SlideShare ist ein Scribd-Unternehmen logo
1 von 21
Downloaden Sie, um offline zu lesen
Remote sensing e-course
PCA and Classification Technique
Fatwa Ramdani
Geoenvironment, Earth Science, Grad. School of Science
Outline
• This course will focus in Principal Component Analysis and
Classification Technique based on remotely-sensed data, SPOT 6
& Landsat 8 OLI. The methods how to analyze and exploit the
SPOT 6 Landsat 8 OLI information for Land Use mapping will be
illustrated in GRASS 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 PCA
• Understand formula module function in open source software
• Understand the benefit of PCA in Classification Technique
Intended Audience
• University student with basic level of
knowledge in Remote Sensing studies
• Course Requirements:
–
–
–
–

Internet access
GRASS software (http://grass.osgeo.org/grass64/binary/mswindows/native/)
QuantumGIS software (http://www.qgis.org/en/site/forusers/download.html)
Download data here ()
1. What is SPOT6?
Launched September 9, 2012, by India's Polar Satellite Launch Vehicle. It is
run by Spot Image based in Toulouse, France. It was initiated by the CNES
(Centre national d'études spatiales – the French space agency) in the 1970s
and was developed in association with the SSTC (Belgian scientific, technical
and cultural services) and the Swedish National Space Board (SNSB).

Resources:
•

http://www.astrium-geo.com/en/143-spot-satellite-imagery
SPOT6 Bands and Products
PANCRO band: 1.5 m panchromatic (0.455 µm – 0.745 µm)
6 m multispectral, 4 bands:
• blue (0.455 µm – 0.525 µm)
• green (0.530 µm – 0.590 µm)
• red (0.625 µm – 0.695 µm)
• near-infrared (0.760 µm – 0.890 µm)
Primary
 Processing level closest to the image acquired by the sensor: it restores perfect collection conditions. The
sensor is placed in rectilinear geometry, the image is clear of any radiometric distortion.
 Optimal for clients familiar with satellite imagery processing techniques wishing to apply their own
production methods (orthorectification or 3D modeling for example).
Ortho
• Georeferenced image in Earth geometry, corrected from off-nadir acquisition and terrain effects.
• Optimal for simple and direct use of the image, and for immediate ingestion into a Geographic Information
System.
• The standard 3D model used for ground corrections is the worldwide Elevation30 dataset (also known as
Reference3D).
Principal Component Analysis (PCA)
is a dimensionality reduction technique used extensively in Remote Sensing studies
(e.g. in change detection studies, image enhancement tasks and more). PCA is in fact a
linear transformation applied on (usually) highly correlated multidimensional (e.g.
multispectral) data.
The input dimensions are transformed in a new coordinate system in which the
produced dimensions (called principal components) contain, in decreasing order, the
greatest variance related with unchanged landscape features. We can guided purely
by the statistical properties of the image itself. The new bands are called components.
PCA has two algebraic solutions:
• Eigenvectors of Covariance (or Correlation) of a given data matrix >> GRASS
• Singular Value Decomposition of a given data matrix
PCA & band ratio’s benefit in
classification
Classification based on the band ratio and subsequent
supervised classification has the possibility of producing the best
result if the spectra of LULC can be fully exploited (the reduction
of data without loss of information, prior to classification).
Resources:
• Lillesand, T. M., and R. W. Kiefer. 2000. Remote Sensing and Image Interpretation,
736. New York: John Wiley and Sons.
• Rogerson, P. A. 2002. “Change Detection Thresholds for Remotely Sensed Images.”
Journal of Geographical Systems 4: 85–97.
Activities!
• Import file using GRASS
• Explore basic statistics
• Displaying the data:
• Produce RGB composite image

• PCA
– Run i.pca module
– Analyze the result

• C
PCA Analysis (for Landsat 8 OLI)
PC has the most positive or negative contribution
i.pca input=B1,B2,B3,B4,B5,B7 output_prefix=PCA
•
•
•
•
•
•

