SlideShare a Scribd company logo
特徴抽出ー線
Line Detection
発表者:NANDEDKAR PARTH SHIRISH
1
今日の流れーTopics
1.Goal of Line Detection, difference with Edge Detection
2.Successive Approximation Method
3.Hough Transform Method
4.RANSAC(Random Sample Consensus) Method
5.Vanishing Point Detection using Hough Transform
6.Applications-Rectangle Detection
2
1. Goal of Line Detection
In image processing, line detection is an algorithm that takes
a collection of n edge points and finds all the lines on which
these edge points lie.
The most popular line detectors are the Hough
transform and convolution-based techniques.
Convolution-based Line Detection:
Same process as for Edge Detection.
3
1. Difference with Edge Detection
An edge is a transition from one phase/object/thing to
another. On one side you have one color, on the other side you
have another color.
A line is a 1D structure. It has the same phase/object/thing
on either side. On one side you have background, on the other
side you have background also.
→Better techniques can better differentiate between these.
4
2.Successive Approximation Method
5
• Transforming from a curve-contour to a simpler
representation (to Piecewise-linear polyline or B-spline curve)
• Algorithm: Mark the first and last point. Find the farthest inlier
from this line and join First and this point. Now remove the
farthest inlier to this line.
• If contour is a line (with noise) we can simplify it to that line.
3.Hough Transform Basics
6
Consider a line-to-point transform, that transforms
the data from x,y space to m,h space, where each
line is transformed to a point.
Problem: neither m or h are bounded, so that Line k
to x axis ⇒ h not defined Line k to y axis ⇒ m → ∞
3.Polar Hough Transform
7
Now the problem is solved,
as both variables are bounded!
→ Polar Hough Transform:
Where f(x,y) is the image, and (r-xcosθ-ysinθ) represents
any arbitrary line in polar form.
→ Unit Sphere & Cubemap Hough Mappings possible(pg. 253)
3.Polar Hough Transform – Theoretical Example
8Output in the case of perfectly continuous lines.
3.Hough Transform for Line Detection
9
→ Goal: To identify straight lines
• Process: For each pixel at (x,y) the Polar Hough transform
algorithm determines if there is enough evidence of a straight
line at that pixel, using votes from sample points.
→ Strengths:
• Gives equations of lines (but not “end-points” of segments).
• Works well with simple images that contain good straight lines.
(Good for Robot Vision)
• Deal with broken lines very well.
• Reasonably efficient if there are “few” edge points.
3.Polar Hough Transform – Broken Line/Sampling Example
10
3.Polar Hough Transform – Discrete case
11
Same as before, but discrete. Number in Accumulator cell
proportional to number of points on the line.
3.Hough Transform for Line Detection
12
→ Problems:
• Very slow of there are many edge points.
• Hough Space is non-linear, different edge sensitivities in
different directions.
• Poor for short lines.
→ Recent Extensions of Hough Method:
• Circle and Ellipse detection by Double Hough Method.
• Image transform plus Hough for general 2D shape detection.
• Vanishing Points Detection(section 4.3.3, part 5 of presentation)
4.RANSAC(Random Sample Consensus) Method
– (For Feature Detection)
13
• Determines the best transformation that includes the most
number of match features (inliers) from the previous step.
• RANSAC loop for planar pattern detection:
1. Select four feature pairs (at random) in the two angles.
2. Compute homography H (see next slide).
3. Compute inliers where SSD(pi’, Hpi) < a certain value,ε.
4. Keep largest set of inliers.
5. Re-compute least-squares estimate on all of the inliers.
4.RANSAC Method – What are Homographies?
14
• Example of Homography
• Projective–mapping between any two
projection planes with the same center of
projection called Homography
4.RANSAC Method – (For Line Detection)
15
→ Simple example: Let us fit a line
• Use biggest set of inliers
• Do least-square fit => SD is low, Very likely it is a line
4.RANSAC Method – Video: Fitting a Line
16
→ Strengths:
• Robust estimation
• Relatively high accuracy
→ Problems:
• Randomness.
• Number of Iterations
required for p% success
5.Vanishing Points Detection – using Hough Transform
17
→ Goal: To collect lost 3D information from perspective in a 2D
image detecting Vanishing points of Parallel lines.
5.Vanishing Points Detection – using Hough Transform
18
→ Textbook method using Cross Product:
Step 1) Calculate Vanishing Point Hypothesis (weight)
= Cross product of any two line vectors=
 Near-Collinear segments downweighted
Step 2) Populate Hough space(accumulator) with weights
and find peaks for Vanishing point votes from the lines.
Step 3) Calculate Least Squares Estimate for all Vanishing
points with respect to lines that voted for it.
5.Vanishing Points Detection – using Hough Transform
19
where = Green Triangle area
Rule: The lower the sum of all areas subtended to segment
endpoints, the more appropriate the vanishing point.
6.Applications
20
Rectangle Detection:
Step 1) First, detect all vanishing points
Step 2) Detect the Edge points/Lines that are aligned along
vanishing lines.
We then efficiently recover the inter-sections of pairs of lines
corresponding to different vanishing points. (論文[8]の方法)
6.Applications
21
Rectangle Detection:
Using only Hough Detection
is an 8 dimensional vector-
space problem (論文[8])
Major Quadrilaterals in
image can be detected
using only Vanishing Point
and Line Detection(論文[8]).
References
[1] Polar Hough:
https://www.wikiwand.com/en/Hough_transform
[2] Hough Accumulator:
https://chmodux.wordpress.com/2012/04/16/target-
acquisition/
[3] Ransac:
https://www.slideshare.net/allynjoycalcaben/computer-vision-
feature-matching-with-ransac-algorithm
[4] Homographies:
https://docs.opencv.org/master/d9/dab/tutorial_homography.
html
22
References
[5] Ransac animation:
https://kapernikov.com/cable-detection-in-lidar-data/
[6] Miscellaneous:
Computer Vision: Algorithms and Applications by Richard
Szeliski
[7] Vanishing Points Examples:
http://teresabernardart.com/the-rules-of-
perspective/#:~:text=There%20are%20three%20basic%20types
,illusion%20of%20depth%20and%20space.
[8] Rectangle Detection Algorithm:
https://www.researchgate.net/publication/228697341_Perspec
tive_rectangle_detection 23

