Semi-Automatic Classification Algorithm: The differences between Minimum Distance, Maximum Likelihood, and Spectral Angle Mapper

Fatwa Ramdani
Geoenvironment, Earth Science, Grad. School of Science
Remote sensing e-course
Semi-Automatic Classification Algorithm: The
differences between Minimum Distance, Maximum
Likelihood, and Spectral Angle Mapper
Outline
• This course will focus in Semi-Automatic Classification
Algorithm: The differences between Minimum Distance,
Maximum Likelihood, and Spectral Angle Mapper based on
remotely-sensed data; Landsat 8 OLI. The methods how to
analyze and exploit the Landsat 8 OLI information for Land Use
mapping will be illustrated in QGIS open source software.
• In final section will be follow with the exercise and questions to
allow student expand their understanding.
Course Goal and Objectives
• Understand the concept of Semi-Automatic Classification
Algorithm
• Understand algorithm in QGIS open source software
• Understand the differences between Minimum Distance,
Maximum Likelihood, and Spectral Angel Mapper algorithm
Intended Audience
• University student with basic level of
knowledge in Remote Sensing studies
• Course Requirements:
– Internet access
– QuantumGIS software (http://www.qgis.org/en/site/forusers/download.html)
– Downloaded data
Semi-Automatic Classification Algorithm
General algorithm of imagery classification
Raw DN
Conversion into TOA
using DOS method
TOA
Band set
Knowledge of
the study area
Producing ROI
(sampling of training data)
Running Semi-Automatic
Classification
Land cover
classification
Accuracy
assessment
Statistic
calculation
Manual input
Minimum Distance
The minimum distance technique uses
the mean vectors of each endmember
and calculates the Euclidean distance
from each unknown pixel to the mean
vector for each class. All pixels are
classified to the nearest class unless a
standard deviation or distance threshold
is specified, in which case some pixels
may be unclassified if they do not meet
the selected criteria.
Reference
Richards, J.A., 1999, Remote Sensing Digital Image
Analysis, Springer-Verlag, Berlin, p. 240.
Maximum Likelihood
Maximum likelihood classification assumes
that the statistics for each class in each band
are normally distributed and calculates the
probability that a given pixel belongs to a
specific class. Unless you select a probability
threshold, all pixels are classified. Each pixel is
assigned to the class that has the highest
probability (that is, the maximum likelihood).
If the highest probability is smaller than a
threshold you specify, the pixel remains
unclassified.
Reference
Richards, J.A., 1999, Remote Sensing Digital Image Analysis,
Springer-Verlag, Berlin, p. 240.
Instead based on training class multispectral distance
measurements, the maximum likelihood decision rule
is based on probability.
The maximum likelihood procedure assumes that
each training class in each band are normally
distributed (Gaussian).
The probability of a pixel belonging to each of a
predefined set of X classes is calculated, and the pixel
is then assigned to the class for which the probability
is the highest.
Spectral Angle Mapper
Spectral Angle Mapper (SAM) is a physically-based spectral classification that uses an n-D angle to match pixels
to reference spectra. The algorithm determines the spectral similarity between two spectra by calculating the
angle between the spectra and treating them as vectors in a space with dimensionality equal to the number of
bands. This technique, when used on calibrated reflectance data, is relatively insensitive to illumination and
albedo effects. Endmember spectra used by SAM can come from ASCII files or spectral libraries, or you can
extract them directly from an image (as ROI average spectra). SAM compares the angle between the
endmember spectrum vector and each pixel vector in n-D space.
Small angles between the two spectrums indicate high similarity and high angles indicate low similarity. This
method is not affected by solar illumination factors, because the angle between the two vectors is independent
of vectors length.
SAM classification assumes reflectance data. However, if you use radiance data, the error is generally not
significant because the origin is still near zero.
Reference
Kruse, F. A., A. B. Lefkoff, J. B. Boardman, K. B. Heidebrecht, A. T. Shapiro, P. J. Barloon, and A. F. H. Goetz, 1993, “The Spectral
Image Processing System (SIPS) - Interactive Visualization and Analysis of Imaging spectrometer Data.” Remote Sensing of the
Environment, v. 44, p. 145 - 163.
Activities!
• Check your computer spec, if 64bit then install the WinPhython first
• Download QGIS and install the Semi-Automatic Classification Plugin, run
your QGIS and click Plugins – Manage and Install Plugins..
• Learn step-by-step the algorithm of Semi-Automatic Classification
• Compare the result between three different method!
Algorithm
Raw DN
Conversion into TOA
using DOS method
TOA
Band set
Knowledge of
the study area
Producing ROI
(sampling of training data)
Running Semi-Automatic
Classification
Land cover
classification
Accuracy
assessment
Statistic
calculation
Manual input
Exercise!
• Explore the DN and TOA values of different
land cover!
• Produce the scatter plot and signature plot of
land cover and analyse it!
Application
• Mapping tropical forest environment,
• Mapping wetland environment,
• Vegetation extraction in urban environment,
• Agricultural fields,
• Etc.
Result; RGB 543
Classification Result
Quiz?
• Which method is the best one? Why?
• What are the advantages and the
disadvantages of the each method?
• What is the difference between Land Use and
Land Cover?
Resources
• Kruse, F. A., A. B. Lefkoff, J. B. Boardman, K. B. Heidebrecht, A. T. Shapiro, P. J. Barloon, and A.
F. H. Goetz, 1993, “The Spectral Image Processing System (SIPS) - Interactive Visualization and
Analysis of Imaging spectrometer Data.” Remote Sensing of the Environment, v. 44, p. 145 -
163.
• Richards, J.A., 1999, Remote Sensing Digital Image Analysis, Springer-Verlag, Berlin, p. 240.
• http://fatwaramdani.wordpress.com/2014/06/26/land-use-classification-using-qgis/
Read more from Luca Congedo, the author of the Semi-Automatic Classification Plugin for QGIS,
here
• http://fromgistors.blogspot.pt/2014/06/land-cover-classification-using-SCP-3.html
Thank you!
Questions?
1 de 17

