SlideShare a Scribd company logo
Methodology and theory behind
Distance Measuring
Algorithm
Using One camera
In this document only theory and mathematics behind algorithm is described, details related
programming is not discussed.
Our Distance Measuring Algorithm (DMA) has three parts
 Track object
 Feed set points
 Measure distance
Track object
A picture is better than thousand words so first see these pictures.
From above images we notice that aspect ratio (width/height) is more or less 1.3 so for tracking
particular object (sign board in our case) we find all objects in image and check aspect ratio of all objects
found in image and discard all object whose aspect ratio is not equal to 1.3 so doing this we can easily
track particular object.
Feeding set points
This method is not plug and play we have to feed some set points let us organize data obtained from
above images in table.
No Aspect ratio
(width/height) no unit
Distance (feet) Area (width x height) in pixels
1 1.37 0.5 280071
2 1.35 2 91520
3 1.313 3 46436
4 1.33 4 26980
5 1.355 5 14664
Measuring Distance
For measuring distance we are using Lagrange’s interpolation formula
Formula for five point’s data
(x- x1) (x- x2)(x- x3)(x- x4) (x- x0)(x- x1) (x- x2)(x- x3)
f(x) = f0+ . . . + f4
(x0 - x1) (x0 - x2)(x0 - x3)(x0 - x4) (x4 - x0)(x4 - x1)(x4 - x2)(x4 - x3)
Follow this link to understand Lagrange’s interpolation
http://mat.iitm.ac.in/home/sryedida/public_html/caimna/interpolation/lagrange.html
Applying langrage’s interpolation to above data to find distance at any point
Distance (D) 0.5 2 3 4 5
Area (A) 280071 91520 46436 26980 14664
Our unknown quantity is distance we know area so we can easily find distance at any value of area.
Limitations
If camera move to close to object then this method does not works

More Related Content

What's hot

Visual Search
Visual SearchVisual Search
Visual Search
Lov Loothra
 
Task 2 animation
Task 2 animationTask 2 animation
Task 2 animation
acffc17
 
Vector and coordinate in games
Vector and coordinate in gamesVector and coordinate in games
Vector and coordinate in games
AshikMdMoinulHossain
 
Machine Learning by Analogy
Machine Learning by AnalogyMachine Learning by Analogy
Machine Learning by Analogy
Colleen Farrelly
 
Chapter 9 Review Lessons 6 10
Chapter 9 Review Lessons 6 10Chapter 9 Review Lessons 6 10
Chapter 9 Review Lessons 6 10
Jessca Lundin
 
Topology for data science
Topology for data scienceTopology for data science
Topology for data science
Colleen Farrelly
 
6 Concor
6 Concor6 Concor
6 Hiclus
6 Hiclus6 Hiclus
IMAGE ENHANCEMENT /ENHANCHING the feature of an image/ Image editor
IMAGE ENHANCEMENT /ENHANCHING the feature of an image/ Image editorIMAGE ENHANCEMENT /ENHANCHING the feature of an image/ Image editor
IMAGE ENHANCEMENT /ENHANCHING the feature of an image/ Image editor
RAHUL DANGWAL
 
Steiner Tree: approach applying for shortest path in selected network
Steiner Tree: approach applying for shortest path in selected networkSteiner Tree: approach applying for shortest path in selected network
Steiner Tree: approach applying for shortest path in selected network
IOSR Journals
 
Multiscale Mapper Networks
Multiscale Mapper NetworksMultiscale Mapper Networks
Multiscale Mapper Networks
Colleen Farrelly
 
Malimu variance and standard deviation
Malimu variance and standard deviationMalimu variance and standard deviation
Malimu variance and standard deviation
Miharbi Ignasm
 
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image DescriptorsPCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
wolf
 
Adding subtractingdecimals
Adding subtractingdecimalsAdding subtractingdecimals
Adding subtractingdecimals
gheovani
 
