of several model instances gets which feature?• How many model instances are there?
• Computational complexity is important• It is infeasible to examine every possible set of parameters
and every possible combination of features
Slide credit: L. Lazebnik
27
![Page 28: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/28.jpg)
Example: Line fitting• Why fit lines?
Many objects characterized by presence of straight lines
• Wait, why aren’t we done just by running edge detection?Kristen Grauman
28
![Page 29: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/29.jpg)
• Extra edge points (clutter), multiple models:
– which points go with which line, if any?
• Only some parts of each line detected, and some parts are missing:
– how to find a line that bridges missing evidence?
• Noise in measured edge points, orientations:
– how to detect true underlying parameters?
Difficulty of line fitting
Kristen Grauman
29
![Page 30: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/30.jpg)
Voting• It’s not feasible to check all combinations of features by
fitting a model to each possible subset.
• Voting is a general technique where we let the features vote for all models that are compatible with it.– Cycle through features, cast votes for model parameters.– Look for model parameters that receive a lot of votes.
• Noise & clutter features will cast votes too, but typically their votes should be inconsistent with the majority of “good” features.
Kristen Grauman
30
![Page 31: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/31.jpg)
Fitting lines: Hough transform
• Given points that belong to a line, what is the line?
• How many lines are there?• Which points belong to which lines?
• Hough Transform is a voting technique that can be used to answer all of these questions.Main idea: 1. Record vote for each possible line
on which each edge point lies.2. Look for lines that get many votes.
Kristen Grauman
31
![Page 32: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/32.jpg)
Finding lines in an image: Hough space
Connection between image (x,y) and Hough (m,b) spaces• A line in the image corresponds to a point in Hough space• To go from image space to Hough space:
– given a set of points (x,y), find all (m,b) such that y = mx + b
x
y
image spacem
b
m0
b0
Hough (parameter) space
Slide credit: Steve Seitz
32
Equation of a line?y = mx + b
![Page 33: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/33.jpg)
Finding lines in an image: Hough space
Connection between image (x,y) and Hough (m,b) spaces• A line in the image corresponds to a point in Hough space• To go from image space to Hough space:
– given a set of points (x,y), find all (m,b) such that y = mx + b• What does a point (x0, y0) in the image space map to?
x
y
m
b
image space Hough (parameter) space
– Answer: the solutions of b = -x0m + y0
– this is a line in Hough space
x0
y0
Slide credit: Steve Seitz
33
![Page 34: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/34.jpg)
Finding lines in an image: Hough space
What are the line parameters for the line that contains both (x0, y0) and (x1, y1)?• It is the intersection of the lines b = –x0m + y0 and
b = –x1m + y1
x
y
m
b
image space Hough (parameter) spacex0
y0
b = –x1m + y1
(x0, y0)
(x1, y1)
34
Slide credit: Kristen Grauman
![Page 35: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/35.jpg)
Finding lines in an image: Hough algorithm
How can we use this to find the most likely parameters (m,b) for the most prominent line in the image space?
• Let each edge point in image space vote for a set of possible parameters in Hough space
• Accumulate votes in discrete set of bins; parameters with the most votes indicate line in image space.
x
y
m
b
image space Hough (parameter) space
35
Slide credit: Kristen Grauman
![Page 36: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/36.jpg)
Polar representation for lines
: perpendicular distance from line to origin
: angle the perpendicular makes with the x-axis
Point in image space sinusoid segment in Hough space
dyx sincos
d
[0,0]
d
x
y
Issues with usual (m,b) parameter space: can take on infinite values, undefined for vertical lines.