Recomendados

Spectral signatures por
Spectral signaturesSpectral signatures
Spectral signaturesKunal Rathod
14K visualizações14 slides
GIS & RS in Forest Mapping por
GIS & RS in Forest MappingGIS & RS in Forest Mapping
GIS & RS in Forest MappingKamlesh Kumar
7.9K visualizações15 slides
Application of remote sensing por
Application of remote sensingApplication of remote sensing
Application of remote sensingAnurag Kumar
24.9K visualizações31 slides
Remote sensing concept, history and principles por
Remote sensing  concept, history and principlesRemote sensing  concept, history and principles
Remote sensing concept, history and principlesAjay Singh Lodhi
1.4K visualizações32 slides
Interpolation por
InterpolationInterpolation
Interpolationseidmmd
992 visualizações4 slides
Spatial interpolation techniques por
Spatial interpolation techniquesSpatial interpolation techniques
Spatial interpolation techniquesManisha Shrivastava
7.7K visualizações22 slides

Mais conteúdo relacionado

Mais procurados

Hyperspectral Imaging por
Hyperspectral ImagingHyperspectral Imaging
Hyperspectral ImagingParikshith Beenaveni
6.1K visualizações20 slides
History of gis por
History of gisHistory of gis
History of gisEhtisham Wajid
1.7K visualizações10 slides
Role of electromagnetic Radiation in Remote Sensing por
Role of electromagnetic Radiation in  Remote SensingRole of electromagnetic Radiation in  Remote Sensing
Role of electromagnetic Radiation in Remote SensingNzar Braim
2.6K visualizações15 slides
Chapter 3: Remote sensing Technology por
Chapter 3: Remote sensing TechnologyChapter 3: Remote sensing Technology
Chapter 3: Remote sensing TechnologyShankar Gangaju
1.8K visualizações40 slides
Image classification and land cover mapping por
Image classification and land cover mappingImage classification and land cover mapping
Image classification and land cover mappingKabir Uddin
19K visualizações90 slides
A review of change detection techniques por
A review of change detection techniques A review of change detection techniques
A review of change detection techniques abhishek_bhatt
44K visualizações57 slides

Mais procurados(20)

