SlideShare a Scribd company logo
1 of 35
SATELLITE IMAGE
CLASSIFICATION
USING K-NN, SVM,
AND DECISION TREE
1. I Gede B. P. (P66077042)
2. Umroh Dian S. (P66077050)
3. Iva N. (P66067021)
4. M. Irsyadi F. (P66067055)
The Outlines
• INTRODUCTION
• METHODOLOGY
• DATA AND PROCESSING
• RESULTS AND ANALYSIS
• CONCLUSION
2
1.
INTRODUCTION
4
Manual Method ?
High Resolution:
Pleiades Image
Low Resolution:
Landsat 8 Image
5
Pleiades
• K-NN
• SVM
• DT
Landsat 8
• K-NN
• SVM
• DT
The purposes:
To find the suitable method for each image
by considering the accuracy.
2.
METHODOLOGY
6
Proposed Flowchart
7
Proposed Flowchart
High Resolution:
Pleiades Image
Low Resolution:
Landsat 8 Image
8
9
K-NN
• K-Nearest-Neighbor algorithm is a method for
classifying objects based on closest training label in the
feature space.
• K value which gives the minimum error rate may be
selected for K-Nearest Neighbor classification.
• Distance function for K-Nearest-Neighbor is Euclidean
distance. It uses distance based comparison to assign
equal weight to each attribute. They can suffer from
poor accuracy when noisy and irrelevant attributes are
given.
• It is classifying the pattern by comparing a given test
pattern with training pattern that are similar to it. It is
widely used in pattern recognition.
(K-Nearest-Neighbor)
Sounds
Claws
?
K=3
10
SVM
• SVM classification uses different planes in space to
divide data points.
• It gains flexibility in the choice of threshold and handles
more input data very efficiently.
• Its performance and accuracy depend upon the
selection of hyper plane and kernel parameter.
• The goal of SVM Classification is to produce a model,
based on the training data, which will be able to predict
class labels of the test data accurately
(Support Vector Machine)
CupcakeMuffin
Cupcakes are topped with
creamy, delicious frosting.
Muffins may have a sugared
top or a very thin glaze.
VS
10
11
(Support Vector Machine)
SVM
Muffins
Cupcakes
12
(Support Vector Machine)
SVM
13
(Support Vector Machine)
SVM
Muffins
Cupcakes
14
DT
• Decision tree consist of mainly three parts: Partitioning
the nodes, find the terminal nodes and allocate class
label to terminal nodes.
• It is based on hierarchical rule. It handles high
dimensional data and representation of knowledge in
tree form which is easy to humans for understanding
purpose.
• When decision tree built, many of branches reflects
noise in the training pattern so, tree pruning attempts to
identify and remove such branches and improve the
accuracy of classification.
(Decision Tree)
3.
DATA AND
PROCESSING
15
16
Data
High Resolution
Low Resolution Landsat 8
North Taiwan ; 2018
Image size: 4300 x 4300 pixels
Pleiades
Colorado, USA ; 2012
Image size: 1300 x 1300 pixels
ENVI 5.3
Processing
High Resolution
Training and Testing Sample
Datasets
• The red color = building region
• The green color = vegetation region
• The blue color = road region
• The yellow color = concrete region
Land Cover Training Area (Segment)
Vegetation 1726
Building 486
Road 72
Concrete 420
17
SVM
Classification
DT
Classification
KNN
Classification
18Vegetation Building Road Concrete
19
High Resolution
Ground Truth
• Digitation
• Manual Interpretation
• Divided into 4 classes:
1.Building
2.Road
3.Vegetation
4.Concrete
Low Resolution
Training and Testing Sample
Datasets
• The red color = urban region
• The green color = vegetation region
• The blue color = water region
Land Cover Training Area (Segment)
Vegetation 11275
Water 98
Urban 10964
20
SVM
Classification
DT
Classification
KNN
Classification
21Vegetation Building Water
22
Low Resolution