Numerical Method Analysis: Algebraic and Transcendental Equations (Linear)
Numerical Method Analysis: Algebraic and Transcendental Equations (Linear)Numerical Method Analysis: Algebraic and Transcendental Equations (Linear)
Numerical Method Analysis: Algebraic and Transcendental Equations (Linear)
Minhas Kamal
 
Michal Erel's SIFT presentation
Michal Erel's SIFT presentationMichal Erel's SIFT presentation
Michal Erel's SIFT presentation
wolf
 
IMPROVING THE RELIABILITY OF DETECTION OF LSB REPLACEMENT STEGANOGRAPHY
IMPROVING THE RELIABILITY OF DETECTION OF LSB REPLACEMENT STEGANOGRAPHYIMPROVING THE RELIABILITY OF DETECTION OF LSB REPLACEMENT STEGANOGRAPHY
IMPROVING THE RELIABILITY OF DETECTION OF LSB REPLACEMENT STEGANOGRAPHY
IJNSA Journal
 
A Fast Content-Based Image Retrieval Method Using Deep Visual Features
A Fast Content-Based Image Retrieval Method Using Deep Visual FeaturesA Fast Content-Based Image Retrieval Method Using Deep Visual Features
A Fast Content-Based Image Retrieval Method Using Deep Visual Features
Hiroki Tanioka
 
★Mean shift a_robust_approach_to_feature_space_analysis
★Mean shift a_robust_approach_to_feature_space_analysis★Mean shift a_robust_approach_to_feature_space_analysis
★Mean shift a_robust_approach_to_feature_space_analysis
irisshicat
 
Hsieh etal spl
Hsieh etal splHsieh etal spl
Hsieh etal spl
Tomasz Waszczyk
 

What's hot (20)

Visual Search
Visual SearchVisual Search
Visual Search
 
Task 2 animation
Task 2 animationTask 2 animation
Task 2 animation
 
Vector and coordinate in games
Vector and coordinate in gamesVector and coordinate in games
Vector and coordinate in games
 
Machine Learning by Analogy
Machine Learning by AnalogyMachine Learning by Analogy
Machine Learning by Analogy
 
Chapter 9 Review Lessons 6 10
Chapter 9 Review Lessons 6 10Chapter 9 Review Lessons 6 10
Chapter 9 Review Lessons 6 10
 
Topology for data science
Topology for data scienceTopology for data science
Topology for data science
 
6 Concor
6 Concor6 Concor
6 Concor
 
6 Hiclus
6 Hiclus6 Hiclus
6 Hiclus
 
IMAGE ENHANCEMENT /ENHANCHING the feature of an image/ Image editor
IMAGE ENHANCEMENT /ENHANCHING the feature of an image/ Image editorIMAGE ENHANCEMENT /ENHANCHING the feature of an image/ Image editor
IMAGE ENHANCEMENT /ENHANCHING the feature of an image/ Image editor
 
Steiner Tree: approach applying for shortest path in selected network
Steiner Tree: approach applying for shortest path in selected networkSteiner Tree: approach applying for shortest path in selected network
Steiner Tree: approach applying for shortest path in selected network
 
Multiscale Mapper Networks
Multiscale Mapper NetworksMultiscale Mapper Networks
Multiscale Mapper Networks
 
Malimu variance and standard deviation
Malimu variance and standard deviationMalimu variance and standard deviation
Malimu variance and standard deviation
 
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image DescriptorsPCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
 
Adding subtractingdecimals
Adding subtractingdecimalsAdding subtractingdecimals
Adding subtractingdecimals
 
Numerical Method Analysis: Algebraic and Transcendental Equations (Linear)
Numerical Method Analysis: Algebraic and Transcendental Equations (Linear)Numerical Method Analysis: Algebraic and Transcendental Equations (Linear)
Numerical Method Analysis: Algebraic and Transcendental Equations (Linear)
 
Michal Erel's SIFT presentation
Michal Erel's SIFT presentationMichal Erel's SIFT presentation
Michal Erel's SIFT presentation
 