Hyperspectral Imaging por Parikshith Beenaveni
Hyperspectral ImagingHyperspectral Imaging
Hyperspectral Imaging
Parikshith Beenaveni6.1K visualizações
History of gis por Ehtisham Wajid
History of gisHistory of gis
History of gis
Ehtisham Wajid1.7K visualizações
Role of electromagnetic Radiation in Remote Sensing por Nzar Braim
Role of electromagnetic Radiation in  Remote SensingRole of electromagnetic Radiation in  Remote Sensing
Role of electromagnetic Radiation in Remote Sensing
Nzar Braim2.6K visualizações
Chapter 3: Remote sensing Technology por Shankar Gangaju
Chapter 3: Remote sensing TechnologyChapter 3: Remote sensing Technology
Chapter 3: Remote sensing Technology
Shankar Gangaju1.8K visualizações
Image classification and land cover mapping por Kabir Uddin
Image classification and land cover mappingImage classification and land cover mapping
Image classification and land cover mapping
Kabir Uddin19K visualizações
A review of change detection techniques por abhishek_bhatt
A review of change detection techniques A review of change detection techniques
A review of change detection techniques
abhishek_bhatt44K visualizações
Thermal Remote Sensing por Rohit Kumar
Thermal Remote SensingThermal Remote Sensing
Thermal Remote Sensing
Rohit Kumar17.3K visualizações
Digital image processing and interpretation por P.K. Mani
Digital image processing and interpretationDigital image processing and interpretation
Digital image processing and interpretation
P.K. Mani14.5K visualizações
Remote Sensing Platforms and Sensors por Uday kumar Devalla
Remote Sensing Platforms and SensorsRemote Sensing Platforms and Sensors
Remote Sensing Platforms and Sensors
Uday kumar Devalla58.1K visualizações
Remote sensing-presentaion por Mouna Guru
Remote sensing-presentaionRemote sensing-presentaion
Remote sensing-presentaion
Mouna Guru7.7K visualizações
Optical remote sensing por Sumant Diwakar
Optical remote sensingOptical remote sensing
Optical remote sensing
Sumant Diwakar4.1K visualizações
Thermal remote sensing por Sakthivel R
Thermal remote sensingThermal remote sensing
Thermal remote sensing
Sakthivel R3K visualizações
Passive and active sensors por Vivek Srivastava
Passive and active sensorsPassive and active sensors
Passive and active sensors
Vivek Srivastava17.2K visualizações
Remote Sensing And GIS Application In Wetland Mapping por Swetha A
Remote Sensing And GIS Application In Wetland MappingRemote Sensing And GIS Application In Wetland Mapping
Remote Sensing And GIS Application In Wetland Mapping
Swetha A9.6K visualizações
Basics of Remote Sensing por Akash Tikhe
Basics of Remote SensingBasics of Remote Sensing
Basics of Remote Sensing
Akash Tikhe10.4K visualizações
WEB GIS AND WEB MAP.pptx por Asim Pt
WEB GIS AND WEB MAP.pptxWEB GIS AND WEB MAP.pptx
WEB GIS AND WEB MAP.pptx
Asim Pt1.1K visualizações
Introduction to aerial photography and photogrammetry.ppt por srinivas2036
Introduction to aerial photography and photogrammetry.pptIntroduction to aerial photography and photogrammetry.ppt
Introduction to aerial photography and photogrammetry.ppt
srinivas203641.6K visualizações
Sentinel 2 por Openmaps
Sentinel 2Sentinel 2
Sentinel 2
Openmaps1.4K visualizações

Destaque

Role of Remote sensing por
Role of Remote sensing Role of Remote sensing
Role of Remote sensing MOHTISHIM CH
344 visualizações15 slides
PCA and Classification por
PCA and ClassificationPCA and Classification
PCA and ClassificationFatwa Ramdani
6K visualizações21 slides
NOISE-ROBUST SPATIAL PREPROCESSING PRIOR TO ENDMEMBER EXTRACTION FROM HYPERSP... por
NOISE-ROBUST SPATIAL PREPROCESSING PRIOR TO ENDMEMBER EXTRACTION FROM HYPERSP...NOISE-ROBUST SPATIAL PREPROCESSING PRIOR TO ENDMEMBER EXTRACTION FROM HYPERSP...
NOISE-ROBUST SPATIAL PREPROCESSING PRIOR TO ENDMEMBER EXTRACTION FROM HYPERSP...grssieee
1.2K visualizações25 slides
Change Detection Dubai por
Change Detection DubaiChange Detection Dubai
Change Detection DubaiIpsit Dash
1.2K visualizações25 slides
Semi-supervised classification for natural language processing por
Semi-supervised classification for natural language processingSemi-supervised classification for natural language processing
Semi-supervised classification for natural language processingRushdi Shams
2.7K visualizações63 slides
Digital image classification22oct por
Digital image classification22octDigital image classification22oct
Digital image classification22octAleemuddin Abbasi
4.4K visualizações85 slides

Destaque(13)