Ground Truth
• Digitation
• Manual Interpretation
• Divided into 3 classes:
1.Urban Area
2.Vegetation
3.Water
4.
RESULTS AND
ANALYSIS
23
24
SVM
Classification
ROI
High Resolution
SVM
Overall Accuracy = 78.60%
Kappa Coefficient = 0.5967
Ground Truth (Percent)
Class Building Road Vegetation Concrete
Building 87.4 1.36 16.82 0.46
Road 0.07 91.47 7.55 0.78
Vegetation 11.74 5.04 74.59 2.41
Concrete 0.79 2.14 1.04 96.36
25
k-NN
Classification
ROI
High Resolution
k-NN
Overall Accuracy = 76.26%
Kappa Coefficient = 0.5673
Ground Truth (Percent)
Class Building Road Vegetation Concrete
Building 87.37 1.09 18.37 0.62
Road 0.24 93.56 8.58 0.81
Vegetation 11.12 2.92 71.09 2.36
Concrete 1.27 2.43 1.95 96.2
26
DT
Classification
ROI
High Resolution
DT
Overall Accuracy = 68.41%
Kappa Coefficient = 0.4294
Ground Truth (Percent)
Class Vegetation Road Building Concrete
Vegetation 68.86 6.97 10.79 4.01
Road 7.31 61.89 18.27 0.62
Building 23.75 27.4 68.12 0.12
Concrete 0.09 3.74 2.81 95.24
27
Ground Truth (Percent)
Class Vegetation Water Urban
Vegetation 97.22 0.09 50.42
Water 0.19 99.56 10.14
Urban 2.59 0.35 39.43
SVM
Classification
ROI
Low Resolution
SVM
Overall Accuracy = 83.30%
Kappa Coefficient = 0.7375
28
k-NN
Classification
ROI
Low Resolution
k-NN
Overall Accuracy = 82.34%
Kappa Coefficient = 0.7253
Ground Truth (Percent)
Class Vegetation Water Urban
Vegetation 92.87 0.07 46.53
Water 0.22 99.54 10.18
Urban 4.79 0.34 42.53
29
DT
Classification
ROI
Low Resolution
DT
Overall Accuracy = 59.08%
Kappa Coefficient = 0.4459
Ground Truth (Percent)
Class Water Urban Vegetation
Water 49.48 8.36 0.07
Urban 1.02 37.1 9.25
Vegetation 0.02 46.18 90.6
30
Accuracy Assessment and Comparisons
Overall Accuracy (%) SVM DT KNN
High Resolution 78.60 68.41 76.26
Low Resolution 83.30 59.08 82.34
In high resolution, the classification accuracy of SVM and DT were
significantly different. However, the classification accuracy of SVM
and KNN were not significantly different.
SVM always showed the most accurate results, followed by
Decision Tree and KNN.
31
0
10
20
30
40
50
60
70
80
90
0 1000 2000 3000
OverallAccuracy(%)
Training Sample
Comparing the Performance of
Training Sample
SVM
KNN
Training Sample Comparison
SVM has flexibility in choice of threshold than both method.
SVM K-NN
Training Data Overall Accuracy (%) Difference (%)
2704 78.6
2.24
1354 76.36
3.23
238 73.13
0.03157 73.16
Training Data Overall Accuracy (%) Difference (%)
2704 76.26
2.78
1354 73.48
7.82
238 65.66
11.56157 54.1
32
The Impact of Distance in Training Sample
Land Cover Training Area (Segment)
Vegetation 1726
Building 486
Road 72
Concrete 420
Land Cover Training Area (Segment)
Vegetation 77
Building 38
Road 4
Concrete 38
Classifier Method Overall Accuracy (%)
SVM 78.6
KNN 76.26
Classifier Method Overall Accuracy (%)
SVM 73.16
KNN 54.1
The distance of training sample have significant impact on the classification result.
The closest distance will produce a better result, especially on the KNN method.
5.
CONCLUSION
33
34
Conclusion
• The SVM method has best accuracy compared to the Decision
Tree and k-Nearest Neighbor methods.
• The value of Kappa coefficient in the SVM method has a high
value compared to both methods.
• The sample size of training samples has more impact on the
classification accuracy for KNN and DT than for SVM. In
addition, SVM has flexibility in choice of threshold than both
method.
• The distance in training sample affect on the classification
result. Especially in the KNN method, we can see the big
difference of overall accuracy based on the number of used
training data.
35

