SlideShare una empresa de Scribd logo
1 de 42
Optimization algorithms for solving
computer vision problems
Olgierd Stankiewicz
Krzysztof Wegner
Chair of Multimedia Telecommunications
and Microelectronics
Poznań University of Technology
Poznań, April 2015
Computer Vision Problems
 Segmentation
 Assigning
each pixel of the image
to a certain
segment
 Depth estimation
 Assigning
a depth value
to
each pixel of the image
2
Computer Vision Problems
 Image stitching
 Assigning
each pixel
of the output image
to a certain source image (transformed)
 Image restoration
 Assigning
to each pixel
of the output image
a colour
from the source image 3
Computer Vision Generalization
 Can be seen as labeling problem
 Assigning
to each pixel of the output image
a label
defined in a certain way
 Label is an index from all possible answers
 Segment index
 Disparity
 Stitched image index
 Colour
4
1 2 5 5 6 2 1 4
3 5 3 4 4 1 8 3
5 4 0 4 7 2 9 6
7 2 2 4 5 3 6 8
2 1 4 0 0 3 4 3
𝑑 𝑥,𝑦 - label
Energy minimization
 There are many ways to label pixels
in an image
 Which one is better?
 What it the goal?
 Energy minimalization problem
5
𝐸 𝑓0,0, 𝑓0,1, … , 𝑓 𝑊−1,0, 𝑓1,0, … … 𝑓 𝑊−1,𝐻−1 = 𝑚𝑖𝑛
𝑓𝑥,𝑦 – label for pixel x,y
𝑊, 𝐻 – image size
Simple?
 Not simple!
 Multivariable, e.g. 1920 x 1080 ≈ 2M varables
 Energy function can be very complex
 Non-monotonic
 Non-linear
 Implicit, with inter-label references
 Classic Stepest Desent
 Not too efficient
 Would probably not find the solution anyway
6
Efficient minimalization
 Special class of energy functions can be
minimalized more efficiently
 Energy function decomposed into sum of:
 Unary terms
 Pairwise terms
 Unary and pairwise terms
7
𝐸 =
𝑥,𝑦
𝑈 𝑥,𝑦 𝑓𝑥,𝑦
𝐸 =
𝑥,𝑦,𝑧,𝑤
𝑇𝑥,𝑦,𝑧,𝑤 𝑓𝑥,𝑦, 𝑓𝑧,𝑤
Efficient minimalization
 Even more efficient when
 Binary labeling problem
 Function argument can be 0 or 1
 Energy function is convex (submodular)
 Triangle inequality
 E.g.
 Monotone
 Linear (Planar etc.)
8
𝑥 + 𝑦 ≤ 𝑥 + |𝑦|
Example 1
 Binary segmentation
 Labels 𝑓𝑥,𝑦 are black(0) and white (1)
 Input image 𝐼 𝑥, 𝑦 𝜖[0..1]
 | ∙ | Linear luminance penalty
 Regularization
 4-pixel neighbourhood
 |∙| Linear segment index difference penalty
9
Left Right
Top
Bottom
dx,y
dx,y-1
dx,y+1
dx-1,y dx+1,y
}
Unary terms
Pairwise terms
𝐸 =
𝑥,𝑦
𝐼 𝑥, 𝑦 − 𝑓𝑥,𝑦
+ 𝑓𝑥,𝑦 − 𝑓𝑥+1,𝑦 ∙ 𝛼
+ 𝑓𝑥,𝑦 − 𝑓𝑥−1,𝑦 ∙ 𝛼
+ 𝑓𝑥,𝑦 − 𝑓𝑥,𝑦−1 ∙ 𝛼
+ 𝑓𝑥,𝑦 − 𝑓𝑥,𝑦+1 ∙ 𝛼
Example 2
 Depth estimation
 Labels 𝑑 𝑥,𝑦 are disparities
 Image matching between pixels in the left/right image
 | ∙ | Linear luminance penalty
 Regularization
 4-pixel neighbourhood
 |∙| Linear disparity difference penalty
10
Left Right
Top
Bottom
dx,y
dx,y-1
dx,y+1
dx-1,y dx+1,y
}
Unary terms
Pairwise terms
𝐸 =
𝑥,𝑦
𝐿 𝑥 + 𝑑 𝑥,𝑦, 𝑦 − 𝑅 𝑥, 𝑦
+ 𝑑 𝑥,𝑦 − 𝑑 𝑥+1,𝑦 ∙ 𝛼
+ 𝑑 𝑥,𝑦 − 𝑑 𝑥−1,𝑦 ∙ 𝛼
+ 𝑑 𝑥,𝑦 − 𝑑 𝑥,𝑦−1 ∙ 𝛼
+ 𝑑 𝑥,𝑦 − 𝑑 𝑥,𝑦+1 ∙ 𝛼
Optimization algorithms
 Viterbi
 State transitions
 Well knowm
 Belief Propagation
 Message passing
 Presented before
 Graph Cuts
11
Node of Markov field, defined by all
possible disparities and their probabilities
Two-directional connection
between nodes of Markov field
........
........
One-directional connection
between nodes of Markov field
a) b)
each-to-each each-to-each
Transition between the states
Graph Cuts
 Graph Cuts can be used for efficient unary
and pairwise energy minimization
 Min Cut == Max Flow theorem
 Solving of
Minimal Cut problem in a graph
is equal to solving of
Maximal Flow problem in the same graph
 Efficient generic algorithms
 Expression of
energy minimization problem
as
MinCut
12
Graphs
 Nodes
 Edges
 Capacity
 Flow (in a particular solution)
 Constraints
 Flow ≤ Capacity
 Flow conservation
 E.g. communication network
13
Minimum s-t cuts
 Special nodes
 S - Source
 T - Sink (Terminal)
 Algorithms
 Augmenting paths [Ford & Fulkerson, 1962]
 Push-relabel [Goldberg-Tarjan, 1986]
14
Augmenting Paths
 Find a path from S to T along non-saturated
edges