PC1 2553.26 (-0.2998,-0.2313,-0.4177,-0.2342,-0.6702,-0.4221) [91.10%]
PC2 168.11 (-0.4841,-0.2400,-0.3196, 0.6894, 0.3382,-0.1276) [ 6.00%]
PC3 58.00 (-0.3717,-0.2467,-0.3222,-0.5897, 0.3657, 0.4645) [ 2.07%]
PC4 16.27 ( 0.1545, 0.0497,-0.3195, 0.3426,-0.4678, 0.7317) [ 0.58%]
PC5 6.27 (-0.6507, 0.0183, 0.6650, 0.0396,-0.2856, 0.2254) [ 0.22%]
PC6 0.92 ( 0.3005,-0.9084, 0.2743, 0.0572,-0.0494, 0.0596) [ 0.03%]
Eigen values, (vectors), and [percent importance]:

The band ratio derived from PC1 is B5/B2. Similarly, the results for PC2–PC3
lead to the choice of the ratios B1/B4, and B4/B7, respectively
PCA Analysis (continue for Landsat 8 OLI)
• Thus,
– PC_landsat_1= -0.2998*B1-0.2313*B2-0.4177*B3…
– PC_landsat_2=-0.4841*B1-0.2400*B2-0.3196B3…
– PC_landsat_3= -0.3717*B1-0.2467*B2-0.3222*B3…
How to evaluate percent of importance? Used eigenvalue;
2553.26/2553.26+168.11+58+ 16.27 + 6.27 +0.92=91.09%
PCA Analysis (continue for Landsat 8 OLI)
•

•

•

PC1 has the highest factor loading of -0.2313 from band 2 (blue), followed by band
4 (red), and then band 1 (coastal aerosol). Therefore, this component is suitable
for mapping coastal environment, wetland, and lake environment. Also capable of
differentiating soil and rock surfaces from vegetation
PC2 has the highest factor loading of 0.6894 from band 4 (red), followed by band 5
(NIR), and then band 7 (SWIR). This component can be termed a healthy (dense,
vigorous) vegetation component because healthy vegetation reflects highly in near
infrared and also some mid infrared energy except in the water absorption zones
in this region
PC3 has the highest factor from band 7 (SWIR), followed by band 5 (NIR), and
then band 2 (blue). PC3 can be termed a dark, dry land component due to the high
mid infrared factor loading. Separated land and water sharply. Band 7 has strong
water absorption region.
Exercise!
• Run i.pca for SPOT6!
i.pca input=spot1,spot2,spot3,spot4 output_prefix=pca.spot

1. Eigen values, (vectors), and [percent importance]:
2. Band Ratio:

?
LULC Classification
#We use the bands ratio result from PCA output
• i.group group=spot_group subgroup=spot_sub
input=pc_spot1,pc_spot2,pc_spot3
• i.cluster group=spot_group subgroup=spot_sub sigfile=urban classes=7
report=urban_report.txt
• remember name of file containing signatures: urban
• i.maxlik group=spot_group subgroup=spot_sub sigfile=spot
class=spot_class

#Converting raster to vector
• r.to.vect -s input=spot_class output=spot_class feature=area
Application
• Mapping coastal environment
– Mangrove forests
– Kelp forest in turbid water
– Submerged vegetation

• Mapping wetland environment
• Mineral exploration in arid environment
Resources
• http://www.crisp.nus.edu.sg/~research/tutorial/opt_int.htm
• http://www.astrium-geo.com/en/4594-spot-6-products
• https://dl.dropboxusercontent.com/u/4437062/CasalPascual_
Gema_TD_2012.pdf
• http://www.geocarto.com.hk/cgi-bin/pages1/sep04/p11.pdf
Result; RGB PC123

d.rgb red=pca.spot.1 green=pca.spot.2 blue=pca.spot.3
PCA; Vegetation and Urbanized Area
Classification Result
Quiz?
• Which bands has the most positive or negative
contribution from SPOT6?
• The band ratio derived from PC1 of SPOT6 is x.
Similarly, the results for PC2–PC3 lead to the choice
of the ratios y, and z. What is the band ratio of x, y,
and z?
• How to produce map pc_spot1, pc_spot2, and
pc_spot3 as band ratio of SPOT6?
Thank you!
Questions?

Weitere ähnliche Inhalte

Was ist angesagt?

