SlideShare ist ein Scribd-Unternehmen logo
1 von 39
Road Extraction fromRemote Sensing Images using SVM combined with FCM and MRF Jiawei Xu MULTIMEDIA PROCESSING LABORATORYDepartment of Electronic Engineering, Hallym UniversityE-mail: abyssecho@hallym.ac.kr
Contents Introduction A brief review of previous methods Multi-times SVM Proposed algorithm Experimental results Performance evaluation Conclusion
A brief review of previous methods Mathematical morphology Hough transform P-value segmentation Genetic algorithm Markov random field
MATHEMATICAL MORPHOLOGY Flowchart of the proposed algorithm in mathematical morphology Original image    2D median filter     open operator    erosion & thinning Structure element:square, rectangle, ball, disk and line… Morphology: Erosion,dilation,openoperator, close operator
Hough transform The Hough transform is most commonly used for the detection of regular curves such as lines, circles, ellipses, etc. Parameter setting in this thesis: Detection sensitivity: 0.15 The smaller the value is, the more features in the image will be considered as lines.
P-value segmentation This figure shows the entire procedure of road extraction using P value segmentation. In figure (a) is an input image with some selected road parts on it, (b) is the cumulative gray-image histogram distribution , (c) is the result of P value segmentation. Application of some morphological operators such as region property, open operator to (c) results in (d), (e) is the road net image using thinning function, (f) shows the input image with the extracted road net overlaid on it
P-value segmentation Post processing incurs an information loss. (a) is the original image, (b) is the P value diagram, (c) is the result of P value segmentation and (d) is the application of some morphological operators, such  as region property, open operator based on (c). Compare with Genetic algorithm threshold segmentation Best fitness and best threshold with generation increase
Markov random field Mean value and variance of selected area Original image       MRF processing        Speckle-like noise removal   Road net
Linear SVMs ,[object Object]
belong to a family of generalized linear classifiers
minimize the empirical classification error
maximize the geometric margin,[object Object]
 To slove such a problem is to import a nonlinear mapping function. If data sets in lower dimensional space are transformed to a higher dimensional space and successfully separated by a linear hyperplane as we showed in right figure ,we can utilize SVM.linear optimal  separating hyper-plane nonlinear optimal separating hyper-plane
Multi-times SVM classification Fig.1:Pre-trained model is constituted by 20 circles from road and 20 asterisks from non-road, respectively.  Advantages: Disadvantages: Easy to be implemented, using LIBSVM Polynomial kernel, RBF kernel and Sigmoid kernel were experimented but due to their similar results, here we only illustrate polynomial kernel function, the formula is as follows: ,[object Object]
Complex post processing ,[object Object]
Block diagram of our approach FCM classifer RS image SVM classifer MRF regularizer       Road image
FCM preprocessor Algorithm Calculate  the fuzzy cluster centers                                                  by using     and the new partition matrix     by using Update       to  3. Stop iteration if    otherwise set                           and return to step 2 non-road-like        non-road-like          road-like  image1                 image 2               image 3 Partition into a collection of c fuzzy clusters with a list of c cluster centers V , such that                               and a partition matrix where     is a numerical  value in [0,1] that tells the degree to which the element    belongs to the i-th cluster.
FCM processing result  (a)                    (b)              (c)               (d)(Road-like image used for further processing)   (a)Original image(b)~(d)cluster 1,2,3
Why we use FCM before SVM? Because of unbalanced data If class A(non-road) samples distributed over a large area Class B(road) samples distributed over a small area, Supposing we use SVM directly, the coefficient Matrix will be more close to the   class that has a large distribution (which means hyper-plane is close to the  large-distributed class because of the property of SVM) An extreme case is : one-class SVM(to detect the outlier) If samples amounts is very few and distributed in an extremely small area, SVM will recognize it as outlier,(in road extraction,for extreme case, road part will be neglected as the outlier)i.e., the hyperplane is unbalancedly assigned, which will lead to misclassification. FCM  can display the each cluster features more obviously,alternatively speaking, enlarge the difference/distance between different clusters, which more or less decrease the misclassification rate.
Test Images & Reference Models to evaluate our performance
Performance evaluation criteria Complete:  Correct:  Rank distance:  Quality :  True positive (TP):  both the processed model and the reference scene model classify the pixel belonging to road. True negative (TN): both the processed model and the reference scene model classify the pixel as belonging to the background. False positive (FP): processed model classifies the pixel as belonging to road, but the reference scene model classifies the pixel as belonging to the background. False negative (FN): the processed model classifies the pixel as belonging to the background, but the reference scene model classifies the pixel as belonging to road
Comparison between SVM and FCM+SVM RS images ,[object Object]
Shanghai.bmp
Vancouver.bmp,[object Object]
Experimental results We intentionally selected RS images with different characteristics:Beijing,shanghai,Vancouver…  (ALL images from http://maps.google.com/) original images             FCM-SVM processing        MRF regularizer          output images
Multi-classes SVM(one against all) RS image             road-class image       lake-class image expectation value initialization  classification of samples to be recognized by SVM  plot result image
Rank distance of K-means, SVM and our method   (%)  We do not list out morphology, Hough transform…because rank distance,  quality percentage and other values are much lower than these approaches
Quality percentage of K-means, SVM and proposed method  (%)
Comparison of FCM+K-means with FCM+SVM (a) Comparison of FCM+K-means with FCM+SVM  (a) results of FCM clustering; (b) FCM followed by K-means clustring; (c) results of FCM followed by SVM.          (b)                (c) (a)          (b)                (c)
Comparison of FCM+K-means with FCM+SVM
GUI IMPLEMENTATION FOR ROAD Extraction: example 1
Example 2
Example 3
Executable file contains DOS window  Road.exe: Classified the functions two categories: One is for manual control methods and the other is for machine learning methods Meanwhile, we can also conceal DOS window
Conclusion This thesis has proposed a new road extraction method based on SVM classification combined with FCM clustering and MRF regularization.  ,[object Object]
Using FCM clustering to separate road-like cluster and the other clusters increases the SVM classification accuracy.
We used MRF regularization to remove speckle-like noise then we could extract the fine road net.
Experimental results with several images with various features show that the proposed method gives us a higher accuracy and strong robustness regardless of input characteristics.,[object Object]
References [1] 	 Stefan Hinz, “Automatic extraction of urban road networks from multi-view aerial imagery”, Technische University 2003 [2]   VladmirVapnik, ”Statistical Learning Theory”, JOHN WILELY & SONS, Inc.1998 [3]	Curt H.Davis, “An integrated system for automatic road mapping from high-resolution multi-spectral satellite imagery by information fusion”, Elsevier Inc. 2004  [4]	Yairmoshe, “GUI with Matlab” Department of Electronic Engineering, Columbia University , May 2004. [5]	http://maps.google.com/ [6]	Yang Li, “A new validity function for fuzzy clustering”, School of mathematical sciences, Beijing normal university, 2005 [6]	Xu Yong and Shaoguang Zhou, “Markov random field for road extraction applications in remote sensing images”, Department of Surveying and Mapping Engineering, Hohai University, 2008 [7]	David M.McKeown ,“Performance evaluation for automatic feature extraction ”, Computer Science Department, Carnegie Mellon University 2000 [8]	Patrick Perez, “Markov random fields and images”, Campus Beauileu, 1999 [9]	Drs. Trani and Rahka, “MATLAB Graphic user interfaces(GUI) computer applications in civil engineering ”, Spring, 2000