 Increase flow along this path until some
edge saturates
15
Augmenting Paths
 Find next path
 Increase flow
16
Augmenting Paths
 Iterate until all paths from S to T have at
least one saturated edge
17
Example
 Let’s assume a graph
 Nodes: s,o,p,q,r,t
 Flow=0
18
s
t
o
p
q
r
sink
terminal
0/3
0/3
0/2
0/3
0/2
0/3
0/4
0/2
Example
 Path 1, Free Capacity:2
19
s
t
o
p
q
r
sink
terminal
0/3
0/3
0/2
0/3
0/2
0/3
0/4
0/2
Example
 Path 1, Add Flow:2
20
s
t
o
p
q
r
sink
terminal
2/3
0/3
0/2
2/3
2/2
0/3
0/4
0/2
Example
 Path 2, Free Capacity:1
21
s
t
o
p
q
r
sink
terminal
2/3
0/3
0/2
2/3
2/2
0/3
0/4
0/2
Example
 Path 2, Add Flow:1
22
s
t
o
p
q
r
sink
terminal
3/3
0/3
0/2
3/3
2/2
1/3
1/4
0/2
Example
 Path 3, Free Capacity:0
23
s
t
o
p
q
r
sink
terminal
3/3
0/3
0/2
3/3
2/2
1/3
1/4
0/2
Example
 Path 4, Free Capacity:2
24
s
t
o
p
q
r
sink
terminal
3/3
0/3
0/2
3/3
2/2
1/3
1/4
0/2
Example
 Path 4, Add Flow:2
25
s
t
o
p
q
r
sink
terminal
3/3
2/3
0/2
3/3
2/2
3/3
1/4
2/2
Example - flow
 Flow from sink: 5 = Flow to terminal: 5
 Maximal flow = 5
26
s
t
o
p
q
r
sink
terminal
3/3
2/3
0/2
3/3
2/2
3/3
1/4
2/2
Example - cut
 All possible cuts
27
s
t
o
p
q
r
sink
terminal
3
3
2
3
2
3
4
2
6
8
7
10
8
5
5
Example – minimal cut
 Minimal Cut = 5
 Two equi-optimal cuts
28
s
t
o
p
q
r
sink
terminal
3
3
2
3
2
3
4
2
5
5
Complexity
 V – number of nodes
 E – number of edges
 Augmenting paths
 𝑂(𝑉 ∙ 𝐸) via bucket data sorting
 Kolmogorov
 𝑂 𝑉 ∙ 𝐸
 Push-relabel
 𝑂 𝑉2 𝐸
 But parrarelizable 29
Graph construction
30
min
𝑓1,𝑓2,…,𝑓𝑛−1,𝑓𝑛
𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛
𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 =
𝑖
𝐸𝑖 𝑓𝑖 +
𝑖
𝐸𝑖,𝑗 𝑓𝑖, 𝑓𝑗
 Each cut throught the graph must represent
energy (some potential solution)
 The graph is a sum of elementary graphs for
each energy term
Graph construction
31
min
𝑓1,𝑓2,…,𝑓𝑛−1,𝑓𝑛
𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛
𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 =
𝑖
𝐸𝑖 𝑓𝑖 +
𝑖
𝐸𝑖,𝑗 𝑓𝑖, 𝑓𝑗
𝐸𝑖 1 − 𝐸𝑖 0
𝑓=1s
𝑓=0t
𝐸𝑖 0 − 𝐸𝑖 1
𝑓=1s
𝑓=0t
𝐸𝑖 1 > 𝐸𝑖 0 𝐸𝑖 1 < 𝐸𝑖 0
𝑓𝑖=0 𝑓𝑖=1
𝐸𝑖 𝑓𝑖 2 3
𝑣𝑖 𝑣𝑖
Graph construction
 x
32
min
𝑓1,𝑓2,…,𝑓𝑛−1,𝑓𝑛
𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛
𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 =
𝑖
𝐸𝑖 𝑓𝑖 +
𝑖
𝐸𝑖,𝑗 𝑓𝑖, 𝑓𝑗
𝐸𝑖,𝑗 1,0 − 𝐸𝑖,𝑗 0,0
𝑓=1s
𝑓=0t
𝑣𝑖
𝑣𝑗
𝐸𝑖,𝑗 1,0 − 𝐸𝑖,𝑗 1,1
𝐸𝑖,𝑗 0,1 + 𝐸𝑖,𝑗 1,0 − 𝐸𝑖,𝑗 0,0 -𝐸𝑖,𝑗 1,1
𝐸𝑖,j 𝑓𝑖, 𝑓𝑗 𝑓j=0 𝑓j=1
𝑓𝑖=0 2 3
𝑓𝑖=1 4 5
Graph construction
33
𝐸𝑖,j 𝑓𝑖, 𝑓𝑗 𝑓j=0 𝑓j=1
𝑓𝑖=0 𝐸𝑖,j 0,0 𝐸𝑖,j 0,1
𝑓𝑖=1 𝐸𝑖,j 1,0 𝐸𝑖,j 1,1
Assume that 𝐸𝑖,j 0,0 is the biggest
𝐸𝑖,j 0,0 𝐸𝑖,j 0,1
𝐸𝑖,j 1,0 𝐸𝑖,j 1,1
=𝐸𝑖,j 0,0 +
0 𝐸𝑖,j 0,1 -𝐸𝑖,j 0,0
𝐸𝑖,j 1,0 -𝐸𝑖,j 0,0 𝐸𝑖,j 1,1 -𝐸𝑖,j 0,0
=𝐸𝑖,j 0,0 +
=
0 0
𝐸𝑖,j 1,0 -𝐸𝑖,j 0,0 𝐸𝑖,j 1,0 -𝐸𝑖,j 0,0
+
0 𝐸𝑖,j 1,1 -𝐸𝑖,j 1,0
0 𝐸𝑖,j 1,1 -𝐸𝑖,j 1,0
+
0 𝐸𝑖,j 0,1 + 𝐸𝑖,j 1,0 − 𝐸𝑖,j 0,0 − 𝐸𝑖,j 1,1
0 0
+
Graph construction
34
min
𝑓1,𝑓2,…,𝑓𝑛−1,𝑓𝑛
𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛
𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 =
𝑖
𝐸𝑖 𝑓𝑖 +
𝑖
𝐸𝑖,𝑗 𝑓𝑖, 𝑓𝑗
𝑓=1s
𝑓=0t
𝑣1
𝑣 𝑛𝑣 𝑛−1𝑣2 𝑣…
Multilabel energy
 𝑓𝑖 can be not only binary
 Multilabel
 The are two graphs constructions commonly
used
 Ishikawa multilabel graph
 Move graph construction
35
Ishikawa graph
 Roy&Cox 98 and Ishikawa 1998, 2000, 2003
36
Ishikawa graph
37
Ishikawa graph
38
 Many nodes required at once
 Many edges
 Very slow
 Restricted only to linear, pairwise terms
a-expansion
 Solves series of binary problems
 𝑓𝑖 can be:
 0 – keep the current label
 1 – change the label to a
39
a-expansion
 Start with any* initial solution
 For each label a in any (e.g. random) order
 Compute optimal a-expansion move
(binary problem)
 Reject the move if there is no energy decrease
 Stop when no expansion move would
decrease energy
40
a-expansion
 Typically two cycles throught all labels are
required
 *Depends on the initial solution
 At given iteration „some” solution is known
 In Ishikawa only after solving the whole graph
41
Thank you for attention
 Questions?
42