IMPROVING THE RELIABILITY OF DETECTION OF LSB REPLACEMENT STEGANOGRAPHY
IMPROVING THE RELIABILITY OF DETECTION OF LSB REPLACEMENT STEGANOGRAPHYIMPROVING THE RELIABILITY OF DETECTION OF LSB REPLACEMENT STEGANOGRAPHY
IMPROVING THE RELIABILITY OF DETECTION OF LSB REPLACEMENT STEGANOGRAPHY
 
A Fast Content-Based Image Retrieval Method Using Deep Visual Features
A Fast Content-Based Image Retrieval Method Using Deep Visual FeaturesA Fast Content-Based Image Retrieval Method Using Deep Visual Features
A Fast Content-Based Image Retrieval Method Using Deep Visual Features
 
★Mean shift a_robust_approach_to_feature_space_analysis
★Mean shift a_robust_approach_to_feature_space_analysis★Mean shift a_robust_approach_to_feature_space_analysis
★Mean shift a_robust_approach_to_feature_space_analysis
 
Hsieh etal spl
Hsieh etal splHsieh etal spl
Hsieh etal spl
 

Viewers also liked

A234 a234m − 14
A234 a234m − 14A234 a234m − 14
A234 a234m − 14
Sameer Ahmed
 
MCRP - copie
MCRP - copieMCRP - copie
MCRP - copie
Sarah de Castro
 
John Blatt_ Resume 070615
John Blatt_ Resume 070615John Blatt_ Resume 070615
John Blatt_ Resume 070615
John Blatt
 
Khaled%20C.V[2[1]
Khaled%20C.V[2[1]Khaled%20C.V[2[1]
Khaled%20C.V[2[1]
khaled hamarsheh
 
LIVER, GALL BLADER, KIDNEY, UROLOGY INSTRUMENTS [SURGICOSE]
LIVER, GALL BLADER, KIDNEY, UROLOGY INSTRUMENTS [SURGICOSE]LIVER, GALL BLADER, KIDNEY, UROLOGY INSTRUMENTS [SURGICOSE]
LIVER, GALL BLADER, KIDNEY, UROLOGY INSTRUMENTS [SURGICOSE]
SURGICOSE
 
ΔΕΦΚΦ/Α/1025336/ΕΞ2017
ΔΕΦΚΦ/Α/1025336/ΕΞ2017ΔΕΦΚΦ/Α/1025336/ΕΞ2017
ΔΕΦΚΦ/Α/1025336/ΕΞ2017
Panayotis Sofianopoulos
 
New cv 2016
New cv 2016New cv 2016
New cv 2016
AJIT RAWAT
 
Final presentation nmdl
Final presentation nmdlFinal presentation nmdl
Final presentation nmdl
bngldstn
 
Your Guide to 'The Cloud'
Your Guide to 'The Cloud'Your Guide to 'The Cloud'
Your Guide to 'The Cloud'
Sam Parker
 
BONE RONGEURS [SURGICOSE PAKISTAN]
BONE RONGEURS [SURGICOSE PAKISTAN]BONE RONGEURS [SURGICOSE PAKISTAN]
BONE RONGEURS [SURGICOSE PAKISTAN]
SURGICOSE
 
Tugas 2
Tugas 2Tugas 2
Tugas 2
cinjy
 
How to increase website conversions by applying the laws of great product design
How to increase website conversions by applying the laws of great product designHow to increase website conversions by applying the laws of great product design
How to increase website conversions by applying the laws of great product design
Lindsay Bayuk
 
appletreeposter2006
appletreeposter2006appletreeposter2006
appletreeposter2006
Mary Beth Levin
 
Debbie Bieller's Resume 5.1.14
Debbie Bieller's Resume 5.1.14Debbie Bieller's Resume 5.1.14
Debbie Bieller's Resume 5.1.14
Debbie Hopkins
 
ZigBee Smart LED light
ZigBee Smart LED lightZigBee Smart LED light
ZigBee Smart LED light
Nancy Xu
 