Role of Remote sensing por MOHTISHIM CH
Role of Remote sensing Role of Remote sensing
Role of Remote sensing
MOHTISHIM CH344 visualizações
PCA and Classification por Fatwa Ramdani
PCA and ClassificationPCA and Classification
PCA and Classification
Fatwa Ramdani6K visualizações
NOISE-ROBUST SPATIAL PREPROCESSING PRIOR TO ENDMEMBER EXTRACTION FROM HYPERSP... por grssieee
NOISE-ROBUST SPATIAL PREPROCESSING PRIOR TO ENDMEMBER EXTRACTION FROM HYPERSP...NOISE-ROBUST SPATIAL PREPROCESSING PRIOR TO ENDMEMBER EXTRACTION FROM HYPERSP...
NOISE-ROBUST SPATIAL PREPROCESSING PRIOR TO ENDMEMBER EXTRACTION FROM HYPERSP...
grssieee1.2K visualizações
Change Detection Dubai por Ipsit Dash
Change Detection DubaiChange Detection Dubai
Change Detection Dubai
Ipsit Dash1.2K visualizações
Semi-supervised classification for natural language processing por Rushdi Shams
Semi-supervised classification for natural language processingSemi-supervised classification for natural language processing
Semi-supervised classification for natural language processing
Rushdi Shams2.7K visualizações
Digital image classification22oct por Aleemuddin Abbasi
Digital image classification22octDigital image classification22oct
Digital image classification22oct
Aleemuddin Abbasi4.4K visualizações
Image classification, remote sensing, P K MANI por P.K. Mani
Image classification, remote sensing, P K MANIImage classification, remote sensing, P K MANI
Image classification, remote sensing, P K MANI
P.K. Mani20.6K visualizações
Semi supervised learning por Ahmed Taha
Semi supervised learningSemi supervised learning
Semi supervised learning
Ahmed Taha1.5K visualizações
Use of remote sensing for land cover monitoring servir science applications por Kabir Uddin
Use of remote sensing for land cover monitoring servir science applicationsUse of remote sensing for land cover monitoring servir science applications
Use of remote sensing for land cover monitoring servir science applications
Kabir Uddin6.5K visualizações
A Brief Introduction to Remote Sensing Satellites por Alireza Rahimzadeganasl
A Brief Introduction to Remote Sensing Satellites A Brief Introduction to Remote Sensing Satellites
A Brief Introduction to Remote Sensing Satellites
Alireza Rahimzadeganasl8.7K visualizações
REMOTE SENSING por KANNAN
REMOTE SENSINGREMOTE SENSING
REMOTE SENSING
KANNAN 33K visualizações
Remote Sensing PPT por Amal Murali
Remote Sensing PPTRemote Sensing PPT
Remote Sensing PPT
Amal Murali223K visualizações
Disaster management ppt por Aniket Pingale
Disaster management pptDisaster management ppt
Disaster management ppt
Aniket Pingale995.2K visualizações

Similar a Semi-Automatic Classification Algorithm: The differences between Minimum Distance, Maximum Likelihood, and Spectral Angle Mapper

IEEE SIGHT Bombay section webinar talk on GIS & Remote Sensing-Introduction t... por
IEEE SIGHT Bombay section webinar talk on GIS & Remote Sensing-Introduction t...IEEE SIGHT Bombay section webinar talk on GIS & Remote Sensing-Introduction t...
IEEE SIGHT Bombay section webinar talk on GIS & Remote Sensing-Introduction t...AdityaAllamraju1
52 visualizações50 slides
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne... por
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...IOSR Journals
292 visualizações11 slides
B49010511 por
B49010511B49010511
B49010511IJERA Editor
301 visualizações7 slides
IRJET- Fusion of VNIR and SWIR Bands of Sentinel-2A Imagery por
IRJET- Fusion of VNIR and SWIR Bands of Sentinel-2A ImageryIRJET- Fusion of VNIR and SWIR Bands of Sentinel-2A Imagery
IRJET- Fusion of VNIR and SWIR Bands of Sentinel-2A ImageryIRJET Journal
12 visualizações5 slides
Abstract por
AbstractAbstract
AbstractIshitva Minocha
269 visualizações14 slides
JPM1407 Exposing Digital Image Forgeries by Illumination Color Classification por
JPM1407   Exposing Digital Image Forgeries by Illumination Color ClassificationJPM1407   Exposing Digital Image Forgeries by Illumination Color Classification
JPM1407 Exposing Digital Image Forgeries by Illumination Color Classificationchennaijp
463 visualizações6 slides

Similar a Semi-Automatic Classification Algorithm: The differences between Minimum Distance, Maximum Likelihood, and Spectral Angle Mapper(20)