Weitere ähnliche Inhalte

Was ist angesagt?

Report bep thomas_blanken
Report bep thomas_blankenReport bep thomas_blanken
Report bep thomas_blankenxepost
 
SINGLE IMAGE SUPER RESOLUTION IN SPATIAL AND WAVELET DOMAIN
SINGLE IMAGE SUPER RESOLUTION IN SPATIAL AND WAVELET DOMAINSINGLE IMAGE SUPER RESOLUTION IN SPATIAL AND WAVELET DOMAIN
SINGLE IMAGE SUPER RESOLUTION IN SPATIAL AND WAVELET DOMAINijma
 
Parallel implementation of geodesic distance transform with application in su...
Parallel implementation of geodesic distance transform with application in su...Parallel implementation of geodesic distance transform with application in su...
Parallel implementation of geodesic distance transform with application in su...Tuan Q. Pham
 
The use of Orfeo Toolbox in the context of map updating
The use of Orfeo Toolbox in the context of map updatingThe use of Orfeo Toolbox in the context of map updating
The use of Orfeo Toolbox in the context of map updatingmelaneum
 
Towards Light-weight and Real-time Line Segment Detection
Towards Light-weight and Real-time Line Segment DetectionTowards Light-weight and Real-time Line Segment Detection
Towards Light-weight and Real-time Line Segment DetectionByung Soo Ko
 
Locating texture boundaries using a fast unsupervised approach based on clust...
Locating texture boundaries using a fast unsupervised approach based on clust...Locating texture boundaries using a fast unsupervised approach based on clust...
Locating texture boundaries using a fast unsupervised approach based on clust...Mehryar (Mike) E., Ph.D.
 
Robust and Real Time Detection of Curvy Lanes (Curves) Having Desired Slopes ...
Robust and Real Time Detection of Curvy Lanes (Curves) Having Desired Slopes ...Robust and Real Time Detection of Curvy Lanes (Curves) Having Desired Slopes ...
Robust and Real Time Detection of Curvy Lanes (Curves) Having Desired Slopes ...csandit
 
New geometric interpretation and analytic solution for quadrilateral reconstr...
New geometric interpretation and analytic solution for quadrilateral reconstr...New geometric interpretation and analytic solution for quadrilateral reconstr...
New geometric interpretation and analytic solution for quadrilateral reconstr...Joo-Haeng Lee
 
FR4.L09.5 - THREE DIMENSIONAL RECONSTRUCTION OF URBAN AREAS USING JOINTLY PHA...
FR4.L09.5 - THREE DIMENSIONAL RECONSTRUCTION OF URBAN AREAS USING JOINTLY PHA...FR4.L09.5 - THREE DIMENSIONAL RECONSTRUCTION OF URBAN AREAS USING JOINTLY PHA...
FR4.L09.5 - THREE DIMENSIONAL RECONSTRUCTION OF URBAN AREAS USING JOINTLY PHA...grssieee
 