Más contenido relacionado

La actualidad más candente

Integer programming branch and bound
Integer programming   branch and boundInteger programming   branch and bound
Integer programming branch and boundAlejandro Angulo
 
Integration with limits
Integration with limitsIntegration with limits
Integration with limitsShaun Wilson
 
RETOOLING OF COLOR IMAGING IN THE QUATERNION ALGEBRA
RETOOLING OF COLOR IMAGING IN THE QUATERNION ALGEBRARETOOLING OF COLOR IMAGING IN THE QUATERNION ALGEBRA
RETOOLING OF COLOR IMAGING IN THE QUATERNION ALGEBRAmathsjournal
 
Basics of pixel neighbor.
Basics of pixel neighbor.Basics of pixel neighbor.
Basics of pixel neighbor.raheel rajput
 
09 p.t (straight line + circle) solution
09 p.t (straight line + circle) solution09 p.t (straight line + circle) solution
09 p.t (straight line + circle) solutionAnamikaRoy39
 
Bresenham's line drawing algorithm
Bresenham's line drawing algorithmBresenham's line drawing algorithm
Bresenham's line drawing algorithmMani Kanth
 
Nonlinear programming 2013
Nonlinear programming 2013Nonlinear programming 2013
Nonlinear programming 2013sharifz
 
preparation of a unit "identities"
preparation of a unit "identities"preparation of a unit "identities"
preparation of a unit "identities"Naseera noushad
 

La actualidad más candente (14)

Chap2
Chap2Chap2
Chap2
 
Integer programming branch and bound
Integer programming   branch and boundInteger programming   branch and bound
Integer programming branch and bound
 
Integration with limits
Integration with limitsIntegration with limits
Integration with limits
 
RETOOLING OF COLOR IMAGING IN THE QUATERNION ALGEBRA
RETOOLING OF COLOR IMAGING IN THE QUATERNION ALGEBRARETOOLING OF COLOR IMAGING IN THE QUATERNION ALGEBRA
RETOOLING OF COLOR IMAGING IN THE QUATERNION ALGEBRA
 
Basics of pixel neighbor.
Basics of pixel neighbor.Basics of pixel neighbor.
Basics of pixel neighbor.
 
09 p.t (straight line + circle) solution
09 p.t (straight line + circle) solution09 p.t (straight line + circle) solution
09 p.t (straight line + circle) solution
 
Regression
RegressionRegression
Regression
 
Maths mind paper 2013
Maths mind paper 2013Maths mind paper 2013
Maths mind paper 2013
 
Render 09
Render 09Render 09
Render 09
 
9 chap
9 chap9 chap
9 chap
 
Bresenham's line drawing algorithm
Bresenham's line drawing algorithmBresenham's line drawing algorithm
Bresenham's line drawing algorithm
 
Algebra formulas
Algebra formulas Algebra formulas
Algebra formulas
 
Nonlinear programming 2013
Nonlinear programming 2013Nonlinear programming 2013
Nonlinear programming 2013
 
preparation of a unit "identities"
preparation of a unit "identities"preparation of a unit "identities"
preparation of a unit "identities"
 

Similar a Optimization algorithms for solving computer vision problems

Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)
Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)
Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)STAIR Lab, Chiba Institute of Technology
 