IEEE SIGHT Bombay section webinar talk on GIS & Remote Sensing-Introduction t... por AdityaAllamraju1
IEEE SIGHT Bombay section webinar talk on GIS & Remote Sensing-Introduction t...IEEE SIGHT Bombay section webinar talk on GIS & Remote Sensing-Introduction t...
IEEE SIGHT Bombay section webinar talk on GIS & Remote Sensing-Introduction t...
AdityaAllamraju152 visualizações
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne... por IOSR Journals
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...
IOSR Journals292 visualizações
B49010511 por IJERA Editor
B49010511B49010511
B49010511
IJERA Editor301 visualizações
IRJET- Fusion of VNIR and SWIR Bands of Sentinel-2A Imagery por IRJET Journal
IRJET- Fusion of VNIR and SWIR Bands of Sentinel-2A ImageryIRJET- Fusion of VNIR and SWIR Bands of Sentinel-2A Imagery
IRJET- Fusion of VNIR and SWIR Bands of Sentinel-2A Imagery
IRJET Journal12 visualizações
Abstract por Ishitva Minocha
AbstractAbstract
Abstract
Ishitva Minocha269 visualizações
JPM1407 Exposing Digital Image Forgeries by Illumination Color Classification por chennaijp
JPM1407   Exposing Digital Image Forgeries by Illumination Color ClassificationJPM1407   Exposing Digital Image Forgeries by Illumination Color Classification
JPM1407 Exposing Digital Image Forgeries by Illumination Color Classification
chennaijp463 visualizações
Dn33686693 por IJERA Editor
Dn33686693Dn33686693
Dn33686693
IJERA Editor212 visualizações
Dn33686693 por IJERA Editor
Dn33686693Dn33686693
Dn33686693
IJERA Editor261 visualizações
Intro to Multitarget Tracking for CURVE por chenhm
Intro to Multitarget Tracking for CURVEIntro to Multitarget Tracking for CURVE
Intro to Multitarget Tracking for CURVE
chenhm1.1K visualizações
Unsupervised Building Extraction from High Resolution Satellite Images Irresp... por CSCJournals
Unsupervised Building Extraction from High Resolution Satellite Images Irresp...Unsupervised Building Extraction from High Resolution Satellite Images Irresp...
Unsupervised Building Extraction from High Resolution Satellite Images Irresp...
CSCJournals205 visualizações
Classification of Multi-date Image using NDVI values por ijsrd.com
Classification of Multi-date Image using NDVI valuesClassification of Multi-date Image using NDVI values
Classification of Multi-date Image using NDVI values
ijsrd.com522 visualizações
Satellite Image Classification using Decision Tree, SVM and k-Nearest Neighbor por National Cheng Kung University
Satellite Image Classification using Decision Tree, SVM and k-Nearest NeighborSatellite Image Classification using Decision Tree, SVM and k-Nearest Neighbor
Satellite Image Classification using Decision Tree, SVM and k-Nearest Neighbor
National Cheng Kung University607 visualizações
UHDMML.pps por butest
UHDMML.ppsUHDMML.pps
UHDMML.pps
butest386 visualizações
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ... por Pinaki Ranjan Sarkar
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 Sarkar1.4K visualizações
Irrera gold2010 por grssieee
Irrera gold2010Irrera gold2010
Irrera gold2010
grssieee293 visualizações
Super-Resolution of Multispectral Images por ijsrd.com
Super-Resolution of Multispectral ImagesSuper-Resolution of Multispectral Images
Super-Resolution of Multispectral Images
ijsrd.com396 visualizações
Digital Image Classification.pptx por Hline Win
Digital Image Classification.pptxDigital Image Classification.pptx
Digital Image Classification.pptx
Hline Win68 visualizações
Deep Learning’s Application in Radar Signal Data II por Yu Huang
Deep Learning’s Application in Radar Signal Data IIDeep Learning’s Application in Radar Signal Data II
Deep Learning’s Application in Radar Signal Data II
Yu Huang285 visualizações