Current issues - Signal & Image Processing: An International Journal (SIPIJ)
Current issues - Signal & Image Processing: An International Journal (SIPIJ)Current issues - Signal & Image Processing: An International Journal (SIPIJ)
Current issues - Signal & Image Processing: An International Journal (SIPIJ)sipij
 
Environment Detection and Path Planning Using the E-puck Robot
Environment Detection and Path Planning Using the E-puck Robot Environment Detection and Path Planning Using the E-puck Robot
Environment Detection and Path Planning Using the E-puck Robot IRJET Journal
 
Final Project Report Nadar
Final Project Report NadarFinal Project Report Nadar
Final Project Report NadarMaher Nadar
 
Double transform contoor extraction
Double transform contoor extractionDouble transform contoor extraction
Double transform contoor extractionarteimi
 
Unconstrained Optimization Method to Design Two Channel Quadrature Mirror Fil...
Unconstrained Optimization Method to Design Two Channel Quadrature Mirror Fil...Unconstrained Optimization Method to Design Two Channel Quadrature Mirror Fil...
Unconstrained Optimization Method to Design Two Channel Quadrature Mirror Fil...CSCJournals
 
Structure and Motion - 3D Reconstruction of Cameras and Structure
Structure and Motion - 3D Reconstruction of Cameras and StructureStructure and Motion - 3D Reconstruction of Cameras and Structure
Structure and Motion - 3D Reconstruction of Cameras and StructureGiovanni Murru
 
Image Processing Research paper
Image Processing Research paperImage Processing Research paper
Image Processing Research paperRonak Vyas
 
Repeat-Frame Selection Algorithm for Frame Rate Video Transcoding
Repeat-Frame Selection Algorithm for Frame Rate Video TranscodingRepeat-Frame Selection Algorithm for Frame Rate Video Transcoding
Repeat-Frame Selection Algorithm for Frame Rate Video TranscodingCSCJournals
 
A Hough Transform Implementation for Line Detection for a Mobile Robot Self-N...
A Hough Transform Implementation for Line Detection for a Mobile Robot Self-N...A Hough Transform Implementation for Line Detection for a Mobile Robot Self-N...
A Hough Transform Implementation for Line Detection for a Mobile Robot Self-N...iosrjce
 

Was ist angesagt? (20)

Report bep thomas_blanken
Report bep thomas_blankenReport bep thomas_blanken
Report bep thomas_blanken
 
SINGLE IMAGE SUPER RESOLUTION IN SPATIAL AND WAVELET DOMAIN
SINGLE IMAGE SUPER RESOLUTION IN SPATIAL AND WAVELET DOMAINSINGLE IMAGE SUPER RESOLUTION IN SPATIAL AND WAVELET DOMAIN
SINGLE IMAGE SUPER RESOLUTION IN SPATIAL AND WAVELET DOMAIN
 
Parallel implementation of geodesic distance transform with application in su...
Parallel implementation of geodesic distance transform with application in su...Parallel implementation of geodesic distance transform with application in su...
Parallel implementation of geodesic distance transform with application in su...
 
The use of Orfeo Toolbox in the context of map updating
The use of Orfeo Toolbox in the context of map updatingThe use of Orfeo Toolbox in the context of map updating
The use of Orfeo Toolbox in the context of map updating
 
Towards Light-weight and Real-time Line Segment Detection
Towards Light-weight and Real-time Line Segment DetectionTowards Light-weight and Real-time Line Segment Detection
Towards Light-weight and Real-time Line Segment Detection
 
Locating texture boundaries using a fast unsupervised approach based on clust...
Locating texture boundaries using a fast unsupervised approach based on clust...Locating texture boundaries using a fast unsupervised approach based on clust...
Locating texture boundaries using a fast unsupervised approach based on clust...
 
D04922630
D04922630D04922630
D04922630
 
Robust and Real Time Detection of Curvy Lanes (Curves) Having Desired Slopes ...
Robust and Real Time Detection of Curvy Lanes (Curves) Having Desired Slopes ...Robust and Real Time Detection of Curvy Lanes (Curves) Having Desired Slopes ...
Robust and Real Time Detection of Curvy Lanes (Curves) Having Desired Slopes ...
 
New geometric interpretation and analytic solution for quadrilateral reconstr...
New geometric interpretation and analytic solution for quadrilateral reconstr...New geometric interpretation and analytic solution for quadrilateral reconstr...
New geometric interpretation and analytic solution for quadrilateral reconstr...
 
FR4.L09.5 - THREE DIMENSIONAL RECONSTRUCTION OF URBAN AREAS USING JOINTLY PHA...
FR4.L09.5 - THREE DIMENSIONAL RECONSTRUCTION OF URBAN AREAS USING JOINTLY PHA...FR4.L09.5 - THREE DIMENSIONAL RECONSTRUCTION OF URBAN AREAS USING JOINTLY PHA...
FR4.L09.5 - THREE DIMENSIONAL RECONSTRUCTION OF URBAN AREAS USING JOINTLY PHA...
 