Boost conversions by localizing your marketing
Boost conversions by localizing your marketingBoost conversions by localizing your marketing
Boost conversions by localizing your marketing
MatchCraft
 
Lucy
LucyLucy
CV of Jianyu Hu (contact info not included)
CV of Jianyu Hu (contact info not included)CV of Jianyu Hu (contact info not included)
CV of Jianyu Hu (contact info not included)
Jianyu (Ken) Hu
 
ΣΕΒ για την Ελληνική Οικονομία - 061016
ΣΕΒ για την Ελληνική Οικονομία - 061016ΣΕΒ για την Ελληνική Οικονομία - 061016
ΣΕΒ για την Ελληνική Οικονομία - 061016
Panayotis Sofianopoulos
 

Viewers also liked (20)

A234 a234m − 14
A234 a234m − 14A234 a234m − 14
A234 a234m − 14
 
MCRP - copie
MCRP - copieMCRP - copie
MCRP - copie
 
John Blatt_ Resume 070615
John Blatt_ Resume 070615John Blatt_ Resume 070615
John Blatt_ Resume 070615
 
Khaled%20C.V[2[1]
Khaled%20C.V[2[1]Khaled%20C.V[2[1]
Khaled%20C.V[2[1]
 
LIVER, GALL BLADER, KIDNEY, UROLOGY INSTRUMENTS [SURGICOSE]
LIVER, GALL BLADER, KIDNEY, UROLOGY INSTRUMENTS [SURGICOSE]LIVER, GALL BLADER, KIDNEY, UROLOGY INSTRUMENTS [SURGICOSE]
LIVER, GALL BLADER, KIDNEY, UROLOGY INSTRUMENTS [SURGICOSE]
 
ΔΕΦΚΦ/Α/1025336/ΕΞ2017
ΔΕΦΚΦ/Α/1025336/ΕΞ2017ΔΕΦΚΦ/Α/1025336/ΕΞ2017
ΔΕΦΚΦ/Α/1025336/ΕΞ2017
 
New cv 2016
New cv 2016New cv 2016
New cv 2016
 
Final presentation nmdl
Final presentation nmdlFinal presentation nmdl
Final presentation nmdl
 
Your Guide to 'The Cloud'
Your Guide to 'The Cloud'Your Guide to 'The Cloud'
Your Guide to 'The Cloud'
 
BONE RONGEURS [SURGICOSE PAKISTAN]
BONE RONGEURS [SURGICOSE PAKISTAN]BONE RONGEURS [SURGICOSE PAKISTAN]
BONE RONGEURS [SURGICOSE PAKISTAN]
 
Brief History of Toile
Brief History of ToileBrief History of Toile
Brief History of Toile
 
Tugas 2
Tugas 2Tugas 2
Tugas 2
 
How to increase website conversions by applying the laws of great product design
How to increase website conversions by applying the laws of great product designHow to increase website conversions by applying the laws of great product design
How to increase website conversions by applying the laws of great product design
 
appletreeposter2006
appletreeposter2006appletreeposter2006
appletreeposter2006
 
Debbie Bieller's Resume 5.1.14
Debbie Bieller's Resume 5.1.14Debbie Bieller's Resume 5.1.14
Debbie Bieller's Resume 5.1.14
 
ZigBee Smart LED light
ZigBee Smart LED lightZigBee Smart LED light
ZigBee Smart LED light
 
Boost conversions by localizing your marketing
Boost conversions by localizing your marketingBoost conversions by localizing your marketing
Boost conversions by localizing your marketing
 
Lucy
LucyLucy
Lucy
 
CV of Jianyu Hu (contact info not included)
CV of Jianyu Hu (contact info not included)CV of Jianyu Hu (contact info not included)
CV of Jianyu Hu (contact info not included)
 