Mais de Fatwa Ramdani

Remote sensing e course (Geohydrology) por
Remote sensing e course (Geohydrology)Remote sensing e course (Geohydrology)
Remote sensing e course (Geohydrology)Fatwa Ramdani
2.2K visualizações21 slides
Management bencana por
Management bencanaManagement bencana
Management bencanaFatwa Ramdani
503 visualizações36 slides
Yuk menulis por
Yuk menulisYuk menulis
Yuk menulisFatwa Ramdani
307 visualizações12 slides
Pelatihan menulis blog dan website por
Pelatihan menulis blog dan websitePelatihan menulis blog dan website
Pelatihan menulis blog dan websiteFatwa Ramdani
530 visualizações12 slides
Field excursion – the changes of old sendai por
Field excursion – the changes of old sendaiField excursion – the changes of old sendai
Field excursion – the changes of old sendaiFatwa Ramdani
691 visualizações22 slides
Could mount fuji erupt por
Could mount fuji eruptCould mount fuji erupt
Could mount fuji eruptFatwa Ramdani
389 visualizações73 slides

Mais de Fatwa Ramdani(7)

Remote sensing e course (Geohydrology) por Fatwa Ramdani
Remote sensing e course (Geohydrology)Remote sensing e course (Geohydrology)
Remote sensing e course (Geohydrology)
Fatwa Ramdani2.2K visualizações
Management bencana por Fatwa Ramdani
Management bencanaManagement bencana
Management bencana
Fatwa Ramdani503 visualizações
Yuk menulis por Fatwa Ramdani
Yuk menulisYuk menulis
Yuk menulis
Fatwa Ramdani307 visualizações
Pelatihan menulis blog dan website por Fatwa Ramdani
Pelatihan menulis blog dan websitePelatihan menulis blog dan website
Pelatihan menulis blog dan website
Fatwa Ramdani530 visualizações
Field excursion – the changes of old sendai por Fatwa Ramdani
Field excursion – the changes of old sendaiField excursion – the changes of old sendai
Field excursion – the changes of old sendai
Fatwa Ramdani691 visualizações
Could mount fuji erupt por Fatwa Ramdani
Could mount fuji eruptCould mount fuji erupt
Could mount fuji erupt
Fatwa Ramdani389 visualizações
Disaster management and recovery in northeast japan por Fatwa Ramdani
Disaster management and recovery in northeast japanDisaster management and recovery in northeast japan
Disaster management and recovery in northeast japan
Fatwa Ramdani723 visualizações

Último

REPRESENTATION - GAUNTLET.pptx por
REPRESENTATION - GAUNTLET.pptxREPRESENTATION - GAUNTLET.pptx
REPRESENTATION - GAUNTLET.pptxiammrhaywood
107 visualizações26 slides
The Value and Role of Media and Information Literacy in the Information Age a... por
The Value and Role of Media and Information Literacy in the Information Age a...The Value and Role of Media and Information Literacy in the Information Age a...
The Value and Role of Media and Information Literacy in the Information Age a...Naseej Academy أكاديمية نسيج
54 visualizações42 slides
Solar System and Galaxies.pptx por
Solar System and Galaxies.pptxSolar System and Galaxies.pptx
Solar System and Galaxies.pptxDrHafizKosar
94 visualizações26 slides
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB... por
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...Nguyen Thanh Tu Collection
73 visualizações113 slides
Jibachha publishing Textbook.docx por
Jibachha publishing Textbook.docxJibachha publishing Textbook.docx
Jibachha publishing Textbook.docxDrJibachhaSahVetphys
47 visualizações14 slides
MIXING OF PHARMACEUTICALS.pptx por
MIXING OF PHARMACEUTICALS.pptxMIXING OF PHARMACEUTICALS.pptx
MIXING OF PHARMACEUTICALS.pptxAnupkumar Sharma
82 visualizações35 slides

Último(20)