Order-Picking-Policies.ppt
Order-Picking-Policies.pptOrder-Picking-Policies.ppt
Order-Picking-Policies.pptTaspiyaAfroz
 
Mm chap08 -_lossy_compression_algorithms
Mm chap08 -_lossy_compression_algorithmsMm chap08 -_lossy_compression_algorithms
Mm chap08 -_lossy_compression_algorithmsEellekwameowusu
 
Extended network and algorithm finding maximal flows
Extended network and algorithm finding maximal flows Extended network and algorithm finding maximal flows
Extended network and algorithm finding maximal flows IJECEIAES
 
Ip 5 discrete mathematics
Ip 5 discrete mathematicsIp 5 discrete mathematics
Ip 5 discrete mathematicsMark Simon
 
Introduction to Neural Networks and Deep Learning from Scratch
Introduction to Neural Networks and Deep Learning from ScratchIntroduction to Neural Networks and Deep Learning from Scratch
Introduction to Neural Networks and Deep Learning from ScratchAhmed BESBES
 
Discrete Math IP4 - Automata Theory
Discrete Math IP4 - Automata TheoryDiscrete Math IP4 - Automata Theory
Discrete Math IP4 - Automata TheoryMark Simon
 
Applied Algorithms and Structures week999
Applied Algorithms and Structures week999Applied Algorithms and Structures week999
Applied Algorithms and Structures week999fashiontrendzz20
 
Unit-2 raster scan graphics,line,circle and polygon algorithms
Unit-2 raster scan graphics,line,circle and polygon algorithmsUnit-2 raster scan graphics,line,circle and polygon algorithms
Unit-2 raster scan graphics,line,circle and polygon algorithmsAmol Gaikwad
 
Count-Distinct Problem
Count-Distinct ProblemCount-Distinct Problem
Count-Distinct ProblemKai Zhang
 
Computer Graphics Unit 1
Computer Graphics Unit 1Computer Graphics Unit 1
Computer Graphics Unit 1aravindangc
 
A MODIFIED DIRECTIONAL WEIGHTED CASCADED-MASK MEDIAN FILTER FOR REMOVAL OF RA...
A MODIFIED DIRECTIONAL WEIGHTED CASCADED-MASK MEDIAN FILTER FOR REMOVAL OF RA...A MODIFIED DIRECTIONAL WEIGHTED CASCADED-MASK MEDIAN FILTER FOR REMOVAL OF RA...
A MODIFIED DIRECTIONAL WEIGHTED CASCADED-MASK MEDIAN FILTER FOR REMOVAL OF RA...cscpconf
 
Image Acquisition and Representation
Image Acquisition and RepresentationImage Acquisition and Representation
Image Acquisition and RepresentationAmnaakhaan
 
Unit-1 Basic Concept of Algorithm.pptx
Unit-1 Basic Concept of Algorithm.pptxUnit-1 Basic Concept of Algorithm.pptx
Unit-1 Basic Concept of Algorithm.pptxssuser01e301
 

Similar a Optimization algorithms for solving computer vision problems (20)

Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)
Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)
Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)
 
Order-Picking-Policies.ppt
Order-Picking-Policies.pptOrder-Picking-Policies.ppt
Order-Picking-Policies.ppt
 
Mm chap08 -_lossy_compression_algorithms
Mm chap08 -_lossy_compression_algorithmsMm chap08 -_lossy_compression_algorithms
Mm chap08 -_lossy_compression_algorithms
 
Extended network and algorithm finding maximal flows
Extended network and algorithm finding maximal flows Extended network and algorithm finding maximal flows
Extended network and algorithm finding maximal flows
 
On Cubic Graceful Labeling
On Cubic Graceful LabelingOn Cubic Graceful Labeling
On Cubic Graceful Labeling
 
algorithm Unit 3
algorithm Unit 3algorithm Unit 3
algorithm Unit 3
 
Ip 5 discrete mathematics
Ip 5 discrete mathematicsIp 5 discrete mathematics
Ip 5 discrete mathematics
 
Project2
Project2Project2
Project2
 
Introduction to Neural Networks and Deep Learning from Scratch
Introduction to Neural Networks and Deep Learning from ScratchIntroduction to Neural Networks and Deep Learning from Scratch
Introduction to Neural Networks and Deep Learning from Scratch
 
Discrete Math IP4 - Automata Theory
Discrete Math IP4 - Automata TheoryDiscrete Math IP4 - Automata Theory
Discrete Math IP4 - Automata Theory
 
Applied Algorithms and Structures week999
Applied Algorithms and Structures week999Applied Algorithms and Structures week999
Applied Algorithms and Structures week999
 
Unit-2 raster scan graphics,line,circle and polygon algorithms
Unit-2 raster scan graphics,line,circle and polygon algorithmsUnit-2 raster scan graphics,line,circle and polygon algorithms
Unit-2 raster scan graphics,line,circle and polygon algorithms
 
raster algorithm.pdf
raster algorithm.pdfraster algorithm.pdf
raster algorithm.pdf
 
Count-Distinct Problem
Count-Distinct ProblemCount-Distinct Problem
Count-Distinct Problem
 
Traveling Salesman Problem
Traveling Salesman Problem Traveling Salesman Problem
Traveling Salesman Problem
 
Computer Graphics Unit 1
Computer Graphics Unit 1Computer Graphics Unit 1
Computer Graphics Unit 1
 
Unit 3 daa
Unit 3 daaUnit 3 daa
Unit 3 daa
 
A MODIFIED DIRECTIONAL WEIGHTED CASCADED-MASK MEDIAN FILTER FOR REMOVAL OF RA...
A MODIFIED DIRECTIONAL WEIGHTED CASCADED-MASK MEDIAN FILTER FOR REMOVAL OF RA...A MODIFIED DIRECTIONAL WEIGHTED CASCADED-MASK MEDIAN FILTER FOR REMOVAL OF RA...
A MODIFIED DIRECTIONAL WEIGHTED CASCADED-MASK MEDIAN FILTER FOR REMOVAL OF RA...
 