ΣΕΒ για την Ελληνική Οικονομία - 061016
ΣΕΒ για την Ελληνική Οικονομία - 061016ΣΕΒ για την Ελληνική Οικονομία - 061016
ΣΕΒ για την Ελληνική Οικονομία - 061016
 

Similar to Distance measuring Algrothim

Machine Learning Tutorial Part - 1 | Machine Learning Tutorial For Beginners ...
Machine Learning Tutorial Part - 1 | Machine Learning Tutorial For Beginners ...Machine Learning Tutorial Part - 1 | Machine Learning Tutorial For Beginners ...
Machine Learning Tutorial Part - 1 | Machine Learning Tutorial For Beginners ...
Simplilearn
 
Comparison of Distance Transform Based Features
Comparison of Distance Transform Based FeaturesComparison of Distance Transform Based Features
Comparison of Distance Transform Based Features
IJERA Editor
 
Purple and Black Simple Technology Keynote Presentation (1).pdf
Purple and Black Simple Technology Keynote Presentation (1).pdfPurple and Black Simple Technology Keynote Presentation (1).pdf
Purple and Black Simple Technology Keynote Presentation (1).pdf
AkshayMapalakajs
 
Introduction to Image Processing
Introduction to Image ProcessingIntroduction to Image Processing
Introduction to Image Processing
Israel Gbati
 
3 ijaems nov-2015-6-development of an advanced technique for historical docum...
3 ijaems nov-2015-6-development of an advanced technique for historical docum...3 ijaems nov-2015-6-development of an advanced technique for historical docum...
3 ijaems nov-2015-6-development of an advanced technique for historical docum...
INFOGAIN PUBLICATION
 
Data Science Interview Questions | Data Science Interview Questions And Answe...
Data Science Interview Questions | Data Science Interview Questions And Answe...Data Science Interview Questions | Data Science Interview Questions And Answe...
Data Science Interview Questions | Data Science Interview Questions And Answe...
Simplilearn
 
Threshold Selection for Image segmentation
Threshold Selection for Image segmentationThreshold Selection for Image segmentation
Threshold Selection for Image segmentation
Parijat Sinha
 
MSE.pptx
MSE.pptxMSE.pptx
MSE.pptx
JantuRahaman
 
A Novel Super Resolution Algorithm Using Interpolation and LWT Based Denoisin...
A Novel Super Resolution Algorithm Using Interpolation and LWT Based Denoisin...A Novel Super Resolution Algorithm Using Interpolation and LWT Based Denoisin...
A Novel Super Resolution Algorithm Using Interpolation and LWT Based Denoisin...
CSCJournals
 
Multiclass recognition with
Multiclass recognition withMulticlass recognition with
Multiclass recognition with
csandit
 
Multiclass Recognition with Multiple Feature Trees
Multiclass Recognition with Multiple Feature TreesMulticlass Recognition with Multiple Feature Trees
Multiclass Recognition with Multiple Feature Trees
csandit
 
Bayes estimators for the shape parameter of pareto type i
Bayes estimators for the shape parameter of pareto type iBayes estimators for the shape parameter of pareto type i
Bayes estimators for the shape parameter of pareto type i
Alexander Decker
 
Bayes estimators for the shape parameter of pareto type i
Bayes estimators for the shape parameter of pareto type iBayes estimators for the shape parameter of pareto type i
Bayes estimators for the shape parameter of pareto type i
Alexander Decker
 
A modified pso based graph cut algorithm for the selection of optimal regular...
A modified pso based graph cut algorithm for the selection of optimal regular...A modified pso based graph cut algorithm for the selection of optimal regular...
A modified pso based graph cut algorithm for the selection of optimal regular...
IAEME Publication
 
Wordoku Puzzle Solver - Image Processing Project
Wordoku Puzzle Solver - Image Processing ProjectWordoku Puzzle Solver - Image Processing Project
Wordoku Puzzle Solver - Image Processing Project
Surya Chandra
 