Current issues - Signal & Image Processing: An International Journal (SIPIJ)
Current issues - Signal & Image Processing: An International Journal (SIPIJ)Current issues - Signal & Image Processing: An International Journal (SIPIJ)
Current issues - Signal & Image Processing: An International Journal (SIPIJ)
 
DICTA 2017 poster
DICTA 2017 posterDICTA 2017 poster
DICTA 2017 poster
 
Environment Detection and Path Planning Using the E-puck Robot
Environment Detection and Path Planning Using the E-puck Robot Environment Detection and Path Planning Using the E-puck Robot
Environment Detection and Path Planning Using the E-puck Robot
 
Final Project Report Nadar
Final Project Report NadarFinal Project Report Nadar
Final Project Report Nadar
 
Double transform contoor extraction
Double transform contoor extractionDouble transform contoor extraction
Double transform contoor extraction
 
Unconstrained Optimization Method to Design Two Channel Quadrature Mirror Fil...
Unconstrained Optimization Method to Design Two Channel Quadrature Mirror Fil...Unconstrained Optimization Method to Design Two Channel Quadrature Mirror Fil...
Unconstrained Optimization Method to Design Two Channel Quadrature Mirror Fil...
 
Structure and Motion - 3D Reconstruction of Cameras and Structure
Structure and Motion - 3D Reconstruction of Cameras and StructureStructure and Motion - 3D Reconstruction of Cameras and Structure
Structure and Motion - 3D Reconstruction of Cameras and Structure
 
Image Processing Research paper
Image Processing Research paperImage Processing Research paper
Image Processing Research paper
 
Repeat-Frame Selection Algorithm for Frame Rate Video Transcoding
Repeat-Frame Selection Algorithm for Frame Rate Video TranscodingRepeat-Frame Selection Algorithm for Frame Rate Video Transcoding
Repeat-Frame Selection Algorithm for Frame Rate Video Transcoding
 
A Hough Transform Implementation for Line Detection for a Mobile Robot Self-N...
A Hough Transform Implementation for Line Detection for a Mobile Robot Self-N...A Hough Transform Implementation for Line Detection for a Mobile Robot Self-N...
A Hough Transform Implementation for Line Detection for a Mobile Robot Self-N...
 

Andere mochten auch

A survey on road extraction from color image using vectorization
A survey on road extraction from color image using vectorizationA survey on road extraction from color image using vectorization
A survey on road extraction from color image using vectorizationeSAT Journals
 
Building extraction from remote sensing imageries by data fusion techniques
Building extraction from remote sensing imageries by data fusion techniquesBuilding extraction from remote sensing imageries by data fusion techniques
Building extraction from remote sensing imageries by data fusion techniqueseSAT Journals
 
Posicionamiento natural seo para la empresa - Octubre 2010
Posicionamiento natural seo para la empresa - Octubre 2010Posicionamiento natural seo para la empresa - Octubre 2010
Posicionamiento natural seo para la empresa - Octubre 2010t2ó | Connect. Convert. Grow.
 
About cci media connecting solutions introduction 2012
About cci media connecting solutions   introduction 2012About cci media connecting solutions   introduction 2012
About cci media connecting solutions introduction 2012Patrick Cotting
 
120 talutloze lichtgewicht ophogingen voor trambaan over a4
120 talutloze lichtgewicht ophogingen voor trambaan over a4120 talutloze lichtgewicht ophogingen voor trambaan over a4
120 talutloze lichtgewicht ophogingen voor trambaan over a4CROW
 
Krishnan Resume (1)
Krishnan Resume (1)Krishnan Resume (1)
Krishnan Resume (1)krishnan N
 
Taller Android UTPL: Estilos y Diálogos
Taller Android UTPL: Estilos y DiálogosTaller Android UTPL: Estilos y Diálogos
Taller Android UTPL: Estilos y DiálogosJuanpshinkei
 
Análisis de pagos en el mundo. Mayo 2016
Análisis de pagos en el mundo. Mayo 2016 Análisis de pagos en el mundo. Mayo 2016
Análisis de pagos en el mundo. Mayo 2016 INFORMA D&B
 
Wikis, blogs, redes sociales
Wikis, blogs, redes socialesWikis, blogs, redes sociales
Wikis, blogs, redes socialesJimanero
 
Programming Healthcare Silos
Programming Healthcare SilosProgramming Healthcare Silos
Programming Healthcare SilosVaibhav Bhandari
 
Extracción del petróleo
Extracción del petróleoExtracción del petróleo
Extracción del petróleoJoanie Cortez
 
El Lazarillo de Tormes (Como niños, la picaresca)
El Lazarillo de Tormes (Como niños, la picaresca)El Lazarillo de Tormes (Como niños, la picaresca)
El Lazarillo de Tormes (Como niños, la picaresca)Samuel Perrino Martínez
 
Parallel DNA Sequence Alignment
Parallel DNA Sequence AlignmentParallel DNA Sequence Alignment
Parallel DNA Sequence AlignmentGiuliana Carullo
 

Andere mochten auch (20)

A survey on road extraction from color image using vectorization
A survey on road extraction from color image using vectorizationA survey on road extraction from color image using vectorization
A survey on road extraction from color image using vectorization
 
Building extraction from remote sensing imageries by data fusion techniques
Building extraction from remote sensing imageries by data fusion techniquesBuilding extraction from remote sensing imageries by data fusion techniques
Building extraction from remote sensing imageries by data fusion techniques
 
Ptek HB3
Ptek HB3Ptek HB3
Ptek HB3
 
Posicionamiento natural seo para la empresa - Octubre 2010
Posicionamiento natural seo para la empresa - Octubre 2010Posicionamiento natural seo para la empresa - Octubre 2010
Posicionamiento natural seo para la empresa - Octubre 2010
 
En La Luz De La Providencia Divina,
En La Luz De La Providencia Divina,En La Luz De La Providencia Divina,
En La Luz De La Providencia Divina,
 
Propuesta de trabajo.
Propuesta de trabajo.Propuesta de trabajo.
Propuesta de trabajo.
 