Change detection using remote sensing and GIS
Change detection using remote sensing and GISChange detection using remote sensing and GIS
Change detection using remote sensing and GISTilok Chetri
 
Semi-Automatic Classification Algorithm: The differences between Minimum Dist...
Semi-Automatic Classification Algorithm: The differences between Minimum Dist...Semi-Automatic Classification Algorithm: The differences between Minimum Dist...
Semi-Automatic Classification Algorithm: The differences between Minimum Dist...Fatwa Ramdani
 
Applications of lidar technology
Applications of lidar technologyApplications of lidar technology
Applications of lidar technologySourabh Jain
 
Gis Geographical Information System Fundamentals
Gis Geographical Information System FundamentalsGis Geographical Information System Fundamentals
Gis Geographical Information System FundamentalsUroosa Samman
 
Network analysis in gis
Network analysis in gisNetwork analysis in gis
Network analysis in gisstudent
 
Landslide monitoring systems & techniques
Landslide monitoring systems & techniquesLandslide monitoring systems & techniques
Landslide monitoring systems & techniquesmaneeb
 
Landuse Classification from Satellite Imagery using Deep Learning
Landuse Classification from Satellite Imagery using Deep LearningLanduse Classification from Satellite Imagery using Deep Learning
Landuse Classification from Satellite Imagery using Deep LearningDataWorks Summit
 
Applications of gis
Applications of gisApplications of gis
Applications of gisPramoda Raj
 
Synthetic aperture radar
Synthetic aperture radar Synthetic aperture radar
Synthetic aperture radar Cigi Cletus
 
Spatial analysis and Analysis Tools
Spatial analysis and Analysis ToolsSpatial analysis and Analysis Tools
Spatial analysis and Analysis ToolsSwapnil Shrivastav
 
Remote Sensing: Principal Component Analysis
Remote Sensing: Principal Component AnalysisRemote Sensing: Principal Component Analysis
Remote Sensing: Principal Component AnalysisKamlesh Kumar
 
Digital image processing and interpretation
Digital image processing and interpretationDigital image processing and interpretation
Digital image processing and interpretationP.K. Mani
 
Exploring Spatial data in GIS Environment
Exploring Spatial data in GIS Environment Exploring Spatial data in GIS Environment
Exploring Spatial data in GIS Environment NAXA-Developers
 
Remote Sensing Data Acquisition,Scanning/Imaging systems
Remote Sensing Data Acquisition,Scanning/Imaging systemsRemote Sensing Data Acquisition,Scanning/Imaging systems
Remote Sensing Data Acquisition,Scanning/Imaging systemsdaniyal rustam
 
Atmospheric correction
Atmospheric correctionAtmospheric correction
Atmospheric correctionNirmal Kumar
 

Was ist angesagt? (20)

Change detection using remote sensing and GIS
Change detection using remote sensing and GISChange detection using remote sensing and GIS
Change detection using remote sensing and GIS
 
Semi-Automatic Classification Algorithm: The differences between Minimum Dist...
Semi-Automatic Classification Algorithm: The differences between Minimum Dist...Semi-Automatic Classification Algorithm: The differences between Minimum Dist...
Semi-Automatic Classification Algorithm: The differences between Minimum Dist...
 
Applications of lidar technology
Applications of lidar technologyApplications of lidar technology
Applications of lidar technology
 
Gis Geographical Information System Fundamentals
Gis Geographical Information System FundamentalsGis Geographical Information System Fundamentals
Gis Geographical Information System Fundamentals
 
Data Mining: Outlier analysis
Data Mining: Outlier analysisData Mining: Outlier analysis
Data Mining: Outlier analysis
 
Network analysis in gis
Network analysis in gisNetwork analysis in gis
Network analysis in gis
 
Landslide monitoring systems & techniques
Landslide monitoring systems & techniquesLandslide monitoring systems & techniques
Landslide monitoring systems & techniques
 
Landuse Classification from Satellite Imagery using Deep Learning
Landuse Classification from Satellite Imagery using Deep LearningLanduse Classification from Satellite Imagery using Deep Learning
Landuse Classification from Satellite Imagery using Deep Learning
 
Applications of gis
Applications of gisApplications of gis
Applications of gis
 
Landsat.pptx
Landsat.pptxLandsat.pptx
Landsat.pptx
 
GIS PPT
GIS PPTGIS PPT
GIS PPT
 
Synthetic aperture radar
Synthetic aperture radar Synthetic aperture radar
Synthetic aperture radar
 
Spatial analysis and Analysis Tools
Spatial analysis and Analysis ToolsSpatial analysis and Analysis Tools
Spatial analysis and Analysis Tools
 