More Related Content

What's hot

Computer Vision - RANSAC
Computer Vision - RANSACComputer Vision - RANSAC
Computer Vision - RANSAC
Wael Badawy
 
Chapter 6 color image processing
Chapter 6 color image processingChapter 6 color image processing
Chapter 6 color image processing
asodariyabhavesh
 
Edge Detection using Hough Transform
Edge Detection using Hough TransformEdge Detection using Hough Transform
Edge Detection using Hough Transform
Mrunal Selokar
 
Image processing second unit Notes
Image processing second unit NotesImage processing second unit Notes
Image processing second unit Notes
AAKANKSHA JAIN
 
Edge detection
Edge detectionEdge detection
Edge detection
Ishraq Al Fataftah
 
Color fundamentals and color models - Digital Image Processing
Color fundamentals and color models - Digital Image ProcessingColor fundamentals and color models - Digital Image Processing
Color fundamentals and color models - Digital Image Processing
Amna
 
Image Processing: Spatial filters
Image Processing: Spatial filtersImage Processing: Spatial filters
Image Processing: Spatial filters
A B Shinde
 
Canny Edge Detection
Canny Edge DetectionCanny Edge Detection
Canny Edge Detection
SN Chakraborty
 
Edge Detection and Segmentation
Edge Detection and SegmentationEdge Detection and Segmentation
Edge Detection and Segmentation
A B Shinde
 
5. gray level transformation
5. gray level transformation5. gray level transformation
5. gray level transformation
MdFazleRabbi18
 
Color Image Processing: Basics
Color Image Processing: BasicsColor Image Processing: Basics
Color Image Processing: Basics
A B Shinde
 