Chapter 5
Chapter 5Chapter 5
Chapter 5
 
AFCN TFC Jess Ibrom - Wellington Phoenix Youth Academy
AFCN TFC Jess Ibrom - Wellington Phoenix Youth AcademyAFCN TFC Jess Ibrom - Wellington Phoenix Youth Academy
AFCN TFC Jess Ibrom - Wellington Phoenix Youth Academy
 
Recopilados
RecopiladosRecopilados
Recopilados
 
About cci media connecting solutions introduction 2012
About cci media connecting solutions   introduction 2012About cci media connecting solutions   introduction 2012
About cci media connecting solutions introduction 2012
 
120 talutloze lichtgewicht ophogingen voor trambaan over a4
120 talutloze lichtgewicht ophogingen voor trambaan over a4120 talutloze lichtgewicht ophogingen voor trambaan over a4
120 talutloze lichtgewicht ophogingen voor trambaan over a4
 
Krishnan Resume (1)
Krishnan Resume (1)Krishnan Resume (1)
Krishnan Resume (1)
 
Taller Android UTPL: Estilos y Diálogos
Taller Android UTPL: Estilos y DiálogosTaller Android UTPL: Estilos y Diálogos
Taller Android UTPL: Estilos y Diálogos
 
Análisis de pagos en el mundo. Mayo 2016
Análisis de pagos en el mundo. Mayo 2016 Análisis de pagos en el mundo. Mayo 2016
Análisis de pagos en el mundo. Mayo 2016
 
Wikis, blogs, redes sociales
Wikis, blogs, redes socialesWikis, blogs, redes sociales
Wikis, blogs, redes sociales
 
Programming Healthcare Silos
Programming Healthcare SilosProgramming Healthcare Silos
Programming Healthcare Silos
 
La pelota -Felisberto Hernández
La pelota -Felisberto HernándezLa pelota -Felisberto Hernández
La pelota -Felisberto Hernández
 
Extracción del petróleo
Extracción del petróleoExtracción del petróleo
Extracción del petróleo
 
El Lazarillo de Tormes (Como niños, la picaresca)
El Lazarillo de Tormes (Como niños, la picaresca)El Lazarillo de Tormes (Como niños, la picaresca)
El Lazarillo de Tormes (Como niños, la picaresca)
 
Parallel DNA Sequence Alignment
Parallel DNA Sequence AlignmentParallel DNA Sequence Alignment
Parallel DNA Sequence Alignment
 

Ähnlich wie Presentation for korea multimedia(in english)

A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHMA ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHMcsandit
 
Part 3. Further Data preprocessing
Part 3. Further Data preprocessingPart 3. Further Data preprocessing
Part 3. Further Data preprocessingbutest
 
Traffic sign detection via graph based ranking and segmentation
Traffic sign detection via graph based ranking and segmentationTraffic sign detection via graph based ranking and segmentation
Traffic sign detection via graph based ranking and segmentationPREMSAI CHEEDELLA
 
Miniproject final group 14
Miniproject final group 14Miniproject final group 14
Miniproject final group 14Ashish Mundhra
 
VEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVMVEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVMcseij
 
VEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVM VEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVM cseij
 
VEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVMVEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVMcseij
 
Vehicle Recognition Using VIBE and SVM
Vehicle Recognition Using VIBE and SVMVehicle Recognition Using VIBE and SVM
Vehicle Recognition Using VIBE and SVMCSEIJJournal
 
Robust and real time detection of
Robust and real time detection ofRobust and real time detection of
Robust and real time detection ofcsandit
 
Introduction to Grad-CAM (complete version)
Introduction to Grad-CAM (complete version)Introduction to Grad-CAM (complete version)
Introduction to Grad-CAM (complete version)Hsing-chuan Hsieh
 
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...IRJET Journal
 
Method of optimization of the fundamental matrix by technique speeded up rob...
Method of optimization of the fundamental matrix by technique  speeded up rob...Method of optimization of the fundamental matrix by technique  speeded up rob...
Method of optimization of the fundamental matrix by technique speeded up rob...IJECEIAES
 
ANOVA and Fisher Criterion based Feature Selection for Lower Dimensional Univ...
ANOVA and Fisher Criterion based Feature Selection for Lower Dimensional Univ...ANOVA and Fisher Criterion based Feature Selection for Lower Dimensional Univ...
ANOVA and Fisher Criterion based Feature Selection for Lower Dimensional Univ...CSCJournals
 
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNNAutomatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNNZihao(Gerald) Zhang
 