Remote Sensing: Principal Component Analysis
Remote Sensing: Principal Component AnalysisRemote Sensing: Principal Component Analysis
Remote Sensing: Principal Component Analysis
 
Digital image processing and interpretation
Digital image processing and interpretationDigital image processing and interpretation
Digital image processing and interpretation
 
Exploring Spatial data in GIS Environment
Exploring Spatial data in GIS Environment Exploring Spatial data in GIS Environment
Exploring Spatial data in GIS Environment
 
Remote Sensing Data Acquisition,Scanning/Imaging systems
Remote Sensing Data Acquisition,Scanning/Imaging systemsRemote Sensing Data Acquisition,Scanning/Imaging systems
Remote Sensing Data Acquisition,Scanning/Imaging systems
 
LISS
LISSLISS
LISS
 
Atmospheric correction
Atmospheric correctionAtmospheric correction
Atmospheric correction
 
Manual of Remote Sensing
Manual of Remote SensingManual of Remote Sensing
Manual of Remote Sensing
 

Andere mochten auch

Practical implementation of pca on satellite images
Practical implementation of pca on satellite imagesPractical implementation of pca on satellite images
Practical implementation of pca on satellite imagesBhanu Pratap
 
Feature Based Image Classification by using Principal Component Analysis
Feature Based Image Classification by using Principal Component AnalysisFeature Based Image Classification by using Principal Component Analysis
Feature Based Image Classification by using Principal Component AnalysisIT Industry
 
Role of Remote sensing
Role of Remote sensing Role of Remote sensing
Role of Remote sensing MOHTISHIM CH
 
A review of change detection techniques
A review of change detection techniques A review of change detection techniques
A review of change detection techniques abhishek_bhatt
 
Remote Sensing PPT
Remote Sensing PPTRemote Sensing PPT
Remote Sensing PPTAmal Murali
 
Negobot: A conversational agent based on game theory for the detection of pae...
Negobot: A conversational agent based on game theory for the detection of pae...Negobot: A conversational agent based on game theory for the detection of pae...
Negobot: A conversational agent based on game theory for the detection of pae...Carlos Laorden
 
Game theory and 3G License Auction
Game theory and 3G License AuctionGame theory and 3G License Auction
Game theory and 3G License AuctionJames Jeffery
 
Cz ii tt_tsne_21022017_public
Cz ii tt_tsne_21022017_public Cz ii tt_tsne_21022017_public
Cz ii tt_tsne_21022017_public Grzegorz Gwardys
 
Change Detection Dubai
Change Detection DubaiChange Detection Dubai
Change Detection DubaiIpsit Dash
 
Feature Extraction for High Resolution Remote Sensing Image Classification us...
Feature Extraction for High Resolution Remote Sensing Image Classification us...Feature Extraction for High Resolution Remote Sensing Image Classification us...
Feature Extraction for High Resolution Remote Sensing Image Classification us...Simone Rossi
 
Application Of Game Theory
Application Of Game TheoryApplication Of Game Theory
Application Of Game TheoryMoonSoup, Inc.
 
Jan Mayer: Vaša konkurencia vás už sleduje - robte to lepšie!
Jan Mayer: Vaša konkurencia vás už sleduje - robte to lepšie!Jan Mayer: Vaša konkurencia vás už sleduje - robte to lepšie!
Jan Mayer: Vaša konkurencia vás už sleduje - robte to lepšie!Pricemania Academy
 
Spatio-temporal demographic classification of the Twitter users
Spatio-temporal demographic classification of the Twitter usersSpatio-temporal demographic classification of the Twitter users
Spatio-temporal demographic classification of the Twitter usersDr Muhammad Adnan
 
Hand movement controlled robotic vehicle
Hand movement controlled robotic vehicleHand movement controlled robotic vehicle
Hand movement controlled robotic vehicleMayank sankhla
 
Remote Sensing Lec 11
Remote Sensing Lec 11Remote Sensing Lec 11
Remote Sensing Lec 11polylsgiedx
 
Use of remote sensing for land cover monitoring servir science applications
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 applicationsKabir Uddin
 
Seminar(Pattern Recognition)
Seminar(Pattern Recognition)Seminar(Pattern Recognition)
Seminar(Pattern Recognition)anurodhsinha
 

Andere mochten auch (20)