More Related Content

What's hot

Visual analysis and pattern recognition using gis and remote sensing techniqu...
Visual analysis and pattern recognition using gis and remote sensing techniqu...Visual analysis and pattern recognition using gis and remote sensing techniqu...
Visual analysis and pattern recognition using gis and remote sensing techniqu...Jaleann M McClurg MPH, CSPO, CSM, DTM
 
[G4]image deblurring, seeing the invisible
[G4]image deblurring, seeing the invisible[G4]image deblurring, seeing the invisible
[G4]image deblurring, seeing the invisibleNAVER D2
 
Multi criteria decision making in spatial data analysis
Multi criteria decision making in spatial data  analysisMulti criteria decision making in spatial data  analysis
Multi criteria decision making in spatial data analysisPreeti Tiwari
 
Image pre processing
Image pre processingImage pre processing
Image pre processingAshish Kumar
 
Digital image processing and interpretation
Digital image processing and interpretationDigital image processing and interpretation
Digital image processing and interpretationP.K. Mani
 
Image classification, remote sensing, P K MANI
Image classification, remote sensing, P K MANIImage classification, remote sensing, P K MANI
Image classification, remote sensing, P K MANIP.K. Mani
 
Digital image processing using matlab
Digital image processing using matlab Digital image processing using matlab
Digital image processing using matlab Amr Rashed
 
ILWIS 3.0 SUMMARY PRESENTATION
ILWIS 3.0 SUMMARY PRESENTATIONILWIS 3.0 SUMMARY PRESENTATION
ILWIS 3.0 SUMMARY PRESENTATIONmusadoto
 
Image Classification Techniques in GIS
Image Classification Techniques in GISImage Classification Techniques in GIS
Image Classification Techniques in GISSadia Rahat
 
Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th Place Solution
Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th Place SolutionKaggle Lyft Motion Prediction for Autonomous Vehicles 4th Place Solution
Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th Place SolutionPreferred Networks
 
PR-132: SSD: Single Shot MultiBox Detector
PR-132: SSD: Single Shot MultiBox DetectorPR-132: SSD: Single Shot MultiBox Detector
PR-132: SSD: Single Shot MultiBox DetectorJinwon Lee
 
Spatial enhancement techniques
Spatial enhancement techniquesSpatial enhancement techniques
Spatial enhancement techniquesAakanchaAnand
 
Iirs Remote sensing application in Urban Planning
Iirs Remote sensing application in Urban PlanningIirs Remote sensing application in Urban Planning
Iirs Remote sensing application in Urban PlanningTushar Dholakia
 
Image classification in remote sensing
Image classification in remote sensingImage classification in remote sensing
Image classification in remote sensingAlexander Decker
 
Image analysis basics and principles
Image analysis basics and principlesImage analysis basics and principles
Image analysis basics and principlesMohsin Siddique
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image ProcessingSahil Biswas
 
Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...
Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...
Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...Bayes Ahmed
 

What's hot (20)

Visual analysis and pattern recognition using gis and remote sensing techniqu...
Visual analysis and pattern recognition using gis and remote sensing techniqu...Visual analysis and pattern recognition using gis and remote sensing techniqu...
Visual analysis and pattern recognition using gis and remote sensing techniqu...
 
Gis
GisGis
Gis
 
[G4]image deblurring, seeing the invisible
[G4]image deblurring, seeing the invisible[G4]image deblurring, seeing the invisible
[G4]image deblurring, seeing the invisible
 
Multi criteria decision making in spatial data analysis
Multi criteria decision making in spatial data  analysisMulti criteria decision making in spatial data  analysis
Multi criteria decision making in spatial data analysis
 
Image pre processing
Image pre processingImage pre processing
Image pre processing
 
Digital image processing and interpretation
Digital image processing and interpretationDigital image processing and interpretation
Digital image processing and interpretation
 
Image classification, remote sensing, P K MANI
Image classification, remote sensing, P K MANIImage classification, remote sensing, P K MANI
Image classification, remote sensing, P K MANI
 
Digital image processing using matlab
Digital image processing using matlab Digital image processing using matlab
Digital image processing using matlab
 
ILWIS 3.0 SUMMARY PRESENTATION
ILWIS 3.0 SUMMARY PRESENTATIONILWIS 3.0 SUMMARY PRESENTATION
ILWIS 3.0 SUMMARY PRESENTATION
 
Remote Sensing
Remote SensingRemote Sensing
Remote Sensing
 
Image Classification Techniques in GIS
Image Classification Techniques in GISImage Classification Techniques in GIS
Image Classification Techniques in GIS
 
Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th Place Solution
Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th Place SolutionKaggle Lyft Motion Prediction for Autonomous Vehicles 4th Place Solution
Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th Place Solution
 
PR-132: SSD: Single Shot MultiBox Detector
PR-132: SSD: Single Shot MultiBox DetectorPR-132: SSD: Single Shot MultiBox Detector
PR-132: SSD: Single Shot MultiBox Detector
 
Gis
GisGis
Gis
 
Spatial enhancement techniques
Spatial enhancement techniquesSpatial enhancement techniques
Spatial enhancement techniques
 
Iirs Remote sensing application in Urban Planning
Iirs Remote sensing application in Urban PlanningIirs Remote sensing application in Urban Planning
Iirs Remote sensing application in Urban Planning
 
Image classification in remote sensing
Image classification in remote sensingImage classification in remote sensing
Image classification in remote sensing
 
Image analysis basics and principles
Image analysis basics and principlesImage analysis basics and principles
Image analysis basics and principles
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
 
Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...
Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...
Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...
 