REPRESENTATION - GAUNTLET.pptx por iammrhaywood
REPRESENTATION - GAUNTLET.pptxREPRESENTATION - GAUNTLET.pptx
REPRESENTATION - GAUNTLET.pptx
iammrhaywood107 visualizações
Solar System and Galaxies.pptx por DrHafizKosar
Solar System and Galaxies.pptxSolar System and Galaxies.pptx
Solar System and Galaxies.pptx
DrHafizKosar94 visualizações
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB... por Nguyen Thanh Tu Collection
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...
Nguyen Thanh Tu Collection73 visualizações
Jibachha publishing Textbook.docx por DrJibachhaSahVetphys
Jibachha publishing Textbook.docxJibachha publishing Textbook.docx
Jibachha publishing Textbook.docx
DrJibachhaSahVetphys47 visualizações
MIXING OF PHARMACEUTICALS.pptx por Anupkumar Sharma
MIXING OF PHARMACEUTICALS.pptxMIXING OF PHARMACEUTICALS.pptx
MIXING OF PHARMACEUTICALS.pptx
Anupkumar Sharma82 visualizações
Structure and Functions of Cell.pdf por Nithya Murugan
Structure and Functions of Cell.pdfStructure and Functions of Cell.pdf
Structure and Functions of Cell.pdf
Nithya Murugan701 visualizações
Narration lesson plan por TARIQ KHAN
Narration lesson planNarration lesson plan
Narration lesson plan
TARIQ KHAN59 visualizações
CONTENTS.pptx por iguerendiain
CONTENTS.pptxCONTENTS.pptx
CONTENTS.pptx
iguerendiain57 visualizações
Monthly Information Session for MV Asterix (November) por Esquimalt MFRC
Monthly Information Session for MV Asterix (November)Monthly Information Session for MV Asterix (November)
Monthly Information Session for MV Asterix (November)
Esquimalt MFRC58 visualizações
11.30.23 Poverty and Inequality in America.pptx por mary850239
11.30.23 Poverty and Inequality in America.pptx11.30.23 Poverty and Inequality in America.pptx
11.30.23 Poverty and Inequality in America.pptx
mary850239167 visualizações
Classification of crude drugs.pptx por GayatriPatra14
Classification of crude drugs.pptxClassification of crude drugs.pptx
Classification of crude drugs.pptx
GayatriPatra1492 visualizações
Google solution challenge..pptx por ChitreshGyanani1
Google solution challenge..pptxGoogle solution challenge..pptx
Google solution challenge..pptx
ChitreshGyanani1135 visualizações
The Accursed House by Émile Gaboriau por DivyaSheta
The Accursed House  by Émile GaboriauThe Accursed House  by Émile Gaboriau
The Accursed House by Émile Gaboriau
DivyaSheta212 visualizações
On Killing a Tree.pptx por AncyTEnglish
On Killing a Tree.pptxOn Killing a Tree.pptx
On Killing a Tree.pptx
AncyTEnglish66 visualizações
Ch. 8 Political Party and Party System.pptx por Rommel Regala
Ch. 8 Political Party and Party System.pptxCh. 8 Political Party and Party System.pptx
Ch. 8 Political Party and Party System.pptx
Rommel Regala53 visualizações
Use of Probiotics in Aquaculture.pptx por AKSHAY MANDAL
Use of Probiotics in Aquaculture.pptxUse of Probiotics in Aquaculture.pptx
Use of Probiotics in Aquaculture.pptx
AKSHAY MANDAL104 visualizações
Ch. 7 Political Participation and Elections.pptx por Rommel Regala
Ch. 7 Political Participation and Elections.pptxCh. 7 Political Participation and Elections.pptx
Ch. 7 Political Participation and Elections.pptx
Rommel Regala105 visualizações
Create a Structure in VBNet.pptx por Breach_P
Create a Structure in VBNet.pptxCreate a Structure in VBNet.pptx
Create a Structure in VBNet.pptx
Breach_P75 visualizações
UNIDAD 3 6º C.MEDIO.pptx por MarcosRodriguezUcedo
UNIDAD 3 6º C.MEDIO.pptxUNIDAD 3 6º C.MEDIO.pptx
UNIDAD 3 6º C.MEDIO.pptx
MarcosRodriguezUcedo124 visualizações

Semi-Automatic Classification Algorithm: The differences between Minimum Distance, Maximum Likelihood, and Spectral Angle Mapper