Practical implementation of pca on satellite images
Practical implementation of pca on satellite imagesPractical implementation of pca on satellite images
Practical implementation of pca on satellite images
 
Feature Based Image Classification by using Principal Component Analysis
Feature Based Image Classification by using Principal Component AnalysisFeature Based Image Classification by using Principal Component Analysis
Feature Based Image Classification by using Principal Component Analysis
 
Role of Remote sensing
Role of Remote sensing Role of Remote sensing
Role of Remote sensing
 
A review of change detection techniques
A review of change detection techniques A review of change detection techniques
A review of change detection techniques
 
Remote Sensing PPT
Remote Sensing PPTRemote Sensing PPT
Remote Sensing PPT
 
Negobot: A conversational agent based on game theory for the detection of pae...
Negobot: A conversational agent based on game theory for the detection of pae...Negobot: A conversational agent based on game theory for the detection of pae...
Negobot: A conversational agent based on game theory for the detection of pae...
 
Game theory and 3G License Auction
Game theory and 3G License AuctionGame theory and 3G License Auction
Game theory and 3G License Auction
 
Cz ii tt_tsne_21022017_public
Cz ii tt_tsne_21022017_public Cz ii tt_tsne_21022017_public
Cz ii tt_tsne_21022017_public
 
Thesis defense
Thesis defenseThesis defense
Thesis defense
 
Change Detection Dubai
Change Detection DubaiChange Detection Dubai
Change Detection Dubai
 
Feature Extraction for High Resolution Remote Sensing Image Classification us...
Feature Extraction for High Resolution Remote Sensing Image Classification us...Feature Extraction for High Resolution Remote Sensing Image Classification us...
Feature Extraction for High Resolution Remote Sensing Image Classification us...
 
Game theory
Game theoryGame theory
Game theory
 
Application Of Game Theory
Application Of Game TheoryApplication Of Game Theory
Application Of Game Theory
 
Jan Mayer: Vaša konkurencia vás už sleduje - robte to lepšie!
Jan Mayer: Vaša konkurencia vás už sleduje - robte to lepšie!Jan Mayer: Vaša konkurencia vás už sleduje - robte to lepšie!
Jan Mayer: Vaša konkurencia vás už sleduje - robte to lepšie!
 
Spatio-temporal demographic classification of the Twitter users
Spatio-temporal demographic classification of the Twitter usersSpatio-temporal demographic classification of the Twitter users
Spatio-temporal demographic classification of the Twitter users
 
Hand movement controlled robotic vehicle
Hand movement controlled robotic vehicleHand movement controlled robotic vehicle
Hand movement controlled robotic vehicle
 
Csc446: Pattern Recognition
Csc446: Pattern Recognition Csc446: Pattern Recognition
Csc446: Pattern Recognition
 
Remote Sensing Lec 11
Remote Sensing Lec 11Remote Sensing Lec 11
Remote Sensing Lec 11
 
Use of remote sensing for land cover monitoring servir science applications
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
 
Seminar(Pattern Recognition)
Seminar(Pattern Recognition)Seminar(Pattern Recognition)
Seminar(Pattern Recognition)
 

Ähnlich wie Remote sensing e-course PCA and Classification Technique (40

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...
Unsupervised Building Extraction from High Resolution Satellite Images Irresp...CSCJournals
 
Image Classification For SAR Images using Modified ANN
Image Classification For SAR Images using Modified ANNImage Classification For SAR Images using Modified ANN
Image Classification For SAR Images using Modified ANNIRJET Journal
 
MediaEval 2016 - MLPBOON Predicting Media Interestingness System
MediaEval 2016 - MLPBOON Predicting Media Interestingness SystemMediaEval 2016 - MLPBOON Predicting Media Interestingness System
MediaEval 2016 - MLPBOON Predicting Media Interestingness Systemmultimediaeval
 
IRJET- Image Registration in GIS: A Survey
IRJET-  	  Image Registration in GIS: A SurveyIRJET-  	  Image Registration in GIS: A Survey
IRJET- Image Registration in GIS: A SurveyIRJET Journal
 
IRJET- Geological Boundary Detection for Satellite Images using AI Technique
IRJET- Geological Boundary Detection for Satellite Images using AI TechniqueIRJET- Geological Boundary Detection for Satellite Images using AI Technique
IRJET- Geological Boundary Detection for Satellite Images using AI TechniqueIRJET Journal
 
MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...
MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...
MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...multimediaeval
 
Final thesis presentation
Final thesis presentationFinal thesis presentation
Final thesis presentationPawan Singh
 
Automated features extraction from satellite images.
Automated features extraction from satellite images.Automated features extraction from satellite images.
Automated features extraction from satellite images.HimanshuGupta1081
 
Performance of RGB and L Base Supervised Classification Technique Using Multi...
Performance of RGB and L Base Supervised Classification Technique Using Multi...Performance of RGB and L Base Supervised Classification Technique Using Multi...
Performance of RGB and L Base Supervised Classification Technique Using Multi...IJERA Editor
 
Environmental Remote Sensing
 Environmental Remote Sensing  Environmental Remote Sensing
Environmental Remote Sensing Ghassan Hadi
 
Placing Images with Refined Language Models and Similarity Search with PCA-re...
Placing Images with Refined Language Models and Similarity Search with PCA-re...Placing Images with Refined Language Models and Similarity Search with PCA-re...
Placing Images with Refined Language Models and Similarity Search with PCA-re...Symeon Papadopoulos
 
Estimation, Detection & Comparison of Soil Nutrients using Matlab
Estimation, Detection & Comparison of Soil Nutrients using MatlabEstimation, Detection & Comparison of Soil Nutrients using Matlab
Estimation, Detection & Comparison of Soil Nutrients using MatlabIRJET Journal
 
CNN MODEL FOR TRAFFIC SIGN RECOGNITION
CNN MODEL FOR TRAFFIC SIGN RECOGNITIONCNN MODEL FOR TRAFFIC SIGN RECOGNITION
CNN MODEL FOR TRAFFIC SIGN RECOGNITIONIRJET Journal
 
Self Automated Rovers
Self Automated RoversSelf Automated Rovers
Self Automated RoversRutikBhoyar
 
Advances in Agricultural remote sensings
Advances in Agricultural remote sensingsAdvances in Agricultural remote sensings
Advances in Agricultural remote sensingsAyanDas644783
 
IRJET - Change Detection in Satellite Images using Convolutional Neural N...
IRJET -  	  Change Detection in Satellite Images using Convolutional Neural N...IRJET -  	  Change Detection in Satellite Images using Convolutional Neural N...
IRJET - Change Detection in Satellite Images using Convolutional Neural N...IRJET Journal
 
IRJET- 3D Object Recognition of Car Image Detection
IRJET-  	  3D Object Recognition of Car Image DetectionIRJET-  	  3D Object Recognition of Car Image Detection
IRJET- 3D Object Recognition of Car Image DetectionIRJET Journal
 
Astroimagej Image Processing And Photometric Extraction For Ultra-Precise As...
Astroimagej  Image Processing And Photometric Extraction For Ultra-Precise As...Astroimagej  Image Processing And Photometric Extraction For Ultra-Precise As...
Astroimagej Image Processing And Photometric Extraction For Ultra-Precise As...Andrew Parish
 

Ähnlich wie Remote sensing e-course PCA and Classification Technique (40 (20)

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...
Unsupervised Building Extraction from High Resolution Satellite Images Irresp...
 
Image Classification For SAR Images using Modified ANN
Image Classification For SAR Images using Modified ANNImage Classification For SAR Images using Modified ANN
Image Classification For SAR Images using Modified ANN
 
MediaEval 2016 - MLPBOON Predicting Media Interestingness System
MediaEval 2016 - MLPBOON Predicting Media Interestingness SystemMediaEval 2016 - MLPBOON Predicting Media Interestingness System
MediaEval 2016 - MLPBOON Predicting Media Interestingness System
 
IRJET- Image Registration in GIS: A Survey
IRJET-  	  Image Registration in GIS: A SurveyIRJET-  	  Image Registration in GIS: A Survey
IRJET- Image Registration in GIS: A Survey
 
IRJET- Geological Boundary Detection for Satellite Images using AI Technique
IRJET- Geological Boundary Detection for Satellite Images using AI TechniqueIRJET- Geological Boundary Detection for Satellite Images using AI Technique
IRJET- Geological Boundary Detection for Satellite Images using AI Technique
 
MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...
MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...
MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...
 