Similar to Satellite Image Classification using Decision Tree, SVM and k-Nearest Neighbor

K- Nearest Neighbor Approach
K- Nearest Neighbor ApproachK- Nearest Neighbor Approach
K- Nearest Neighbor ApproachKumud Arora
 
Data Processing Using THEOS Satellite Imagery for Disaster Monitoring (Case S...
Data Processing Using THEOS Satellite Imagery for Disaster Monitoring (Case S...Data Processing Using THEOS Satellite Imagery for Disaster Monitoring (Case S...
Data Processing Using THEOS Satellite Imagery for Disaster Monitoring (Case S...NopphawanTamkuan
 
CAMCOS_final Presentation_Group2.pptx
CAMCOS_final Presentation_Group2.pptxCAMCOS_final Presentation_Group2.pptx
CAMCOS_final Presentation_Group2.pptxhuzaifaazam3
 
IGARSS2011-I-Ling.ppt
IGARSS2011-I-Ling.pptIGARSS2011-I-Ling.ppt
IGARSS2011-I-Ling.pptgrssieee
 
Trackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity CalorimeterTrackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity CalorimeterYousef Fadila
 
Do Fractional Norms and Quasinorms Help to Overcome the Curse of Dimensiona...
Do Fractional Norms and Quasinorms Help to Overcome the Curse of Dimensiona...Do Fractional Norms and Quasinorms Help to Overcome the Curse of Dimensiona...
Do Fractional Norms and Quasinorms Help to Overcome the Curse of Dimensiona...Alexander Gorban
 
TENSOR VOTING BASED BINARY CLASSIFIER
TENSOR VOTING BASED BINARY CLASSIFIERTENSOR VOTING BASED BINARY CLASSIFIER
TENSOR VOTING BASED BINARY CLASSIFIERcscpconf
 
Application of combined support vector machines in process fault diagnosis
Application of combined support vector machines in process fault diagnosisApplication of combined support vector machines in process fault diagnosis
Application of combined support vector machines in process fault diagnosisDr.Pooja Jain
 
SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)Reheman Baikejiang
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...MLconf
 
Validation Study of Dimensionality Reduction Impact on Breast Cancer Classifi...
Validation Study of Dimensionality Reduction Impact on Breast Cancer Classifi...Validation Study of Dimensionality Reduction Impact on Breast Cancer Classifi...
Validation Study of Dimensionality Reduction Impact on Breast Cancer Classifi...ijcsit
 
final_year_project
final_year_projectfinal_year_project
final_year_projectMALLIKA H.M
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer VisionSungjoon Choi
 
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...Pinaki Ranjan Sarkar
 
Compressed learning for time series classification
Compressed learning for time series classificationCompressed learning for time series classification
Compressed learning for time series classification學翰 施
 
Project presentation
Project presentationProject presentation
Project presentationMaham Sajid
 

Similar to Satellite Image Classification using Decision Tree, SVM and k-Nearest Neighbor (20)

K- Nearest Neighbor Approach
K- Nearest Neighbor ApproachK- Nearest Neighbor Approach
K- Nearest Neighbor Approach
 
Data Processing Using THEOS Satellite Imagery for Disaster Monitoring (Case S...
Data Processing Using THEOS Satellite Imagery for Disaster Monitoring (Case S...Data Processing Using THEOS Satellite Imagery for Disaster Monitoring (Case S...
Data Processing Using THEOS Satellite Imagery for Disaster Monitoring (Case S...
 
CAMCOS_final Presentation_Group2.pptx
CAMCOS_final Presentation_Group2.pptxCAMCOS_final Presentation_Group2.pptx
CAMCOS_final Presentation_Group2.pptx
 
IGARSS2011-I-Ling.ppt
IGARSS2011-I-Ling.pptIGARSS2011-I-Ling.ppt
IGARSS2011-I-Ling.ppt
 
Trackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity CalorimeterTrackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity Calorimeter
 
Do Fractional Norms and Quasinorms Help to Overcome the Curse of Dimensiona...
Do Fractional Norms and Quasinorms Help to Overcome the Curse of Dimensiona...Do Fractional Norms and Quasinorms Help to Overcome the Curse of Dimensiona...
Do Fractional Norms and Quasinorms Help to Overcome the Curse of Dimensiona...
 