Image columns
Imag
e ro
ws
Kristen Grauman
36
![Page 37: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/37.jpg)
• Hough line demo
• http://www.dis.uniroma1.it/~iocchi/slides/icra2001/java/hough.html
37
Slide credit: Kristen Grauman
![Page 38: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/38.jpg)
Hough transform algorithmUsing the polar parameterization:
Basic Hough transform algorithm1. Initialize H[d, ]=02. for each edge point I[x,y] in the image
for = [min to max ] // some quantization
H[d, ] += 13. Find the value(s) of (d, ) where H[d, ] is maximum4. The detected line in the image is given by
H: accumulator array (votes)
d
Time complexity (in terms of number of votes per pt)?
dyx sincos
Source: Steve Seitz
sincos yxd
sincos yxd
38
![Page 39: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/39.jpg)
39
Original image Canny edges
Vote space and top peaks
Kristen Grauman
![Page 40: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/40.jpg)
Showing longest segments found
Kristen Grauman
40
![Page 41: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/41.jpg)
Impact of noise on Hough
Image spaceedge coordinates Votes
x
y d
What difficulty does this present for an implementation?41
Slide credit: Kristen Grauman
![Page 42: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/42.jpg)
Image spaceedge coordinates
Votes
Impact of noise on Hough
Here, everything appears to be “noise”, or random edge points, but we still see peaks in the vote space. 42
Slide credit: Kristen Grauman
![Page 43: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/43.jpg)
ExtensionsExtension 1: Use the image gradient
1. same2. for each edge point I[x,y] in the image
= gradient at (x,y)
H[d, ] += 13. same4. same
(Reduces degrees of freedom)
Extension 2• give more votes for stronger edges
Extension 3• change the sampling of (d, ) to give more/less resolution
Extension 4• The same procedure can be used with circles, squares, or any
other shape
sincos yxd
43
Slide credit: Kristen Grauman
![Page 44: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/44.jpg)
ExtensionsExtension 1: Use the image gradient
1. same2. for each edge point I[x,y] in the image
compute unique (d, ) based on image gradient at (x,y) H[d, ] += 1
3. same4. same
(Reduces degrees of freedom)
Extension 2• give more votes for stronger edges (use magnitude of gradient)
Extension 3• change the sampling of (d, ) to give more/less resolution
Extension 4• The same procedure can be used with circles, squares, or any
other shape…
Source: Steve Seitz
44
![Page 45: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/45.jpg)
Hough transform for circles
• For a fixed radius r
• Circle: center (a,b) and radius r222 )()( rbyax ii
Image space Hough space a
b
Adapted by Devi Parikh from: Kristen Grauman
45
Equation of circle?
Equation of set of circles that all pass through a point?
![Page 46: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/46.jpg)
Hough transform for circles
• For a fixed radius r
• Circle: center (a,b) and radius r222 )()( rbyax ii
Image space Hough space
Intersection: most votes for center occur here.
Kristen Grauman
46
![Page 47: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/47.jpg)
Hough transform for circles
• For an unknown radius r
• Circle: center (a,b) and radius r222 )()( rbyax ii
Hough spaceImage space
b
a
r
?
Kristen Grauman
47
![Page 48: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/48.jpg)
Hough transform for circles
• For an unknown radius r
• Circle: center (a,b) and radius r222 )()( rbyax ii
Hough spaceImage space
b
a
r
Kristen Grauman
48
![Page 49: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/49.jpg)
Hough transform for circles
• For an unknown radius r, known gradient direction
• Circle: center (a,b) and radius r222 )()( rbyax ii
Hough spaceImage space
θ
x
Kristen Grauman
49
![Page 50: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/50.jpg)
Hough transform for circles
For every edge pixel (x,y) : For each possible radius value r: For each possible gradient direction θ:
// or use estimated gradient at (x,y) a = x – r cos(θ) // column b = y + r sin(θ) // row H[a,b,r] += 1end
end
• Check out online demo : http://www.markschulze.net/java/hough/
Time complexity per edgel?
Kristen Grauman
50
![Page 51: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/51.jpg)
Original Edges
Example: detecting circles with HoughVotes: Penny
Note: a different Hough transform (with separate accumulators) was used for each circle radius (quarters vs. penny).