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...ijma
 
A New Approach to Linear Estimation Problem in Multiuser Massive MIMO Systems
A New Approach to Linear Estimation Problem in Multiuser Massive MIMO SystemsA New Approach to Linear Estimation Problem in Multiuser Massive MIMO Systems
A New Approach to Linear Estimation Problem in Multiuser Massive MIMO SystemsRadita Apriana
 
Estimation of Terrain Gradient Conditions & Obstacle Detection Using a Monocu...
Estimation of Terrain Gradient Conditions & Obstacle Detection Using a Monocu...Estimation of Terrain Gradient Conditions & Obstacle Detection Using a Monocu...
Estimation of Terrain Gradient Conditions & Obstacle Detection Using a Monocu...Connor Goddard
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)IJERD Editor
 

Ähnlich wie Presentation for korea multimedia(in english) (20)

A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHMA ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
A ROS IMPLEMENTATION OF THE MONO-SLAM ALGORITHM
 
Part 3. Further Data preprocessing
Part 3. Further Data preprocessingPart 3. Further Data preprocessing
Part 3. Further Data preprocessing
 
Traffic sign detection via graph based ranking and segmentation
Traffic sign detection via graph based ranking and segmentationTraffic sign detection via graph based ranking and segmentation
Traffic sign detection via graph based ranking and segmentation
 
Miniproject final group 14
Miniproject final group 14Miniproject final group 14
Miniproject final group 14
 
crowd counting.pptx
crowd counting.pptxcrowd counting.pptx
crowd counting.pptx
 
VEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVMVEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVM
 
VEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVM VEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVM
 
VEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVMVEHICLE RECOGNITION USING VIBE AND SVM
VEHICLE RECOGNITION USING VIBE AND SVM
 
Vehicle Recognition Using VIBE and SVM
Vehicle Recognition Using VIBE and SVMVehicle Recognition Using VIBE and SVM
Vehicle Recognition Using VIBE and SVM
 
Robust and real time detection of
Robust and real time detection ofRobust and real time detection of
Robust and real time detection of
 
Introduction to Grad-CAM (complete version)
Introduction to Grad-CAM (complete version)Introduction to Grad-CAM (complete version)
Introduction to Grad-CAM (complete version)
 
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
IRJET- Digital Image Forgery Detection using Local Binary Patterns (LBP) and ...
 
Method of optimization of the fundamental matrix by technique speeded up rob...
Method of optimization of the fundamental matrix by technique  speeded up rob...Method of optimization of the fundamental matrix by technique  speeded up rob...
Method of optimization of the fundamental matrix by technique speeded up rob...
 
ANOVA and Fisher Criterion based Feature Selection for Lower Dimensional Univ...
ANOVA and Fisher Criterion based Feature Selection for Lower Dimensional Univ...ANOVA and Fisher Criterion based Feature Selection for Lower Dimensional Univ...
ANOVA and Fisher Criterion based Feature Selection for Lower Dimensional Univ...
 
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNNAutomatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
 
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
 
A New Approach to Linear Estimation Problem in Multiuser Massive MIMO Systems
A New Approach to Linear Estimation Problem in Multiuser Massive MIMO SystemsA New Approach to Linear Estimation Problem in Multiuser Massive MIMO Systems
A New Approach to Linear Estimation Problem in Multiuser Massive MIMO Systems
 
Graphics
GraphicsGraphics
Graphics
 
Estimation of Terrain Gradient Conditions & Obstacle Detection Using a Monocu...
Estimation of Terrain Gradient Conditions & Obstacle Detection Using a Monocu...Estimation of Terrain Gradient Conditions & Obstacle Detection Using a Monocu...
Estimation of Terrain Gradient Conditions & Obstacle Detection Using a Monocu...
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 

Kürzlich hochgeladen

AUDIENCE THEORY -CULTIVATION THEORY - GERBNER.pptx
AUDIENCE THEORY -CULTIVATION THEORY -  GERBNER.pptxAUDIENCE THEORY -CULTIVATION THEORY -  GERBNER.pptx
AUDIENCE THEORY -CULTIVATION THEORY - GERBNER.pptxiammrhaywood
 
AMERICAN LANGUAGE HUB_Level2_Student'sBook_Answerkey.pdf
AMERICAN LANGUAGE HUB_Level2_Student'sBook_Answerkey.pdfAMERICAN LANGUAGE HUB_Level2_Student'sBook_Answerkey.pdf
AMERICAN LANGUAGE HUB_Level2_Student'sBook_Answerkey.pdfphamnguyenenglishnb
 
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)lakshayb543
 
How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17Celine George
 
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxINTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxHumphrey A Beña
 
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxBarangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxCarlos105
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPCeline George
 
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdfInclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdfTechSoup
 
Culture Uniformity or Diversity IN SOCIOLOGY.pptx
Culture Uniformity or Diversity IN SOCIOLOGY.pptxCulture Uniformity or Diversity IN SOCIOLOGY.pptx
Culture Uniformity or Diversity IN SOCIOLOGY.pptxPoojaSen20
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Mark Reed
 
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Karra SKD Conference Presentation Revised.pptx
Karra SKD Conference Presentation Revised.pptxKarra SKD Conference Presentation Revised.pptx
Karra SKD Conference Presentation Revised.pptxAshokKarra1
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parentsnavabharathschool99
 