Fundamental steps in image processing
Fundamental steps in image processingFundamental steps in image processing
Fundamental steps in image processing
PremaPRC211300301103
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extraction
skylian
 
Chain code in dip
Chain code in dipChain code in dip
Chain code in dip
Rishav Bhurtel
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
Gayan Sampath
 
Edge linking in image processing
Edge linking in image processingEdge linking in image processing
Edge linking in image processing
VARUN KUMAR
 
Image segmentation
Image segmentation Image segmentation
Feature detection and matching
Feature detection and matchingFeature detection and matching
Feature detection and matching
Kuppusamy P
 
SIFT
SIFTSIFT
Fundamentals and image compression models
Fundamentals and image compression modelsFundamentals and image compression models
Fundamentals and image compression models
lavanya marichamy
 

What's hot (20)

Computer Vision - RANSAC
Computer Vision - RANSACComputer Vision - RANSAC
Computer Vision - RANSAC
 
Chapter 6 color image processing
Chapter 6 color image processingChapter 6 color image processing
Chapter 6 color image processing
 
Edge Detection using Hough Transform
Edge Detection using Hough TransformEdge Detection using Hough Transform
Edge Detection using Hough Transform
 
Image processing second unit Notes
Image processing second unit NotesImage processing second unit Notes
Image processing second unit Notes
 
Edge detection
Edge detectionEdge detection
Edge detection
 
Color fundamentals and color models - Digital Image Processing
Color fundamentals and color models - Digital Image ProcessingColor fundamentals and color models - Digital Image Processing
Color fundamentals and color models - Digital Image Processing
 
Image Processing: Spatial filters
Image Processing: Spatial filtersImage Processing: Spatial filters
Image Processing: Spatial filters
 
Canny Edge Detection
Canny Edge DetectionCanny Edge Detection
Canny Edge Detection
 
Edge Detection and Segmentation
Edge Detection and SegmentationEdge Detection and Segmentation
Edge Detection and Segmentation
 
5. gray level transformation
5. gray level transformation5. gray level transformation
5. gray level transformation
 
Color Image Processing: Basics
Color Image Processing: BasicsColor Image Processing: Basics
Color Image Processing: Basics
 
Fundamental steps in image processing
Fundamental steps in image processingFundamental steps in image processing
Fundamental steps in image processing
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extraction
 
Chain code in dip
Chain code in dipChain code in dip
Chain code in dip
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
Edge linking in image processing
Edge linking in image processingEdge linking in image processing
Edge linking in image processing
 
Image segmentation
Image segmentation Image segmentation
Image segmentation
 
Feature detection and matching
Feature detection and matchingFeature detection and matching
Feature detection and matching
 
SIFT
SIFTSIFT
SIFT
 
Fundamentals and image compression models
Fundamentals and image compression modelsFundamentals and image compression models
Fundamentals and image compression models
 

Similar to Line Detection in Computer Vision

Line Detection in Computer Vision - Recent Developments and Applications
Line Detection in Computer Vision - Recent Developments and ApplicationsLine Detection in Computer Vision - Recent Developments and Applications
Line Detection in Computer Vision - Recent Developments and Applications
Parth Nandedkar
 
Practical Digital Image Processing 3
 Practical Digital Image Processing 3 Practical Digital Image Processing 3
Practical Digital Image Processing 3
Aly Abdelkareem
 
Lane detection by use of canny edge
Lane detection by use of canny edgeLane detection by use of canny edge
Lane detection by use of canny edge
banz23
 
color doppler
color dopplercolor doppler
color doppler
MsccMohamed
 
Ray Tracing
Ray TracingRay Tracing
Ray Tracing
Syed Zaid Irshad
 
Internet hyperbolic mapping paper by Krioukov
Internet hyperbolic mapping paper by KrioukovInternet hyperbolic mapping paper by Krioukov
Internet hyperbolic mapping paper by Krioukov
Meenakshi Tripathi
 