51
Slide credit: Kristen Grauman
![Page 52: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/52.jpg)
Original Edges
Example: detecting circles with HoughVotes: QuarterCombined detections
Coin finding sample images from: Vivek Kwatra
52
Slide credit: Kristen Grauman
![Page 53: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/53.jpg)
Example: iris detection
• Hemerson Pistori and Eduardo Rocha Costa http://rsbweb.nih.gov/ij/plugins/hough-circles.html
Gradient+threshold Hough space (fixed radius)
Max detections
Kristen Grauman
53
![Page 54: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/54.jpg)
Example: iris detection
• An Iris Detection Method Using the Hough Transform and Its Evaluation for Facial and Eye Movement, by Hideki Kashima, Hitoshi Hongo, Kunihito Kato, Kazuhiko Yamamoto, ACCV 2002.
Kristen Grauman
54
![Page 55: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/55.jpg)
Voting: practical tips
• Minimize irrelevant tokens first
• Choose a good grid / discretization
• Vote for neighbors, also (smoothing in accumulator array)
• Use direction of edge to reduce parameters by 1
• To read back which points voted for “winning” peaks, keep tags on the votes.
Too coarseToo fine ?
Kristen Grauman
55
![Page 56: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/56.jpg)
Hough transform: pros and consPros• All points are processed independently, so can cope with
occlusion, gaps• Some robustness to noise: noise points unlikely to
contribute consistently to any single bin• Can detect multiple instances of a model in a single pass
Cons• Complexity of search time increases exponentially with
the number of model parameters • Non-target shapes can produce spurious peaks in
parameter space• Quantization: can be tricky to pick a good grid size
Kristen Grauman
56
![Page 57: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/57.jpg)
Generalized Hough Transform
Model image Vote spaceNovel image
xxx
xx
Now suppose those colors encode gradient directions…
• What if we want to detect arbitrary shapes?
Intuition:
Ref. point
Displacement vectors
Kristen Grauman
57
![Page 58: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/58.jpg)
• Define a model shape by its boundary points and a reference point.
[Dana H. Ballard, Generalizing the Hough Transform to Detect Arbitrary Shapes, 1980]
x a
p1
θp2
θ
At each boundary point, compute displacement vector: r = a – pi.
Store these vectors in a table indexed by gradient orientation θ.
Generalized Hough Transform
Offline procedure:
Model shape
θ
θ
…
…
…
Kristen Grauman
58
![Page 59: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/59.jpg)
p1
θ θ
For each edge point:• Use its gradient orientation θ
to index into stored table • Use retrieved r vectors to
vote for reference point
Generalized Hough Transform
Detection procedure:
Assuming translation is the only transformation here, i.e., orientation and scale are fixed.
x
θ θ
Novel image
θ
θ
…
…
…
θ
xx
xx
Kristen Grauman
59
![Page 60: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/60.jpg)
Generalized Hough for object detection• Instead of indexing displacements by gradient
orientation, index by matched local patterns.
B. Leibe, A. Leonardis, and B. Schiele, Combined Object Categorization and Segmentation with an Implicit Shape Model, ECCV Workshop on Statistical Learning in Computer Vision 2004
training image
“visual codeword” withdisplacement vectors
Source: L. Lazebnik60
![Page 61: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/61.jpg)
• Instead of indexing displacements by gradient orientation, index by “visual codeword”
B. Leibe, A. Leonardis, and B. Schiele, Combined Object Categorization and Segmentation with an Implicit Shape Model, ECCV Workshop on Statistical Learning in Computer Vision 2004
test image
Source: L. Lazebnik
Generalized Hough for object detection
61
![Page 62: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/62.jpg)
Summary• Grouping/segmentation useful to make a compact
representation and merge similar features– associate features based on defined similarity measure and
clustering objective
• Fitting problems require finding any supporting evidence for a model, even within clutter and missing features.– associate features with an explicit model
• Voting approaches, such as the Hough transform, make it possible to find likely model parameters without searching all combinations of features.– Hough transform approach for lines, circles, …, arbitrary shapes
defined by a set of boundary points, recognition from patches.Kristen Grauman
62
![Page 63: Fitting : Voting and the Hough Transform Thursday, September 17 th 2015 Devi Parikh Virginia Tech 1 Slide credit: Kristen Grauman Disclaimer: Many slides.](https://reader036.fdocuments.us/reader036/viewer/2022062600/5a4d1b897f8b9ab0599bdf44/html5/thumbnails/63.jpg)
Questions?
See you Tuesday!
63