TENSOR VOTING BASED BINARY CLASSIFIER
TENSOR VOTING BASED BINARY CLASSIFIERTENSOR VOTING BASED BINARY CLASSIFIER
TENSOR VOTING BASED BINARY CLASSIFIER
 
Lower back pain Regression models
Lower back pain Regression modelsLower back pain Regression models
Lower back pain Regression models
 
Application of combined support vector machines in process fault diagnosis
Application of combined support vector machines in process fault diagnosisApplication of combined support vector machines in process fault diagnosis
Application of combined support vector machines in process fault diagnosis
 
SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
 
Validation Study of Dimensionality Reduction Impact on Breast Cancer Classifi...
Validation Study of Dimensionality Reduction Impact on Breast Cancer Classifi...Validation Study of Dimensionality Reduction Impact on Breast Cancer Classifi...
Validation Study of Dimensionality Reduction Impact on Breast Cancer Classifi...
 
final_year_project
final_year_projectfinal_year_project
final_year_project
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer Vision
 
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
 
Compressed learning for time series classification
Compressed learning for time series classificationCompressed learning for time series classification
Compressed learning for time series classification
 
crowd counting.pptx
crowd counting.pptxcrowd counting.pptx
crowd counting.pptx
 
Cluster Analysis for Dummies
Cluster Analysis for DummiesCluster Analysis for Dummies
Cluster Analysis for Dummies
 
Project presentation
Project presentationProject presentation
Project presentation
 
K - Nearest neighbor ( KNN )
K - Nearest neighbor  ( KNN )K - Nearest neighbor  ( KNN )
K - Nearest neighbor ( KNN )
 

More from National Cheng Kung University

Accuracy assessment and 3D Mapping by Consumer Grade Spherical Camera
Accuracy assessment and 3D Mapping by Consumer Grade Spherical CameraAccuracy assessment and 3D Mapping by Consumer Grade Spherical Camera
Accuracy assessment and 3D Mapping by Consumer Grade Spherical CameraNational Cheng Kung University
 
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...National Cheng Kung University
 
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...National Cheng Kung University
 
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical CameraNational Cheng Kung University
 
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical CameraNational Cheng Kung University
 
Optimal Filtering with Kalman Filters and Smoothers Using AndroSensor IMU Data
Optimal Filtering with Kalman Filters and Smoothers Using AndroSensor IMU DataOptimal Filtering with Kalman Filters and Smoothers Using AndroSensor IMU Data
Optimal Filtering with Kalman Filters and Smoothers Using AndroSensor IMU DataNational Cheng Kung University
 
A Method of Mining Association Rules for Geographical Points of Interest
A Method of Mining Association Rules for Geographical Points of InterestA Method of Mining Association Rules for Geographical Points of Interest
A Method of Mining Association Rules for Geographical Points of InterestNational Cheng Kung University
 
Building classification model, tree model, confusion matrix and prediction ac...
Building classification model, tree model, confusion matrix and prediction ac...Building classification model, tree model, confusion matrix and prediction ac...
Building classification model, tree model, confusion matrix and prediction ac...National Cheng Kung University
 
Accuracy Analysis of Three-Dimensional Model Reconstructed by Spherical Video...
Accuracy Analysis of Three-Dimensional Model Reconstructed by Spherical Video...Accuracy Analysis of Three-Dimensional Model Reconstructed by Spherical Video...
Accuracy Analysis of Three-Dimensional Model Reconstructed by Spherical Video...National Cheng Kung University
 
Association Rule (Data Mining) - Frequent Itemset Generation, Closed Frequent...
Association Rule (Data Mining) - Frequent Itemset Generation, Closed Frequent...Association Rule (Data Mining) - Frequent Itemset Generation, Closed Frequent...
Association Rule (Data Mining) - Frequent Itemset Generation, Closed Frequent...National Cheng Kung University
 
The rotation matrix (DCM) and quaternion in Inertial Survey and Navigation Sy...
The rotation matrix (DCM) and quaternion in Inertial Survey and Navigation Sy...The rotation matrix (DCM) and quaternion in Inertial Survey and Navigation Sy...
The rotation matrix (DCM) and quaternion in Inertial Survey and Navigation Sy...National Cheng Kung University
 
SIFT/SURF can achieve scale, rotation and illumination invariant during image...
SIFT/SURF can achieve scale, rotation and illumination invariant during image...SIFT/SURF can achieve scale, rotation and illumination invariant during image...
SIFT/SURF can achieve scale, rotation and illumination invariant during image...National Cheng Kung University
 