Rapidly-Exploring Random Tree
Rapidly-Exploring Random TreeRapidly-Exploring Random Tree
Rapidly-Exploring Random Tree
Abhishek Bhandwaldar
 
1516 contouring
1516 contouring1516 contouring
1516 contouring
Dr Fereidoun Dejahang
 
Machine learning for high-speed corner detection
Machine learning for high-speed corner detectionMachine learning for high-speed corner detection
Machine learning for high-speed corner detection
butest
 
CS401_M2_L6_Solid Area Scan Conversion.pptx
CS401_M2_L6_Solid Area Scan Conversion.pptxCS401_M2_L6_Solid Area Scan Conversion.pptx
CS401_M2_L6_Solid Area Scan Conversion.pptx
lara333479
 
Chapter10 image segmentation
Chapter10 image segmentationChapter10 image segmentation
Chapter10 image segmentation
asodariyabhavesh
 
A Method to Determine End-Points ofStraight Lines Detected Using the Hough Tr...
A Method to Determine End-Points ofStraight Lines Detected Using the Hough Tr...A Method to Determine End-Points ofStraight Lines Detected Using the Hough Tr...
A Method to Determine End-Points ofStraight Lines Detected Using the Hough Tr...
IJERA Editor
 
Path Finding Solutions For Grid Based Graph
Path Finding Solutions For Grid Based GraphPath Finding Solutions For Grid Based Graph
Path Finding Solutions For Grid Based Graph
acijjournal
 
cv1.ppt
cv1.pptcv1.ppt
cv1.ppt
sachin397946
 
06 image features
06 image features06 image features
06 image features
ankit_ppt
 
lec09_ransac.pptx
lec09_ransac.pptxlec09_ransac.pptx
lec09_ransac.pptx
AneesAbbasi14
 
Robot Motion Planning Introduction to Mobile Robotics.pdf
Robot Motion Planning Introduction to Mobile Robotics.pdfRobot Motion Planning Introduction to Mobile Robotics.pdf
Robot Motion Planning Introduction to Mobile Robotics.pdf
Vien43
 
Modèle de coordination du groupe de robots mobiles
Modèle de coordination du groupe de robots mobilesModèle de coordination du groupe de robots mobiles
Modèle de coordination du groupe de robots mobiles
Akrem Hadji
 
Computer Vision: Feature matching with RANSAC Algorithm
Computer Vision: Feature matching with RANSAC AlgorithmComputer Vision: Feature matching with RANSAC Algorithm
Computer Vision: Feature matching with RANSAC Algorithm
allyn joy calcaben
 
Slide share version historical background of diffractometer
Slide share version historical background of diffractometerSlide share version historical background of diffractometer
Slide share version historical background of diffractometer
University of Karachi
 

Similar to Line Detection in Computer Vision (20)

Line Detection in Computer Vision - Recent Developments and Applications
Line Detection in Computer Vision - Recent Developments and ApplicationsLine Detection in Computer Vision - Recent Developments and Applications
Line Detection in Computer Vision - Recent Developments and Applications
 
Practical Digital Image Processing 3
 Practical Digital Image Processing 3 Practical Digital Image Processing 3
Practical Digital Image Processing 3
 
Lane detection by use of canny edge
Lane detection by use of canny edgeLane detection by use of canny edge
Lane detection by use of canny edge
 
color doppler
color dopplercolor doppler
color doppler
 
Ray Tracing
Ray TracingRay Tracing
Ray Tracing
 
Internet hyperbolic mapping paper by Krioukov
Internet hyperbolic mapping paper by KrioukovInternet hyperbolic mapping paper by Krioukov
Internet hyperbolic mapping paper by Krioukov
 
Rapidly-Exploring Random Tree
Rapidly-Exploring Random TreeRapidly-Exploring Random Tree
Rapidly-Exploring Random Tree
 
1516 contouring
1516 contouring1516 contouring
1516 contouring
 
Machine learning for high-speed corner detection
Machine learning for high-speed corner detectionMachine learning for high-speed corner detection
Machine learning for high-speed corner detection
 