Image Acquisition and Representation
Image Acquisition and RepresentationImage Acquisition and Representation
Image Acquisition and Representation
 
Unit-1 Basic Concept of Algorithm.pptx
Unit-1 Basic Concept of Algorithm.pptxUnit-1 Basic Concept of Algorithm.pptx
Unit-1 Basic Concept of Algorithm.pptx
 

Más de Krzysztof Wegner

Wprowadzenie teoretyczne do przestrzeni pola światła
Wprowadzenie teoretyczne do przestrzeni pola światłaWprowadzenie teoretyczne do przestrzeni pola światła
Wprowadzenie teoretyczne do przestrzeni pola światłaKrzysztof Wegner
 
Techniki rejestracji i przetwarzania pola światła
Techniki rejestracji i przetwarzania pola światłaTechniki rejestracji i przetwarzania pola światła
Techniki rejestracji i przetwarzania pola światłaKrzysztof Wegner
 
New omnidirectional test sequences
New omnidirectional test sequencesNew omnidirectional test sequences
New omnidirectional test sequencesKrzysztof Wegner
 
Omni LightFiled Experimental System
Omni LightFiled Experimental SystemOmni LightFiled Experimental System
Omni LightFiled Experimental SystemKrzysztof Wegner
 
Overview of the evaluation framework for 3DoF+
Overview of the evaluation framework for 3DoF+Overview of the evaluation framework for 3DoF+
Overview of the evaluation framework for 3DoF+Krzysztof Wegner
 
Camera calibration technique
Camera calibration techniqueCamera calibration technique
Camera calibration techniqueKrzysztof Wegner
 
Techniki kalibracji systemów wielowidokowych wprowadzenie teoretyczne
Techniki kalibracji systemów wielowidokowych wprowadzenie teoretyczneTechniki kalibracji systemów wielowidokowych wprowadzenie teoretyczne
Techniki kalibracji systemów wielowidokowych wprowadzenie teoretyczneKrzysztof Wegner
 
Architektura kodera HEVC-3D Kodowanie wielowidokowych sekwencji wizyjnych z ...
Architektura kodera HEVC-3D Kodowanie wielowidokowych sekwencji wizyjnych z ...Architektura kodera HEVC-3D Kodowanie wielowidokowych sekwencji wizyjnych z ...
Architektura kodera HEVC-3D Kodowanie wielowidokowych sekwencji wizyjnych z ...Krzysztof Wegner
 
Wyznaczenie map głębi z jednoczesną estymacją przysłonięć
Wyznaczenie map głębi z jednoczesną estymacją przysłonięćWyznaczenie map głębi z jednoczesną estymacją przysłonięć
Wyznaczenie map głębi z jednoczesną estymacją przysłonięćKrzysztof Wegner
 
Telewizja trójwymiarowa - wyzwania
Telewizja trójwymiarowa - wyzwaniaTelewizja trójwymiarowa - wyzwania
Telewizja trójwymiarowa - wyzwaniaKrzysztof Wegner
 
Implementacja algorytmów na procesory kart graficznych
Implementacja algorytmów na procesory kart graficznychImplementacja algorytmów na procesory kart graficznych
Implementacja algorytmów na procesory kart graficznychKrzysztof Wegner
 
Nowoczesne techniki wyznaczania map głębi
Nowoczesne techniki wyznaczania map głębiNowoczesne techniki wyznaczania map głębi
Nowoczesne techniki wyznaczania map głębiKrzysztof Wegner
 
Synteza widoków wirtualnych w systemach telewizji swobodnego punktu widzenia
Synteza widoków wirtualnych w systemach telewizji swobodnego punktu widzeniaSynteza widoków wirtualnych w systemach telewizji swobodnego punktu widzenia
Synteza widoków wirtualnych w systemach telewizji swobodnego punktu widzeniaKrzysztof Wegner
 

Más de Krzysztof Wegner (20)

Wprowadzenie teoretyczne do przestrzeni pola światła
Wprowadzenie teoretyczne do przestrzeni pola światłaWprowadzenie teoretyczne do przestrzeni pola światła
Wprowadzenie teoretyczne do przestrzeni pola światła
 
Techniki rejestracji i przetwarzania pola światła
Techniki rejestracji i przetwarzania pola światłaTechniki rejestracji i przetwarzania pola światła
Techniki rejestracji i przetwarzania pola światła
 
MUCHA StartCupDay
MUCHA StartCupDayMUCHA StartCupDay
MUCHA StartCupDay
 
3DoF+ Framework Overview
3DoF+ Framework Overview3DoF+ Framework Overview
3DoF+ Framework Overview
 
New omnidirectional test sequences
New omnidirectional test sequencesNew omnidirectional test sequences
New omnidirectional test sequences
 
Omni LightFiled System
Omni LightFiled SystemOmni LightFiled System
Omni LightFiled System
 
Omni LightFiled Experimental System
Omni LightFiled Experimental SystemOmni LightFiled Experimental System
Omni LightFiled Experimental System
 