Fuzzy Region Merging Using Fuzzy Similarity Measurement on Image Segmentation
Fuzzy Region Merging Using Fuzzy Similarity Measurement  on Image Segmentation  Fuzzy Region Merging Using Fuzzy Similarity Measurement  on Image Segmentation
Fuzzy Region Merging Using Fuzzy Similarity Measurement on Image Segmentation
IJECEIAES
 
Blind Image Seperation Using Forward Difference Method (FDM)
Blind Image Seperation Using Forward Difference Method (FDM)Blind Image Seperation Using Forward Difference Method (FDM)
Blind Image Seperation Using Forward Difference Method (FDM)
sipij
 
2014-mo444-practical-assignment-04-paulo_faria
2014-mo444-practical-assignment-04-paulo_faria2014-mo444-practical-assignment-04-paulo_faria
2014-mo444-practical-assignment-04-paulo_faria
Paulo Faria
 
Improving Analogy Software Effort Estimation using Fuzzy Feature Subset Selec...
Improving Analogy Software Effort Estimation using Fuzzy Feature Subset Selec...Improving Analogy Software Effort Estimation using Fuzzy Feature Subset Selec...
Improving Analogy Software Effort Estimation using Fuzzy Feature Subset Selec...
gregoryg
 
Working with the data for Machine Learning
Working with the data for Machine LearningWorking with the data for Machine Learning
Working with the data for Machine Learning
Mehwish690898
 

Similar to Distance measuring Algrothim (20)

Machine Learning Tutorial Part - 1 | Machine Learning Tutorial For Beginners ...
Machine Learning Tutorial Part - 1 | Machine Learning Tutorial For Beginners ...Machine Learning Tutorial Part - 1 | Machine Learning Tutorial For Beginners ...
Machine Learning Tutorial Part - 1 | Machine Learning Tutorial For Beginners ...
 
Comparison of Distance Transform Based Features
Comparison of Distance Transform Based FeaturesComparison of Distance Transform Based Features
Comparison of Distance Transform Based Features
 
Purple and Black Simple Technology Keynote Presentation (1).pdf
Purple and Black Simple Technology Keynote Presentation (1).pdfPurple and Black Simple Technology Keynote Presentation (1).pdf
Purple and Black Simple Technology Keynote Presentation (1).pdf
 
Introduction to Image Processing
Introduction to Image ProcessingIntroduction to Image Processing
Introduction to Image Processing
 
3 ijaems nov-2015-6-development of an advanced technique for historical docum...
3 ijaems nov-2015-6-development of an advanced technique for historical docum...3 ijaems nov-2015-6-development of an advanced technique for historical docum...
3 ijaems nov-2015-6-development of an advanced technique for historical docum...
 
Data Science Interview Questions | Data Science Interview Questions And Answe...
Data Science Interview Questions | Data Science Interview Questions And Answe...Data Science Interview Questions | Data Science Interview Questions And Answe...
Data Science Interview Questions | Data Science Interview Questions And Answe...
 
Threshold Selection for Image segmentation
Threshold Selection for Image segmentationThreshold Selection for Image segmentation
Threshold Selection for Image segmentation
 
MSE.pptx
MSE.pptxMSE.pptx
MSE.pptx
 
A Novel Super Resolution Algorithm Using Interpolation and LWT Based Denoisin...
A Novel Super Resolution Algorithm Using Interpolation and LWT Based Denoisin...A Novel Super Resolution Algorithm Using Interpolation and LWT Based Denoisin...
A Novel Super Resolution Algorithm Using Interpolation and LWT Based Denoisin...
 