CS401_M2_L6_Solid Area Scan Conversion.pptx
CS401_M2_L6_Solid Area Scan Conversion.pptxCS401_M2_L6_Solid Area Scan Conversion.pptx
CS401_M2_L6_Solid Area Scan Conversion.pptx
 
Chapter10 image segmentation
Chapter10 image segmentationChapter10 image segmentation
Chapter10 image segmentation
 
A Method to Determine End-Points ofStraight Lines Detected Using the Hough Tr...
A Method to Determine End-Points ofStraight Lines Detected Using the Hough Tr...A Method to Determine End-Points ofStraight Lines Detected Using the Hough Tr...
A Method to Determine End-Points ofStraight Lines Detected Using the Hough Tr...
 
Path Finding Solutions For Grid Based Graph
Path Finding Solutions For Grid Based GraphPath Finding Solutions For Grid Based Graph
Path Finding Solutions For Grid Based Graph
 
cv1.ppt
cv1.pptcv1.ppt
cv1.ppt
 
06 image features
06 image features06 image features
06 image features
 
lec09_ransac.pptx
lec09_ransac.pptxlec09_ransac.pptx
lec09_ransac.pptx
 
Robot Motion Planning Introduction to Mobile Robotics.pdf
Robot Motion Planning Introduction to Mobile Robotics.pdfRobot Motion Planning Introduction to Mobile Robotics.pdf
Robot Motion Planning Introduction to Mobile Robotics.pdf
 
Modèle de coordination du groupe de robots mobiles
Modèle de coordination du groupe de robots mobilesModèle de coordination du groupe de robots mobiles
Modèle de coordination du groupe de robots mobiles
 
Computer Vision: Feature matching with RANSAC Algorithm
Computer Vision: Feature matching with RANSAC AlgorithmComputer Vision: Feature matching with RANSAC Algorithm
Computer Vision: Feature matching with RANSAC Algorithm
 
Slide share version historical background of diffractometer
Slide share version historical background of diffractometerSlide share version historical background of diffractometer
Slide share version historical background of diffractometer
 

More from Parth Nandedkar

Large scale cell tracking using an approximated Sinkhorn algorithm
Large scale cell tracking using an approximated Sinkhorn algorithmLarge scale cell tracking using an approximated Sinkhorn algorithm
Large scale cell tracking using an approximated Sinkhorn algorithm
Parth Nandedkar
 
Large scale cell tracking using an approximated Sinkhorn algorithm
Large scale cell tracking using an approximated Sinkhorn algorithmLarge scale cell tracking using an approximated Sinkhorn algorithm
Large scale cell tracking using an approximated Sinkhorn algorithm
Parth Nandedkar
 
Discount tracker - Fujitsu Hackathon
Discount tracker - Fujitsu HackathonDiscount tracker - Fujitsu Hackathon
Discount tracker - Fujitsu Hackathon
Parth Nandedkar
 
Motion and Position Map in Cell Tracking for Bioimaging
Motion and Position Map in Cell Tracking for BioimagingMotion and Position Map in Cell Tracking for Bioimaging
Motion and Position Map in Cell Tracking for Bioimaging
Parth Nandedkar
 
Speech at english_seminar
Speech at english_seminarSpeech at english_seminar
Speech at english_seminar
Parth Nandedkar
 
Permutations and Combinations IIT JEE+Olympiad Lecture 1
Permutations and Combinations IIT JEE+Olympiad Lecture 1 Permutations and Combinations IIT JEE+Olympiad Lecture 1
Permutations and Combinations IIT JEE+Olympiad Lecture 1
Parth Nandedkar
 
Permutations and Combinations IIT JEE+Olympiad Lecture 4
Permutations and Combinations IIT JEE+Olympiad Lecture 4Permutations and Combinations IIT JEE+Olympiad Lecture 4
Permutations and Combinations IIT JEE+Olympiad Lecture 4
Parth Nandedkar
 