MTP_2023_Mucha.pptx
MTP_2023_Mucha.pptxMTP_2023_Mucha.pptx
MTP_2023_Mucha.pptx
 
Overview of the evaluation framework for 3DoF+
Overview of the evaluation framework for 3DoF+Overview of the evaluation framework for 3DoF+
Overview of the evaluation framework for 3DoF+
 
Okienka Systemu Windows
Okienka Systemu WindowsOkienka Systemu Windows
Okienka Systemu Windows
 
Camera calibration technique
Camera calibration techniqueCamera calibration technique
Camera calibration technique
 
Techniki kalibracji systemów wielowidokowych wprowadzenie teoretyczne
Techniki kalibracji systemów wielowidokowych wprowadzenie teoretyczneTechniki kalibracji systemów wielowidokowych wprowadzenie teoretyczne
Techniki kalibracji systemów wielowidokowych wprowadzenie teoretyczne
 
3D-HEVC Test Model
3D-HEVC Test Model 3D-HEVC Test Model
3D-HEVC Test Model
 
Architektura kodera HEVC-3D Kodowanie wielowidokowych sekwencji wizyjnych z ...
Architektura kodera HEVC-3D Kodowanie wielowidokowych sekwencji wizyjnych z ...Architektura kodera HEVC-3D Kodowanie wielowidokowych sekwencji wizyjnych z ...
Architektura kodera HEVC-3D Kodowanie wielowidokowych sekwencji wizyjnych z ...
 
Wyznaczenie map głębi z jednoczesną estymacją przysłonięć
Wyznaczenie map głębi z jednoczesną estymacją przysłonięćWyznaczenie map głębi z jednoczesną estymacją przysłonięć
Wyznaczenie map głębi z jednoczesną estymacją przysłonięć
 
Telewizja trójwymiarowa - wyzwania
Telewizja trójwymiarowa - wyzwaniaTelewizja trójwymiarowa - wyzwania
Telewizja trójwymiarowa - wyzwania
 
Implementacja algorytmów na procesory kart graficznych
Implementacja algorytmów na procesory kart graficznychImplementacja algorytmów na procesory kart graficznych
Implementacja algorytmów na procesory kart graficznych
 
Nowoczesne techniki wyznaczania map głębi
Nowoczesne techniki wyznaczania map głębiNowoczesne techniki wyznaczania map głębi
Nowoczesne techniki wyznaczania map głębi
 
Synteza widoków wirtualnych w systemach telewizji swobodnego punktu widzenia
Synteza widoków wirtualnych w systemach telewizji swobodnego punktu widzeniaSynteza widoków wirtualnych w systemach telewizji swobodnego punktu widzenia
Synteza widoków wirtualnych w systemach telewizji swobodnego punktu widzenia
 
Repozytoria GIT
Repozytoria GITRepozytoria GIT
Repozytoria GIT
 

Último

Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationnomboosow
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991RKavithamani
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...EduSkills OECD
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Celine George
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...Marc Dusseiller Dusjagr
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpinRaunakKeshri1
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfJayanti Pande
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphThiyagu K
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Educationpboyjonauth
 
URLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website AppURLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website AppCeline George
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfciinovamais
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityGeoBlogs
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdfSoniaTolstoy
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3JemimahLaneBuaron
 

Último (20)

Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communication
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
 
Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpin
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Education
 
URLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website AppURLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website App
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
 
Staff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSDStaff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSD
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3
 