3D reconstruction by photogrammetry and 4D deformation measurement
3D reconstruction by photogrammetry and 4D deformation measurement3D reconstruction by photogrammetry and 4D deformation measurement
3D reconstruction by photogrammetry and 4D deformation measurementNational Cheng Kung University
 

More from National Cheng Kung University (20)

Accuracy assessment and 3D Mapping by Consumer Grade Spherical Camera
Accuracy assessment and 3D Mapping by Consumer Grade Spherical CameraAccuracy assessment and 3D Mapping by Consumer Grade Spherical Camera
Accuracy assessment and 3D Mapping by Consumer Grade Spherical Camera
 
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
 
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
3D Rekonstruksi Bangunan Menggunakan Gambar Panorama Sebagai Upaya Untuk Miti...
 
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
 
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
3D Indoor and Outdoor Mapping from Point Cloud Generated by Spherical Camera
 
Handbook PPI Tainan Taiwan 2018
Handbook PPI Tainan Taiwan 2018Handbook PPI Tainan Taiwan 2018
Handbook PPI Tainan Taiwan 2018
 
Optimal Filtering with Kalman Filters and Smoothers Using AndroSensor IMU Data
Optimal Filtering with Kalman Filters and Smoothers Using AndroSensor IMU DataOptimal Filtering with Kalman Filters and Smoothers Using AndroSensor IMU Data
Optimal Filtering with Kalman Filters and Smoothers Using AndroSensor IMU Data
 
EKF and RTS smoother toolbox
EKF and RTS smoother toolboxEKF and RTS smoother toolbox
EKF and RTS smoother toolbox
 
Kalman Filter Basic
Kalman Filter BasicKalman Filter Basic
Kalman Filter Basic
 
A Method of Mining Association Rules for Geographical Points of Interest
A Method of Mining Association Rules for Geographical Points of InterestA Method of Mining Association Rules for Geographical Points of Interest
A Method of Mining Association Rules for Geographical Points of Interest
 
DSM Extraction from Pleiades Images Using RSP
DSM Extraction from Pleiades Images Using RSPDSM Extraction from Pleiades Images Using RSP
DSM Extraction from Pleiades Images Using RSP
 
Calibration of Inertial Sensor within Smartphone
Calibration of Inertial Sensor within SmartphoneCalibration of Inertial Sensor within Smartphone
Calibration of Inertial Sensor within Smartphone
 
Pengukuran GPS Menggunakan Trimble Secara Manual
Pengukuran GPS Menggunakan Trimble Secara ManualPengukuran GPS Menggunakan Trimble Secara Manual
Pengukuran GPS Menggunakan Trimble Secara Manual
 
Building classification model, tree model, confusion matrix and prediction ac...
Building classification model, tree model, confusion matrix and prediction ac...Building classification model, tree model, confusion matrix and prediction ac...
Building classification model, tree model, confusion matrix and prediction ac...
 
Accuracy Analysis of Three-Dimensional Model Reconstructed by Spherical Video...
Accuracy Analysis of Three-Dimensional Model Reconstructed by Spherical Video...Accuracy Analysis of Three-Dimensional Model Reconstructed by Spherical Video...
Accuracy Analysis of Three-Dimensional Model Reconstructed by Spherical Video...
 
Association Rule (Data Mining) - Frequent Itemset Generation, Closed Frequent...
Association Rule (Data Mining) - Frequent Itemset Generation, Closed Frequent...Association Rule (Data Mining) - Frequent Itemset Generation, Closed Frequent...
Association Rule (Data Mining) - Frequent Itemset Generation, Closed Frequent...
 
The rotation matrix (DCM) and quaternion in Inertial Survey and Navigation Sy...
The rotation matrix (DCM) and quaternion in Inertial Survey and Navigation Sy...The rotation matrix (DCM) and quaternion in Inertial Survey and Navigation Sy...
The rotation matrix (DCM) and quaternion in Inertial Survey and Navigation Sy...
 
SIFT/SURF can achieve scale, rotation and illumination invariant during image...
SIFT/SURF can achieve scale, rotation and illumination invariant during image...SIFT/SURF can achieve scale, rotation and illumination invariant during image...
SIFT/SURF can achieve scale, rotation and illumination invariant during image...
 