Permutations and Combinations IIT JEE+Olympiad Lecture 3
Permutations and Combinations IIT JEE+Olympiad Lecture 3 Permutations and Combinations IIT JEE+Olympiad Lecture 3
Permutations and Combinations IIT JEE+Olympiad Lecture 3
Parth Nandedkar
 
LSTM and GRU RNNs in Sentiment Analysis (Japanese)
LSTM and GRU RNNs in Sentiment Analysis (Japanese)LSTM and GRU RNNs in Sentiment Analysis (Japanese)
LSTM and GRU RNNs in Sentiment Analysis (Japanese)
Parth Nandedkar
 
Deep Learning Demonstration using Tensorflow (7th lecture)
Deep Learning Demonstration using Tensorflow (7th lecture)Deep Learning Demonstration using Tensorflow (7th lecture)
Deep Learning Demonstration using Tensorflow (7th lecture)
Parth Nandedkar
 
Basics of Deep Learning (2nd lecture)
Basics of Deep Learning (2nd lecture)Basics of Deep Learning (2nd lecture)
Basics of Deep Learning (2nd lecture)
Parth Nandedkar
 

More from Parth Nandedkar (11)

Large scale cell tracking using an approximated Sinkhorn algorithm
Large scale cell tracking using an approximated Sinkhorn algorithmLarge scale cell tracking using an approximated Sinkhorn algorithm
Large scale cell tracking using an approximated Sinkhorn algorithm
 
Large scale cell tracking using an approximated Sinkhorn algorithm
Large scale cell tracking using an approximated Sinkhorn algorithmLarge scale cell tracking using an approximated Sinkhorn algorithm
Large scale cell tracking using an approximated Sinkhorn algorithm
 
Discount tracker - Fujitsu Hackathon
Discount tracker - Fujitsu HackathonDiscount tracker - Fujitsu Hackathon
Discount tracker - Fujitsu Hackathon
 
Motion and Position Map in Cell Tracking for Bioimaging
Motion and Position Map in Cell Tracking for BioimagingMotion and Position Map in Cell Tracking for Bioimaging
Motion and Position Map in Cell Tracking for Bioimaging
 
Speech at english_seminar
Speech at english_seminarSpeech at english_seminar
Speech at english_seminar
 
Permutations and Combinations IIT JEE+Olympiad Lecture 1
Permutations and Combinations IIT JEE+Olympiad Lecture 1 Permutations and Combinations IIT JEE+Olympiad Lecture 1
Permutations and Combinations IIT JEE+Olympiad Lecture 1
 
Permutations and Combinations IIT JEE+Olympiad Lecture 4
Permutations and Combinations IIT JEE+Olympiad Lecture 4Permutations and Combinations IIT JEE+Olympiad Lecture 4
Permutations and Combinations IIT JEE+Olympiad Lecture 4
 
Permutations and Combinations IIT JEE+Olympiad Lecture 3
Permutations and Combinations IIT JEE+Olympiad Lecture 3 Permutations and Combinations IIT JEE+Olympiad Lecture 3
Permutations and Combinations IIT JEE+Olympiad Lecture 3
 
LSTM and GRU RNNs in Sentiment Analysis (Japanese)
LSTM and GRU RNNs in Sentiment Analysis (Japanese)LSTM and GRU RNNs in Sentiment Analysis (Japanese)
LSTM and GRU RNNs in Sentiment Analysis (Japanese)
 
Deep Learning Demonstration using Tensorflow (7th lecture)
Deep Learning Demonstration using Tensorflow (7th lecture)Deep Learning Demonstration using Tensorflow (7th lecture)
Deep Learning Demonstration using Tensorflow (7th lecture)
 
Basics of Deep Learning (2nd lecture)
Basics of Deep Learning (2nd lecture)Basics of Deep Learning (2nd lecture)
Basics of Deep Learning (2nd lecture)
 

Recently uploaded

一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
74nqk8xf
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Kiwi Creative
 