Optimization algorithms for solving computer vision problems

  • 1. Optimization algorithms for solving computer vision problems Olgierd Stankiewicz Krzysztof Wegner Chair of Multimedia Telecommunications and Microelectronics Poznań University of Technology Poznań, April 2015
  • 2. Computer Vision Problems  Segmentation  Assigning each pixel of the image to a certain segment  Depth estimation  Assigning a depth value to each pixel of the image 2
  • 3. Computer Vision Problems  Image stitching  Assigning each pixel of the output image to a certain source image (transformed)  Image restoration  Assigning to each pixel of the output image a colour from the source image 3
  • 4. Computer Vision Generalization  Can be seen as labeling problem  Assigning to each pixel of the output image a label defined in a certain way  Label is an index from all possible answers  Segment index  Disparity  Stitched image index  Colour 4 1 2 5 5 6 2 1 4 3 5 3 4 4 1 8 3 5 4 0 4 7 2 9 6 7 2 2 4 5 3 6 8 2 1 4 0 0 3 4 3 𝑑 𝑥,𝑦 - label
  • 5. Energy minimization  There are many ways to label pixels in an image  Which one is better?  What it the goal?  Energy minimalization problem 5 𝐸 𝑓0,0, 𝑓0,1, … , 𝑓 𝑊−1,0, 𝑓1,0, … … 𝑓 𝑊−1,𝐻−1 = 𝑚𝑖𝑛 𝑓𝑥,𝑦 – label for pixel x,y 𝑊, 𝐻 – image size
  • 6. Simple?  Not simple!  Multivariable, e.g. 1920 x 1080 ≈ 2M varables  Energy function can be very complex  Non-monotonic  Non-linear  Implicit, with inter-label references  Classic Stepest Desent  Not too efficient  Would probably not find the solution anyway 6
  • 7. Efficient minimalization  Special class of energy functions can be minimalized more efficiently  Energy function decomposed into sum of:  Unary terms  Pairwise terms  Unary and pairwise terms 7 𝐸 = 𝑥,𝑦 𝑈 𝑥,𝑦 𝑓𝑥,𝑦 𝐸 = 𝑥,𝑦,𝑧,𝑤 𝑇𝑥,𝑦,𝑧,𝑤 𝑓𝑥,𝑦, 𝑓𝑧,𝑤
  • 8. Efficient minimalization  Even more efficient when  Binary labeling problem  Function argument can be 0 or 1  Energy function is convex (submodular)  Triangle inequality  E.g.  Monotone  Linear (Planar etc.) 8 𝑥 + 𝑦 ≤ 𝑥 + |𝑦|
  • 9. Example 1  Binary segmentation  Labels 𝑓𝑥,𝑦 are black(0) and white (1)  Input image 𝐼 𝑥, 𝑦 𝜖[0..1]  | ∙ | Linear luminance penalty  Regularization  4-pixel neighbourhood  |∙| Linear segment index difference penalty 9 Left Right Top Bottom dx,y dx,y-1 dx,y+1 dx-1,y dx+1,y } Unary terms Pairwise terms 𝐸 = 𝑥,𝑦 𝐼 𝑥, 𝑦 − 𝑓𝑥,𝑦 + 𝑓𝑥,𝑦 − 𝑓𝑥+1,𝑦 ∙ 𝛼 + 𝑓𝑥,𝑦 − 𝑓𝑥−1,𝑦 ∙ 𝛼 + 𝑓𝑥,𝑦 − 𝑓𝑥,𝑦−1 ∙ 𝛼 + 𝑓𝑥,𝑦 − 𝑓𝑥,𝑦+1 ∙ 𝛼
  • 10. Example 2  Depth estimation  Labels 𝑑 𝑥,𝑦 are disparities  Image matching between pixels in the left/right image  | ∙ | Linear luminance penalty  Regularization  4-pixel neighbourhood  |∙| Linear disparity difference penalty 10 Left Right Top Bottom dx,y dx,y-1 dx,y+1 dx-1,y dx+1,y } Unary terms Pairwise terms 𝐸 = 𝑥,𝑦 𝐿 𝑥 + 𝑑 𝑥,𝑦, 𝑦 − 𝑅 𝑥, 𝑦 + 𝑑 𝑥,𝑦 − 𝑑 𝑥+1,𝑦 ∙ 𝛼 + 𝑑 𝑥,𝑦 − 𝑑 𝑥−1,𝑦 ∙ 𝛼 + 𝑑 𝑥,𝑦 − 𝑑 𝑥,𝑦−1 ∙ 𝛼 + 𝑑 𝑥,𝑦 − 𝑑 𝑥,𝑦+1 ∙ 𝛼
  • 11. Optimization algorithms  Viterbi  State transitions  Well knowm  Belief Propagation  Message passing  Presented before  Graph Cuts 11 Node of Markov field, defined by all possible disparities and their probabilities Two-directional connection between nodes of Markov field ........ ........ One-directional connection between nodes of Markov field a) b) each-to-each each-to-each Transition between the states
  • 12. Graph Cuts  Graph Cuts can be used for efficient unary and pairwise energy minimization  Min Cut == Max Flow theorem  Solving of Minimal Cut problem in a graph is equal to solving of Maximal Flow problem in the same graph  Efficient generic algorithms  Expression of energy minimization problem as MinCut 12
  • 13. Graphs  Nodes  Edges  Capacity  Flow (in a particular solution)  Constraints  Flow ≤ Capacity  Flow conservation  E.g. communication network 13
  • 14. Minimum s-t cuts  Special nodes  S - Source  T - Sink (Terminal)  Algorithms  Augmenting paths [Ford & Fulkerson, 1962]  Push-relabel [Goldberg-Tarjan, 1986] 14