3D reconstruction by photogrammetry and 4D deformation measurement
3D reconstruction by photogrammetry and 4D deformation measurement3D reconstruction by photogrammetry and 4D deformation measurement
3D reconstruction by photogrammetry and 4D deformation measurement
 
Shadow Detection Using MatLAB
Shadow Detection Using MatLABShadow Detection Using MatLAB
Shadow Detection Using MatLAB
 

Recently uploaded

Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingrakeshbaidya232001
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024Mark Billinghurst
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxupamatechverse
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130Suhani Kapoor
 
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCollege Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Dr.Costas Sachpazis
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxpurnimasatapathy1234
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINESIVASHANKAR N
 
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxAsutosh Ranjan
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escortsranjana rawat
 
Internship report on mechanical engineering
Internship report on mechanical engineeringInternship report on mechanical engineering
Internship report on mechanical engineeringmalavadedarshan25
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSSIVASHANKAR N
 
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Dr.Costas Sachpazis
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerAnamika Sarkar
 

Recently uploaded (20)

Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptx
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
 
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCollege Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptx
 
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCRCall Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
 
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
 
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptx
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
 
Internship report on mechanical engineering
Internship report on mechanical engineeringInternship report on mechanical engineering
Internship report on mechanical engineering
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
 
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
 
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptxExploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
 