ENGLISH6-Q4-W3.pptxqurter our high choom
ENGLISH6-Q4-W3.pptxqurter our high choomENGLISH6-Q4-W3.pptxqurter our high choom
ENGLISH6-Q4-W3.pptxqurter our high choomnelietumpap1
 
ACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfSpandanaRallapalli
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management SystemChristalin Nelson
 
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...Nguyen Thanh Tu Collection
 
Keynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designKeynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designMIPLM
 
Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatYousafMalik24
 

Kürzlich hochgeladen (20)

AUDIENCE THEORY -CULTIVATION THEORY - GERBNER.pptx
AUDIENCE THEORY -CULTIVATION THEORY -  GERBNER.pptxAUDIENCE THEORY -CULTIVATION THEORY -  GERBNER.pptx
AUDIENCE THEORY -CULTIVATION THEORY - GERBNER.pptx
 
AMERICAN LANGUAGE HUB_Level2_Student'sBook_Answerkey.pdf
AMERICAN LANGUAGE HUB_Level2_Student'sBook_Answerkey.pdfAMERICAN LANGUAGE HUB_Level2_Student'sBook_Answerkey.pdf
AMERICAN LANGUAGE HUB_Level2_Student'sBook_Answerkey.pdf
 
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
 
How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17
 
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxINTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
 
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxBarangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERP
 
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdfInclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
 
Culture Uniformity or Diversity IN SOCIOLOGY.pptx
Culture Uniformity or Diversity IN SOCIOLOGY.pptxCulture Uniformity or Diversity IN SOCIOLOGY.pptx
Culture Uniformity or Diversity IN SOCIOLOGY.pptx
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)
 
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Kamla Market (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
 
Karra SKD Conference Presentation Revised.pptx
Karra SKD Conference Presentation Revised.pptxKarra SKD Conference Presentation Revised.pptx
Karra SKD Conference Presentation Revised.pptx
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parents
 
ENGLISH6-Q4-W3.pptxqurter our high choom
ENGLISH6-Q4-W3.pptxqurter our high choomENGLISH6-Q4-W3.pptxqurter our high choom
ENGLISH6-Q4-W3.pptxqurter our high choom
 
ACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdf
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management System
 
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
 
Raw materials used in Herbal Cosmetics.pptx
Raw materials used in Herbal Cosmetics.pptxRaw materials used in Herbal Cosmetics.pptx
Raw materials used in Herbal Cosmetics.pptx
 
Keynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designKeynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-design
 
Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice great
 

Presentation for korea multimedia(in english)