  • 15. Augmenting Paths  Find a path from S to T along non-saturated edges  Increase flow along this path until some edge saturates 15
  • 16. Augmenting Paths  Find next path  Increase flow 16
  • 17. Augmenting Paths  Iterate until all paths from S to T have at least one saturated edge 17
  • 18. Example  Let’s assume a graph  Nodes: s,o,p,q,r,t  Flow=0 18 s t o p q r sink terminal 0/3 0/3 0/2 0/3 0/2 0/3 0/4 0/2
  • 19. Example  Path 1, Free Capacity:2 19 s t o p q r sink terminal 0/3 0/3 0/2 0/3 0/2 0/3 0/4 0/2
  • 20. Example  Path 1, Add Flow:2 20 s t o p q r sink terminal 2/3 0/3 0/2 2/3 2/2 0/3 0/4 0/2
  • 21. Example  Path 2, Free Capacity:1 21 s t o p q r sink terminal 2/3 0/3 0/2 2/3 2/2 0/3 0/4 0/2
  • 22. Example  Path 2, Add Flow:1 22 s t o p q r sink terminal 3/3 0/3 0/2 3/3 2/2 1/3 1/4 0/2
  • 23. Example  Path 3, Free Capacity:0 23 s t o p q r sink terminal 3/3 0/3 0/2 3/3 2/2 1/3 1/4 0/2
  • 24. Example  Path 4, Free Capacity:2 24 s t o p q r sink terminal 3/3 0/3 0/2 3/3 2/2 1/3 1/4 0/2
  • 25. Example  Path 4, Add Flow:2 25 s t o p q r sink terminal 3/3 2/3 0/2 3/3 2/2 3/3 1/4 2/2
  • 26. Example - flow  Flow from sink: 5 = Flow to terminal: 5  Maximal flow = 5 26 s t o p q r sink terminal 3/3 2/3 0/2 3/3 2/2 3/3 1/4 2/2
  • 27. Example - cut  All possible cuts 27 s t o p q r sink terminal 3 3 2 3 2 3 4 2 6 8 7 10 8 5 5
  • 28. Example – minimal cut  Minimal Cut = 5  Two equi-optimal cuts 28 s t o p q r sink terminal 3 3 2 3 2 3 4 2 5 5
  • 29. Complexity  V – number of nodes  E – number of edges  Augmenting paths  𝑂(𝑉 ∙ 𝐸) via bucket data sorting  Kolmogorov  𝑂 𝑉 ∙ 𝐸  Push-relabel  𝑂 𝑉2 𝐸  But parrarelizable 29
  • 30. Graph construction 30 min 𝑓1,𝑓2,…,𝑓𝑛−1,𝑓𝑛 𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 = 𝑖 𝐸𝑖 𝑓𝑖 + 𝑖 𝐸𝑖,𝑗 𝑓𝑖, 𝑓𝑗  Each cut throught the graph must represent energy (some potential solution)  The graph is a sum of elementary graphs for each energy term
  • 31. Graph construction 31 min 𝑓1,𝑓2,…,𝑓𝑛−1,𝑓𝑛 𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 = 𝑖 𝐸𝑖 𝑓𝑖 + 𝑖 𝐸𝑖,𝑗 𝑓𝑖, 𝑓𝑗 𝐸𝑖 1 − 𝐸𝑖 0 𝑓=1s 𝑓=0t 𝐸𝑖 0 − 𝐸𝑖 1 𝑓=1s 𝑓=0t 𝐸𝑖 1 > 𝐸𝑖 0 𝐸𝑖 1 < 𝐸𝑖 0 𝑓𝑖=0 𝑓𝑖=1 𝐸𝑖 𝑓𝑖 2 3 𝑣𝑖 𝑣𝑖
  • 32. Graph construction  x 32 min 𝑓1,𝑓2,…,𝑓𝑛−1,𝑓𝑛 𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 = 𝑖 𝐸𝑖 𝑓𝑖 + 𝑖 𝐸𝑖,𝑗 𝑓𝑖, 𝑓𝑗 𝐸𝑖,𝑗 1,0 − 𝐸𝑖,𝑗 0,0 𝑓=1s 𝑓=0t 𝑣𝑖 𝑣𝑗 𝐸𝑖,𝑗 1,0 − 𝐸𝑖,𝑗 1,1 𝐸𝑖,𝑗 0,1 + 𝐸𝑖,𝑗 1,0 − 𝐸𝑖,𝑗 0,0 -𝐸𝑖,𝑗 1,1 𝐸𝑖,j 𝑓𝑖, 𝑓𝑗 𝑓j=0 𝑓j=1 𝑓𝑖=0 2 3 𝑓𝑖=1 4 5
  • 33. Graph construction 33 𝐸𝑖,j 𝑓𝑖, 𝑓𝑗 𝑓j=0 𝑓j=1 𝑓𝑖=0 𝐸𝑖,j 0,0 𝐸𝑖,j 0,1 𝑓𝑖=1 𝐸𝑖,j 1,0 𝐸𝑖,j 1,1 Assume that 𝐸𝑖,j 0,0 is the biggest 𝐸𝑖,j 0,0 𝐸𝑖,j 0,1 𝐸𝑖,j 1,0 𝐸𝑖,j 1,1 =𝐸𝑖,j 0,0 + 0 𝐸𝑖,j 0,1 -𝐸𝑖,j 0,0 𝐸𝑖,j 1,0 -𝐸𝑖,j 0,0 𝐸𝑖,j 1,1 -𝐸𝑖,j 0,0 =𝐸𝑖,j 0,0 + = 0 0 𝐸𝑖,j 1,0 -𝐸𝑖,j 0,0 𝐸𝑖,j 1,0 -𝐸𝑖,j 0,0 + 0 𝐸𝑖,j 1,1 -𝐸𝑖,j 1,0 0 𝐸𝑖,j 1,1 -𝐸𝑖,j 1,0 + 0 𝐸𝑖,j 0,1 + 𝐸𝑖,j 1,0 − 𝐸𝑖,j 0,0 − 𝐸𝑖,j 1,1 0 0 +
  • 34. Graph construction 34 min 𝑓1,𝑓2,…,𝑓𝑛−1,𝑓𝑛 𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 𝐸 𝑓1, 𝑓2, … , 𝑓𝑛−1, 𝑓𝑛 = 𝑖 𝐸𝑖 𝑓𝑖 + 𝑖 𝐸𝑖,𝑗 𝑓𝑖, 𝑓𝑗 𝑓=1s 𝑓=0t 𝑣1 𝑣 𝑛𝑣 𝑛−1𝑣2 𝑣…
  • 35. Multilabel energy  𝑓𝑖 can be not only binary  Multilabel  The are two graphs constructions commonly used  Ishikawa multilabel graph  Move graph construction 35
  • 36. Ishikawa graph  Roy&Cox 98 and Ishikawa 1998, 2000, 2003 36
  • 38. Ishikawa graph 38  Many nodes required at once  Many edges  Very slow  Restricted only to linear, pairwise terms
  • 39. a-expansion  Solves series of binary problems  𝑓𝑖 can be:  0 – keep the current label  1 – change the label to a 39
  • 40. a-expansion  Start with any* initial solution  For each label a in any (e.g. random) order  Compute optimal a-expansion move (binary problem)  Reject the move if there is no energy decrease  Stop when no expansion move would decrease energy 40
  • 41. a-expansion  Typically two cycles throught all labels are required  *Depends on the initial solution  At given iteration „some” solution is known  In Ishikawa only after solving the whole graph 41
  • 42. Thank you for attention  Questions? 42