Final thesis presentation
Final thesis presentationFinal thesis presentation
Final thesis presentation
 
Automated features extraction from satellite images.
Automated features extraction from satellite images.Automated features extraction from satellite images.
Automated features extraction from satellite images.
 
Performance of RGB and L Base Supervised Classification Technique Using Multi...
Performance of RGB and L Base Supervised Classification Technique Using Multi...Performance of RGB and L Base Supervised Classification Technique Using Multi...
Performance of RGB and L Base Supervised Classification Technique Using Multi...
 
GIS Presentation.pptx
GIS Presentation.pptxGIS Presentation.pptx
GIS Presentation.pptx
 
Environmental Remote Sensing
 Environmental Remote Sensing  Environmental Remote Sensing
Environmental Remote Sensing
 
Placing Images with Refined Language Models and Similarity Search with PCA-re...
Placing Images with Refined Language Models and Similarity Search with PCA-re...Placing Images with Refined Language Models and Similarity Search with PCA-re...
Placing Images with Refined Language Models and Similarity Search with PCA-re...
 
Estimation, Detection & Comparison of Soil Nutrients using Matlab
Estimation, Detection & Comparison of Soil Nutrients using MatlabEstimation, Detection & Comparison of Soil Nutrients using Matlab
Estimation, Detection & Comparison of Soil Nutrients using Matlab
 
vegetation analysis
vegetation analysisvegetation analysis
vegetation analysis
 
CNN MODEL FOR TRAFFIC SIGN RECOGNITION
CNN MODEL FOR TRAFFIC SIGN RECOGNITIONCNN MODEL FOR TRAFFIC SIGN RECOGNITION
CNN MODEL FOR TRAFFIC SIGN RECOGNITION
 
Self Automated Rovers
Self Automated RoversSelf Automated Rovers
Self Automated Rovers
 
Advances in Agricultural remote sensings
Advances in Agricultural remote sensingsAdvances in Agricultural remote sensings
Advances in Agricultural remote sensings
 
IRJET - Change Detection in Satellite Images using Convolutional Neural N...
IRJET -  	  Change Detection in Satellite Images using Convolutional Neural N...IRJET -  	  Change Detection in Satellite Images using Convolutional Neural N...
IRJET - Change Detection in Satellite Images using Convolutional Neural N...
 
IRJET- 3D Object Recognition of Car Image Detection
IRJET-  	  3D Object Recognition of Car Image DetectionIRJET-  	  3D Object Recognition of Car Image Detection
IRJET- 3D Object Recognition of Car Image Detection
 
Astroimagej Image Processing And Photometric Extraction For Ultra-Precise As...
Astroimagej  Image Processing And Photometric Extraction For Ultra-Precise As...Astroimagej  Image Processing And Photometric Extraction For Ultra-Precise As...
Astroimagej Image Processing And Photometric Extraction For Ultra-Precise As...
 

Mehr von Fatwa Ramdani

Remote sensing e course (Geohydrology)
Remote sensing e course (Geohydrology)Remote sensing e course (Geohydrology)
Remote sensing e course (Geohydrology)Fatwa Ramdani
 
Pelatihan menulis blog dan website
Pelatihan menulis blog dan websitePelatihan menulis blog dan website
Pelatihan menulis blog dan websiteFatwa Ramdani
 
Field excursion – the changes of old sendai
Field excursion – the changes of old sendaiField excursion – the changes of old sendai
Field excursion – the changes of old sendaiFatwa Ramdani
 
Could mount fuji erupt
Could mount fuji eruptCould mount fuji erupt
Could mount fuji eruptFatwa Ramdani
 
Disaster management and recovery in northeast japan
Disaster management and recovery in northeast japanDisaster management and recovery in northeast japan
Disaster management and recovery in northeast japanFatwa Ramdani
 

Mehr von Fatwa Ramdani (7)

Remote sensing e course (Geohydrology)
Remote sensing e course (Geohydrology)Remote sensing e course (Geohydrology)
Remote sensing e course (Geohydrology)
 
Management bencana
Management bencanaManagement bencana
Management bencana
 
Yuk menulis
Yuk menulisYuk menulis
Yuk menulis
 
Pelatihan menulis blog dan website
Pelatihan menulis blog dan websitePelatihan menulis blog dan website
Pelatihan menulis blog dan website
 