  • 1. Road Extraction fromRemote Sensing Images using SVM combined with FCM and MRF Jiawei Xu MULTIMEDIA PROCESSING LABORATORYDepartment of Electronic Engineering, Hallym UniversityE-mail: abyssecho@hallym.ac.kr
  • 2. Contents Introduction A brief review of previous methods Multi-times SVM Proposed algorithm Experimental results Performance evaluation Conclusion
  • 3. A brief review of previous methods Mathematical morphology Hough transform P-value segmentation Genetic algorithm Markov random field
  • 4. MATHEMATICAL MORPHOLOGY Flowchart of the proposed algorithm in mathematical morphology Original image 2D median filter open operator erosion & thinning Structure element:square, rectangle, ball, disk and line… Morphology: Erosion,dilation,openoperator, close operator
  • 5. Hough transform The Hough transform is most commonly used for the detection of regular curves such as lines, circles, ellipses, etc. Parameter setting in this thesis: Detection sensitivity: 0.15 The smaller the value is, the more features in the image will be considered as lines.
  • 6. P-value segmentation This figure shows the entire procedure of road extraction using P value segmentation. In figure (a) is an input image with some selected road parts on it, (b) is the cumulative gray-image histogram distribution , (c) is the result of P value segmentation. Application of some morphological operators such as region property, open operator to (c) results in (d), (e) is the road net image using thinning function, (f) shows the input image with the extracted road net overlaid on it
  • 7. P-value segmentation Post processing incurs an information loss. (a) is the original image, (b) is the P value diagram, (c) is the result of P value segmentation and (d) is the application of some morphological operators, such as region property, open operator based on (c). Compare with Genetic algorithm threshold segmentation Best fitness and best threshold with generation increase
  • 8. Markov random field Mean value and variance of selected area Original image MRF processing Speckle-like noise removal Road net
  • 9.
  • 10. belong to a family of generalized linear classifiers
  • 11. minimize the empirical classification error
  • 12.
  • 13. To slove such a problem is to import a nonlinear mapping function. If data sets in lower dimensional space are transformed to a higher dimensional space and successfully separated by a linear hyperplane as we showed in right figure ,we can utilize SVM.linear optimal separating hyper-plane nonlinear optimal separating hyper-plane
  • 14.
  • 15.
  • 16. Block diagram of our approach FCM classifer RS image SVM classifer MRF regularizer Road image
  • 17. FCM preprocessor Algorithm Calculate the fuzzy cluster centers by using and the new partition matrix by using Update to 3. Stop iteration if otherwise set and return to step 2 non-road-like non-road-like road-like image1 image 2 image 3 Partition into a collection of c fuzzy clusters with a list of c cluster centers V , such that and a partition matrix where is a numerical value in [0,1] that tells the degree to which the element belongs to the i-th cluster.
  • 18. FCM processing result (a) (b) (c) (d)(Road-like image used for further processing) (a)Original image(b)~(d)cluster 1,2,3
  • 19. Why we use FCM before SVM? Because of unbalanced data If class A(non-road) samples distributed over a large area Class B(road) samples distributed over a small area, Supposing we use SVM directly, the coefficient Matrix will be more close to the class that has a large distribution (which means hyper-plane is close to the large-distributed class because of the property of SVM) An extreme case is : one-class SVM(to detect the outlier) If samples amounts is very few and distributed in an extremely small area, SVM will recognize it as outlier,(in road extraction,for extreme case, road part will be neglected as the outlier)i.e., the hyperplane is unbalancedly assigned, which will lead to misclassification. FCM can display the each cluster features more obviously,alternatively speaking, enlarge the difference/distance between different clusters, which more or less decrease the misclassification rate.
  • 20. Test Images & Reference Models to evaluate our performance
  • 21. Performance evaluation criteria Complete: Correct: Rank distance: Quality : True positive (TP): both the processed model and the reference scene model classify the pixel belonging to road. True negative (TN): both the processed model and the reference scene model classify the pixel as belonging to the background. False positive (FP): processed model classifies the pixel as belonging to road, but the reference scene model classifies the pixel as belonging to the background. False negative (FN): the processed model classifies the pixel as belonging to the background, but the reference scene model classifies the pixel as belonging to road
  • 22.
  • 24.
  • 25. Experimental results We intentionally selected RS images with different characteristics:Beijing,shanghai,Vancouver… (ALL images from http://maps.google.com/) original images FCM-SVM processing MRF regularizer output images
  • 26. Multi-classes SVM(one against all) RS image road-class image lake-class image expectation value initialization classification of samples to be recognized by SVM plot result image
  • 27. Rank distance of K-means, SVM and our method (%) We do not list out morphology, Hough transform…because rank distance, quality percentage and other values are much lower than these approaches
  • 28. Quality percentage of K-means, SVM and proposed method (%)
  • 29. Comparison of FCM+K-means with FCM+SVM (a) Comparison of FCM+K-means with FCM+SVM (a) results of FCM clustering; (b) FCM followed by K-means clustring; (c) results of FCM followed by SVM. (b) (c) (a) (b) (c)
  • 31. GUI IMPLEMENTATION FOR ROAD Extraction: example 1
  • 34. Executable file contains DOS window Road.exe: Classified the functions two categories: One is for manual control methods and the other is for machine learning methods Meanwhile, we can also conceal DOS window
  • 35.
  • 36. Using FCM clustering to separate road-like cluster and the other clusters increases the SVM classification accuracy.
  • 37. We used MRF regularization to remove speckle-like noise then we could extract the fine road net.
  • 38.
  • 39. References [1] Stefan Hinz, “Automatic extraction of urban road networks from multi-view aerial imagery”, Technische University 2003 [2] VladmirVapnik, ”Statistical Learning Theory”, JOHN WILELY & SONS, Inc.1998 [3] Curt H.Davis, “An integrated system for automatic road mapping from high-resolution multi-spectral satellite imagery by information fusion”, Elsevier Inc. 2004 [4] Yairmoshe, “GUI with Matlab” Department of Electronic Engineering, Columbia University , May 2004. [5] http://maps.google.com/ [6] Yang Li, “A new validity function for fuzzy clustering”, School of mathematical sciences, Beijing normal university, 2005 [6] Xu Yong and Shaoguang Zhou, “Markov random field for road extraction applications in remote sensing images”, Department of Surveying and Mapping Engineering, Hohai University, 2008 [7] David M.McKeown ,“Performance evaluation for automatic feature extraction ”, Computer Science Department, Carnegie Mellon University 2000 [8] Patrick Perez, “Markov random fields and images”, Campus Beauileu, 1999 [9] Drs. Trani and Rahka, “MATLAB Graphic user interfaces(GUI) computer applications in civil engineering ”, Spring, 2000
  • 40. Other fields From 2009.01 to 2009.12 OpenCV1.0+VC6.0 OpenGL+VC6.0 OpenCV2.0+VS2008 Java3d on Myeclipse 7.5
  • 41. OpenCV1.0+VC6.0 Haarcascade Cascade: Stage1: Classifier11: Feature11 Classifier12: Feature12 ... Stage2: Classifier21: Feature21 CvHaarFeature, CvHaarClassifier, CvHaarStageClassifier, CvHaarClassifierCascade Boosted Haar------Tree structure Here, we import cvLoadHaarClassifierCascade
  • 42. OpenGL+VC6.0 3D effect by using Anaglyph glasses
  • 43. OpenCV2.0+Visual studio2008 Configuration(CMake setup…) Debug/Release Rebuild Options -> Projects and Solutions -> VC++ Directories Car plate recognition
  • 44. Soft matting Function: Image enhancement Boxfilter.m: Equivalent to the function: colfilt(imSrc, [2*r+1, 2*r+1], 'sliding', @sum) - But much faster Guidefilter.m % - guidance image: I % - filtering input image: p (should be a gray-scale/single channel image) % - local window radius: r % - regularization parameter: eps