The Ipsos - AI - Monitor 2024 Report.pdf
The  Ipsos - AI - Monitor 2024 Report.pdfThe  Ipsos - AI - Monitor 2024 Report.pdf
The Ipsos - AI - Monitor 2024 Report.pdf
Social Samosa
 
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
v3tuleee
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
Sm321
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
Timothy Spann
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
Social Samosa
 
State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023
kuntobimo2016
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
Bill641377
 
Natural Language Processing (NLP), RAG and its applications .pptx
Natural Language Processing (NLP), RAG and its applications .pptxNatural Language Processing (NLP), RAG and its applications .pptx
Natural Language Processing (NLP), RAG and its applications .pptx
fkyes25
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
nuttdpt
 
University of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma TranscriptUniversity of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma Transcript
soxrziqu
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
bopyb
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
rwarrenll
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
nuttdpt
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
AndrzejJarynowski
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
g4dpvqap0
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
sameer shah
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
Timothy Spann
 
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
ahzuo
 

Recently uploaded (20)

一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
 
The Ipsos - AI - Monitor 2024 Report.pdf
The  Ipsos - AI - Monitor 2024 Report.pdfThe  Ipsos - AI - Monitor 2024 Report.pdf
The Ipsos - AI - Monitor 2024 Report.pdf
 
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
 
State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
 
Natural Language Processing (NLP), RAG and its applications .pptx
Natural Language Processing (NLP), RAG and its applications .pptxNatural Language Processing (NLP), RAG and its applications .pptx
Natural Language Processing (NLP), RAG and its applications .pptx
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
 
University of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma TranscriptUniversity of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma Transcript
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
 