Satellite Image Classification using Decision Tree, SVM and k-Nearest Neighbor

  • 1. SATELLITE IMAGE CLASSIFICATION USING K-NN, SVM, AND DECISION TREE 1. I Gede B. P. (P66077042) 2. Umroh Dian S. (P66077050) 3. Iva N. (P66067021) 4. M. Irsyadi F. (P66067055)
  • 2. The Outlines • INTRODUCTION • METHODOLOGY • DATA AND PROCESSING • RESULTS AND ANALYSIS • CONCLUSION 2
  • 4. 4 Manual Method ? High Resolution: Pleiades Image Low Resolution: Landsat 8 Image
  • 5. 5 Pleiades • K-NN • SVM • DT Landsat 8 • K-NN • SVM • DT The purposes: To find the suitable method for each image by considering the accuracy.
  • 8. Proposed Flowchart High Resolution: Pleiades Image Low Resolution: Landsat 8 Image 8
  • 9. 9 K-NN • K-Nearest-Neighbor algorithm is a method for classifying objects based on closest training label in the feature space. • K value which gives the minimum error rate may be selected for K-Nearest Neighbor classification. • Distance function for K-Nearest-Neighbor is Euclidean distance. It uses distance based comparison to assign equal weight to each attribute. They can suffer from poor accuracy when noisy and irrelevant attributes are given. • It is classifying the pattern by comparing a given test pattern with training pattern that are similar to it. It is widely used in pattern recognition. (K-Nearest-Neighbor) Sounds Claws ? K=3
  • 10. 10 SVM • SVM classification uses different planes in space to divide data points. • It gains flexibility in the choice of threshold and handles more input data very efficiently. • Its performance and accuracy depend upon the selection of hyper plane and kernel parameter. • The goal of SVM Classification is to produce a model, based on the training data, which will be able to predict class labels of the test data accurately (Support Vector Machine) CupcakeMuffin Cupcakes are topped with creamy, delicious frosting. Muffins may have a sugared top or a very thin glaze. VS 10
  • 14. 14 DT • Decision tree consist of mainly three parts: Partitioning the nodes, find the terminal nodes and allocate class label to terminal nodes. • It is based on hierarchical rule. It handles high dimensional data and representation of knowledge in tree form which is easy to humans for understanding purpose. • When decision tree built, many of branches reflects noise in the training pattern so, tree pruning attempts to identify and remove such branches and improve the accuracy of classification. (Decision Tree)
  • 16. 16 Data High Resolution Low Resolution Landsat 8 North Taiwan ; 2018 Image size: 4300 x 4300 pixels Pleiades Colorado, USA ; 2012 Image size: 1300 x 1300 pixels ENVI 5.3 Processing
  • 17. High Resolution Training and Testing Sample Datasets • The red color = building region • The green color = vegetation region • The blue color = road region • The yellow color = concrete region Land Cover Training Area (Segment) Vegetation 1726 Building 486 Road 72 Concrete 420 17
  • 19. 19 High Resolution Ground Truth • Digitation • Manual Interpretation • Divided into 4 classes: 1.Building 2.Road 3.Vegetation 4.Concrete
  • 20. Low Resolution Training and Testing Sample Datasets • The red color = urban region • The green color = vegetation region • The blue color = water region Land Cover Training Area (Segment) Vegetation 11275 Water 98 Urban 10964 20
  • 22. 22 Low Resolution Ground Truth • Digitation • Manual Interpretation • Divided into 3 classes: 1.Urban Area 2.Vegetation 3.Water
  • 24. 24 SVM Classification ROI High Resolution SVM Overall Accuracy = 78.60% Kappa Coefficient = 0.5967 Ground Truth (Percent) Class Building Road Vegetation Concrete Building 87.4 1.36 16.82 0.46 Road 0.07 91.47 7.55 0.78 Vegetation 11.74 5.04 74.59 2.41 Concrete 0.79 2.14 1.04 96.36
  • 25. 25 k-NN Classification ROI High Resolution k-NN Overall Accuracy = 76.26% Kappa Coefficient = 0.5673 Ground Truth (Percent) Class Building Road Vegetation Concrete Building 87.37 1.09 18.37 0.62 Road 0.24 93.56 8.58 0.81 Vegetation 11.12 2.92 71.09 2.36 Concrete 1.27 2.43 1.95 96.2
  • 26. 26 DT Classification ROI High Resolution DT Overall Accuracy = 68.41% Kappa Coefficient = 0.4294 Ground Truth (Percent) Class Vegetation Road Building Concrete Vegetation 68.86 6.97 10.79 4.01 Road 7.31 61.89 18.27 0.62 Building 23.75 27.4 68.12 0.12 Concrete 0.09 3.74 2.81 95.24
  • 27. 27 Ground Truth (Percent) Class Vegetation Water Urban Vegetation 97.22 0.09 50.42 Water 0.19 99.56 10.14 Urban 2.59 0.35 39.43 SVM Classification ROI Low Resolution SVM Overall Accuracy = 83.30% Kappa Coefficient = 0.7375
  • 28. 28 k-NN Classification ROI Low Resolution k-NN Overall Accuracy = 82.34% Kappa Coefficient = 0.7253 Ground Truth (Percent) Class Vegetation Water Urban Vegetation 92.87 0.07 46.53 Water 0.22 99.54 10.18 Urban 4.79 0.34 42.53
  • 29. 29 DT Classification ROI Low Resolution DT Overall Accuracy = 59.08% Kappa Coefficient = 0.4459 Ground Truth (Percent) Class Water Urban Vegetation Water 49.48 8.36 0.07 Urban 1.02 37.1 9.25 Vegetation 0.02 46.18 90.6
  • 30. 30 Accuracy Assessment and Comparisons Overall Accuracy (%) SVM DT KNN High Resolution 78.60 68.41 76.26 Low Resolution 83.30 59.08 82.34 In high resolution, the classification accuracy of SVM and DT were significantly different. However, the classification accuracy of SVM and KNN were not significantly different. SVM always showed the most accurate results, followed by Decision Tree and KNN.
  • 31. 31 0 10 20 30 40 50 60 70 80 90 0 1000 2000 3000 OverallAccuracy(%) Training Sample Comparing the Performance of Training Sample SVM KNN Training Sample Comparison SVM has flexibility in choice of threshold than both method. SVM K-NN Training Data Overall Accuracy (%) Difference (%) 2704 78.6 2.24 1354 76.36 3.23 238 73.13 0.03157 73.16 Training Data Overall Accuracy (%) Difference (%) 2704 76.26 2.78 1354 73.48 7.82 238 65.66 11.56157 54.1
  • 32. 32 The Impact of Distance in Training Sample Land Cover Training Area (Segment) Vegetation 1726 Building 486 Road 72 Concrete 420 Land Cover Training Area (Segment) Vegetation 77 Building 38 Road 4 Concrete 38 Classifier Method Overall Accuracy (%) SVM 78.6 KNN 76.26 Classifier Method Overall Accuracy (%) SVM 73.16 KNN 54.1 The distance of training sample have significant impact on the classification result. The closest distance will produce a better result, especially on the KNN method.
  • 34. 34 Conclusion • The SVM method has best accuracy compared to the Decision Tree and k-Nearest Neighbor methods. • The value of Kappa coefficient in the SVM method has a high value compared to both methods. • The sample size of training samples has more impact on the classification accuracy for KNN and DT than for SVM. In addition, SVM has flexibility in choice of threshold than both method. • The distance in training sample affect on the classification result. Especially in the KNN method, we can see the big difference of overall accuracy based on the number of used training data.
  • 35. 35

Editor's Notes

  1. Example of k-NN classification. The test sample (green circle) should be classified either to the first class of blue squares or to the second class of red triangles. If k = 3 (solid line circle) it is assigned to the second class because there are 2 triangles and only 1 square inside the inner circle. If k = 5 (dashed line circle) it is assigned to the first class (3 squares vs. 2 triangles inside the outer circle).