  • 1. Fatwa Ramdani Geoenvironment, Earth Science, Grad. School of Science Remote sensing e-course Semi-Automatic Classification Algorithm: The differences between Minimum Distance, Maximum Likelihood, and Spectral Angle Mapper
  • 2. Outline • This course will focus in Semi-Automatic Classification Algorithm: The differences between Minimum Distance, Maximum Likelihood, and Spectral Angle Mapper based on remotely-sensed data; Landsat 8 OLI. The methods how to analyze and exploit the Landsat 8 OLI information for Land Use mapping will be illustrated in QGIS open source software. • In final section will be follow with the exercise and questions to allow student expand their understanding.
  • 3. Course Goal and Objectives • Understand the concept of Semi-Automatic Classification Algorithm • Understand algorithm in QGIS open source software • Understand the differences between Minimum Distance, Maximum Likelihood, and Spectral Angel Mapper algorithm
  • 4. Intended Audience • University student with basic level of knowledge in Remote Sensing studies • Course Requirements: – Internet access – QuantumGIS software (http://www.qgis.org/en/site/forusers/download.html) – Downloaded data
  • 5. Semi-Automatic Classification Algorithm General algorithm of imagery classification Raw DN Conversion into TOA using DOS method TOA Band set Knowledge of the study area Producing ROI (sampling of training data) Running Semi-Automatic Classification Land cover classification Accuracy assessment Statistic calculation Manual input
  • 6. Minimum Distance The minimum distance technique uses the mean vectors of each endmember and calculates the Euclidean distance from each unknown pixel to the mean vector for each class. All pixels are classified to the nearest class unless a standard deviation or distance threshold is specified, in which case some pixels may be unclassified if they do not meet the selected criteria. Reference Richards, J.A., 1999, Remote Sensing Digital Image Analysis, Springer-Verlag, Berlin, p. 240.
  • 7. Maximum Likelihood Maximum likelihood classification assumes that the statistics for each class in each band are normally distributed and calculates the probability that a given pixel belongs to a specific class. Unless you select a probability threshold, all pixels are classified. Each pixel is assigned to the class that has the highest probability (that is, the maximum likelihood). If the highest probability is smaller than a threshold you specify, the pixel remains unclassified. Reference Richards, J.A., 1999, Remote Sensing Digital Image Analysis, Springer-Verlag, Berlin, p. 240. Instead based on training class multispectral distance measurements, the maximum likelihood decision rule is based on probability. The maximum likelihood procedure assumes that each training class in each band are normally distributed (Gaussian). The probability of a pixel belonging to each of a predefined set of X classes is calculated, and the pixel is then assigned to the class for which the probability is the highest.
  • 8. Spectral Angle Mapper Spectral Angle Mapper (SAM) is a physically-based spectral classification that uses an n-D angle to match pixels to reference spectra. The algorithm determines the spectral similarity between two spectra by calculating the angle between the spectra and treating them as vectors in a space with dimensionality equal to the number of bands. This technique, when used on calibrated reflectance data, is relatively insensitive to illumination and albedo effects. Endmember spectra used by SAM can come from ASCII files or spectral libraries, or you can extract them directly from an image (as ROI average spectra). SAM compares the angle between the endmember spectrum vector and each pixel vector in n-D space. Small angles between the two spectrums indicate high similarity and high angles indicate low similarity. This method is not affected by solar illumination factors, because the angle between the two vectors is independent of vectors length. SAM classification assumes reflectance data. However, if you use radiance data, the error is generally not significant because the origin is still near zero. Reference Kruse, F. A., A. B. Lefkoff, J. B. Boardman, K. B. Heidebrecht, A. T. Shapiro, P. J. Barloon, and A. F. H. Goetz, 1993, “The Spectral Image Processing System (SIPS) - Interactive Visualization and Analysis of Imaging spectrometer Data.” Remote Sensing of the Environment, v. 44, p. 145 - 163.
  • 9. Activities! • Check your computer spec, if 64bit then install the WinPhython first • Download QGIS and install the Semi-Automatic Classification Plugin, run your QGIS and click Plugins – Manage and Install Plugins.. • Learn step-by-step the algorithm of Semi-Automatic Classification • Compare the result between three different method!
  • 10. Algorithm Raw DN Conversion into TOA using DOS method TOA Band set Knowledge of the study area Producing ROI (sampling of training data) Running Semi-Automatic Classification Land cover classification Accuracy assessment Statistic calculation Manual input
  • 11. Exercise! • Explore the DN and TOA values of different land cover! • Produce the scatter plot and signature plot of land cover and analyse it!
  • 12. Application • Mapping tropical forest environment, • Mapping wetland environment, • Vegetation extraction in urban environment, • Agricultural fields, • Etc.
  • 15. Quiz? • Which method is the best one? Why? • What are the advantages and the disadvantages of the each method? • What is the difference between Land Use and Land Cover?
  • 16. Resources • Kruse, F. A., A. B. Lefkoff, J. B. Boardman, K. B. Heidebrecht, A. T. Shapiro, P. J. Barloon, and A. F. H. Goetz, 1993, “The Spectral Image Processing System (SIPS) - Interactive Visualization and Analysis of Imaging spectrometer Data.” Remote Sensing of the Environment, v. 44, p. 145 - 163. • Richards, J.A., 1999, Remote Sensing Digital Image Analysis, Springer-Verlag, Berlin, p. 240. • http://fatwaramdani.wordpress.com/2014/06/26/land-use-classification-using-qgis/ Read more from Luca Congedo, the author of the Semi-Automatic Classification Plugin for QGIS, here • http://fromgistors.blogspot.pt/2014/06/land-cover-classification-using-SCP-3.html