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
 

Line Detection in Computer Vision

  • 2. 今日の流れーTopics 1.Goal of Line Detection, difference with Edge Detection 2.Successive Approximation Method 3.Hough Transform Method 4.RANSAC(Random Sample Consensus) Method 5.Vanishing Point Detection using Hough Transform 6.Applications-Rectangle Detection 2
  • 3. 1. Goal of Line Detection In image processing, line detection is an algorithm that takes a collection of n edge points and finds all the lines on which these edge points lie. The most popular line detectors are the Hough transform and convolution-based techniques. Convolution-based Line Detection: Same process as for Edge Detection. 3
  • 4. 1. Difference with Edge Detection An edge is a transition from one phase/object/thing to another. On one side you have one color, on the other side you have another color. A line is a 1D structure. It has the same phase/object/thing on either side. On one side you have background, on the other side you have background also. →Better techniques can better differentiate between these. 4
  • 5. 2.Successive Approximation Method 5 • Transforming from a curve-contour to a simpler representation (to Piecewise-linear polyline or B-spline curve) • Algorithm: Mark the first and last point. Find the farthest inlier from this line and join First and this point. Now remove the farthest inlier to this line. • If contour is a line (with noise) we can simplify it to that line.
  • 6. 3.Hough Transform Basics 6 Consider a line-to-point transform, that transforms the data from x,y space to m,h space, where each line is transformed to a point. Problem: neither m or h are bounded, so that Line k to x axis ⇒ h not defined Line k to y axis ⇒ m → ∞
  • 7. 3.Polar Hough Transform 7 Now the problem is solved, as both variables are bounded! → Polar Hough Transform: Where f(x,y) is the image, and (r-xcosθ-ysinθ) represents any arbitrary line in polar form. → Unit Sphere & Cubemap Hough Mappings possible(pg. 253)
  • 8. 3.Polar Hough Transform – Theoretical Example 8Output in the case of perfectly continuous lines.
  • 9. 3.Hough Transform for Line Detection 9 → Goal: To identify straight lines • Process: For each pixel at (x,y) the Polar Hough transform algorithm determines if there is enough evidence of a straight line at that pixel, using votes from sample points. → Strengths: • Gives equations of lines (but not “end-points” of segments). • Works well with simple images that contain good straight lines. (Good for Robot Vision) • Deal with broken lines very well. • Reasonably efficient if there are “few” edge points.
  • 10. 3.Polar Hough Transform – Broken Line/Sampling Example 10
  • 11. 3.Polar Hough Transform – Discrete case 11 Same as before, but discrete. Number in Accumulator cell proportional to number of points on the line.
  • 12. 3.Hough Transform for Line Detection 12 → Problems: • Very slow of there are many edge points. • Hough Space is non-linear, different edge sensitivities in different directions. • Poor for short lines. → Recent Extensions of Hough Method: • Circle and Ellipse detection by Double Hough Method. • Image transform plus Hough for general 2D shape detection. • Vanishing Points Detection(section 4.3.3, part 5 of presentation)
  • 13. 4.RANSAC(Random Sample Consensus) Method – (For Feature Detection) 13 • Determines the best transformation that includes the most number of match features (inliers) from the previous step. • RANSAC loop for planar pattern detection: 1. Select four feature pairs (at random) in the two angles. 2. Compute homography H (see next slide). 3. Compute inliers where SSD(pi’, Hpi) < a certain value,ε. 4. Keep largest set of inliers. 5. Re-compute least-squares estimate on all of the inliers.
  • 14. 4.RANSAC Method – What are Homographies? 14 • Example of Homography • Projective–mapping between any two projection planes with the same center of projection called Homography
  • 15. 4.RANSAC Method – (For Line Detection) 15 → Simple example: Let us fit a line • Use biggest set of inliers • Do least-square fit => SD is low, Very likely it is a line
  • 16. 4.RANSAC Method – Video: Fitting a Line 16 → Strengths: • Robust estimation • Relatively high accuracy → Problems: • Randomness. • Number of Iterations required for p% success
  • 17. 5.Vanishing Points Detection – using Hough Transform 17 → Goal: To collect lost 3D information from perspective in a 2D image detecting Vanishing points of Parallel lines.
  • 18. 5.Vanishing Points Detection – using Hough Transform 18 → Textbook method using Cross Product: Step 1) Calculate Vanishing Point Hypothesis (weight) = Cross product of any two line vectors=  Near-Collinear segments downweighted Step 2) Populate Hough space(accumulator) with weights and find peaks for Vanishing point votes from the lines. Step 3) Calculate Least Squares Estimate for all Vanishing points with respect to lines that voted for it.
  • 19. 5.Vanishing Points Detection – using Hough Transform 19 where = Green Triangle area Rule: The lower the sum of all areas subtended to segment endpoints, the more appropriate the vanishing point.
  • 20. 6.Applications 20 Rectangle Detection: Step 1) First, detect all vanishing points Step 2) Detect the Edge points/Lines that are aligned along vanishing lines. We then efficiently recover the inter-sections of pairs of lines corresponding to different vanishing points. (論文[8]の方法)
  • 21. 6.Applications 21 Rectangle Detection: Using only Hough Detection is an 8 dimensional vector- space problem (論文[8]) Major Quadrilaterals in image can be detected using only Vanishing Point and Line Detection(論文[8]).
  • 22. References [1] Polar Hough: https://www.wikiwand.com/en/Hough_transform [2] Hough Accumulator: https://chmodux.wordpress.com/2012/04/16/target- acquisition/ [3] Ransac: https://www.slideshare.net/allynjoycalcaben/computer-vision- feature-matching-with-ransac-algorithm [4] Homographies: https://docs.opencv.org/master/d9/dab/tutorial_homography. html 22
  • 23. References [5] Ransac animation: https://kapernikov.com/cable-detection-in-lidar-data/ [6] Miscellaneous: Computer Vision: Algorithms and Applications by Richard Szeliski [7] Vanishing Points Examples: http://teresabernardart.com/the-rules-of- perspective/#:~:text=There%20are%20three%20basic%20types ,illusion%20of%20depth%20and%20space. [8] Rectangle Detection Algorithm: https://www.researchgate.net/publication/228697341_Perspec tive_rectangle_detection 23