Multiclass recognition with
Multiclass recognition withMulticlass recognition with
Multiclass recognition with
 
Multiclass Recognition with Multiple Feature Trees
Multiclass Recognition with Multiple Feature TreesMulticlass Recognition with Multiple Feature Trees
Multiclass Recognition with Multiple Feature Trees
 
Bayes estimators for the shape parameter of pareto type i
Bayes estimators for the shape parameter of pareto type iBayes estimators for the shape parameter of pareto type i
Bayes estimators for the shape parameter of pareto type i
 
Bayes estimators for the shape parameter of pareto type i
Bayes estimators for the shape parameter of pareto type iBayes estimators for the shape parameter of pareto type i
Bayes estimators for the shape parameter of pareto type i
 
A modified pso based graph cut algorithm for the selection of optimal regular...
A modified pso based graph cut algorithm for the selection of optimal regular...A modified pso based graph cut algorithm for the selection of optimal regular...
A modified pso based graph cut algorithm for the selection of optimal regular...
 
Wordoku Puzzle Solver - Image Processing Project
Wordoku Puzzle Solver - Image Processing ProjectWordoku Puzzle Solver - Image Processing Project
Wordoku Puzzle Solver - Image Processing Project
 
Fuzzy Region Merging Using Fuzzy Similarity Measurement on Image Segmentation
Fuzzy Region Merging Using Fuzzy Similarity Measurement  on Image Segmentation  Fuzzy Region Merging Using Fuzzy Similarity Measurement  on Image Segmentation
Fuzzy Region Merging Using Fuzzy Similarity Measurement on Image Segmentation
 
Blind Image Seperation Using Forward Difference Method (FDM)
Blind Image Seperation Using Forward Difference Method (FDM)Blind Image Seperation Using Forward Difference Method (FDM)
Blind Image Seperation Using Forward Difference Method (FDM)
 
2014-mo444-practical-assignment-04-paulo_faria
2014-mo444-practical-assignment-04-paulo_faria2014-mo444-practical-assignment-04-paulo_faria
2014-mo444-practical-assignment-04-paulo_faria
 
Improving Analogy Software Effort Estimation using Fuzzy Feature Subset Selec...
Improving Analogy Software Effort Estimation using Fuzzy Feature Subset Selec...Improving Analogy Software Effort Estimation using Fuzzy Feature Subset Selec...
Improving Analogy Software Effort Estimation using Fuzzy Feature Subset Selec...
 
Working with the data for Machine Learning
Working with the data for Machine LearningWorking with the data for Machine Learning
Working with the data for Machine Learning
 

Distance measuring Algrothim

  • 1. Methodology and theory behind Distance Measuring Algorithm Using One camera
  • 2. In this document only theory and mathematics behind algorithm is described, details related programming is not discussed. Our Distance Measuring Algorithm (DMA) has three parts  Track object  Feed set points  Measure distance Track object A picture is better than thousand words so first see these pictures.
  • 3.
  • 4.
  • 5.
  • 6. From above images we notice that aspect ratio (width/height) is more or less 1.3 so for tracking particular object (sign board in our case) we find all objects in image and check aspect ratio of all objects found in image and discard all object whose aspect ratio is not equal to 1.3 so doing this we can easily track particular object. Feeding set points This method is not plug and play we have to feed some set points let us organize data obtained from above images in table. No Aspect ratio (width/height) no unit Distance (feet) Area (width x height) in pixels 1 1.37 0.5 280071 2 1.35 2 91520 3 1.313 3 46436
  • 7. 4 1.33 4 26980 5 1.355 5 14664 Measuring Distance For measuring distance we are using Lagrange’s interpolation formula Formula for five point’s data (x- x1) (x- x2)(x- x3)(x- x4) (x- x0)(x- x1) (x- x2)(x- x3) f(x) = f0+ . . . + f4 (x0 - x1) (x0 - x2)(x0 - x3)(x0 - x4) (x4 - x0)(x4 - x1)(x4 - x2)(x4 - x3) Follow this link to understand Lagrange’s interpolation http://mat.iitm.ac.in/home/sryedida/public_html/caimna/interpolation/lagrange.html Applying langrage’s interpolation to above data to find distance at any point Distance (D) 0.5 2 3 4 5 Area (A) 280071 91520 46436 26980 14664 Our unknown quantity is distance we know area so we can easily find distance at any value of area. Limitations If camera move to close to object then this method does not works