Field excursion – the changes of old sendai
Field excursion – the changes of old sendaiField excursion – the changes of old sendai
Field excursion – the changes of old sendai
 
Could mount fuji erupt
Could mount fuji eruptCould mount fuji erupt
Could mount fuji erupt
 
Disaster management and recovery in northeast japan
Disaster management and recovery in northeast japanDisaster management and recovery in northeast japan
Disaster management and recovery in northeast japan
 

Kürzlich hochgeladen

Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfPatidar M
 
How to Manage Buy 3 Get 1 Free in Odoo 17
How to Manage Buy 3 Get 1 Free in Odoo 17How to Manage Buy 3 Get 1 Free in Odoo 17
How to Manage Buy 3 Get 1 Free in Odoo 17Celine George
 
ESP 4-EDITED.pdfmmcncncncmcmmnmnmncnmncmnnjvnnv
ESP 4-EDITED.pdfmmcncncncmcmmnmnmncnmncmnnjvnnvESP 4-EDITED.pdfmmcncncncmcmmnmnmncnmncmnnjvnnv
ESP 4-EDITED.pdfmmcncncncmcmmnmnmncnmncmnnjvnnvRicaMaeCastro1
 
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQ-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQuiz Club NITW
 
Indexing Structures in Database Management system.pdf
Indexing Structures in Database Management system.pdfIndexing Structures in Database Management system.pdf
Indexing Structures in Database Management system.pdfChristalin Nelson
 
Beauty Amidst the Bytes_ Unearthing Unexpected Advantages of the Digital Wast...
Beauty Amidst the Bytes_ Unearthing Unexpected Advantages of the Digital Wast...Beauty Amidst the Bytes_ Unearthing Unexpected Advantages of the Digital Wast...
Beauty Amidst the Bytes_ Unearthing Unexpected Advantages of the Digital Wast...DhatriParmar
 
MS4 level being good citizen -imperative- (1) (1).pdf
MS4 level   being good citizen -imperative- (1) (1).pdfMS4 level   being good citizen -imperative- (1) (1).pdf
MS4 level being good citizen -imperative- (1) (1).pdfMr Bounab Samir
 
BIOCHEMISTRY-CARBOHYDRATE METABOLISM CHAPTER 2.pptx
BIOCHEMISTRY-CARBOHYDRATE METABOLISM CHAPTER 2.pptxBIOCHEMISTRY-CARBOHYDRATE METABOLISM CHAPTER 2.pptx
BIOCHEMISTRY-CARBOHYDRATE METABOLISM CHAPTER 2.pptxSayali Powar
 
Mythology Quiz-4th April 2024, Quiz Club NITW
Mythology Quiz-4th April 2024, Quiz Club NITWMythology Quiz-4th April 2024, Quiz Club NITW
Mythology Quiz-4th April 2024, Quiz Club NITWQuiz Club NITW
 
Textual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSTextual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSMae Pangan
 
Concurrency Control in Database Management system
Concurrency Control in Database Management systemConcurrency Control in Database Management system
Concurrency Control in Database Management systemChristalin Nelson
 
4.11.24 Poverty and Inequality in America.pptx
4.11.24 Poverty and Inequality in America.pptx4.11.24 Poverty and Inequality in America.pptx
4.11.24 Poverty and Inequality in America.pptxmary850239
 
How to Make a Duplicate of Your Odoo 17 Database
How to Make a Duplicate of Your Odoo 17 DatabaseHow to Make a Duplicate of Your Odoo 17 Database
How to Make a Duplicate of Your Odoo 17 DatabaseCeline George
 
4.11.24 Mass Incarceration and the New Jim Crow.pptx
4.11.24 Mass Incarceration and the New Jim Crow.pptx4.11.24 Mass Incarceration and the New Jim Crow.pptx
4.11.24 Mass Incarceration and the New Jim Crow.pptxmary850239
 
ICS 2208 Lecture Slide Notes for Topic 6
ICS 2208 Lecture Slide Notes for Topic 6ICS 2208 Lecture Slide Notes for Topic 6
ICS 2208 Lecture Slide Notes for Topic 6Vanessa Camilleri
 
Oppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and FilmOppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and FilmStan Meyer
 
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...Nguyen Thanh Tu Collection
 
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDecoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDhatriParmar
 

Kürzlich hochgeladen (20)

Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdf
 
How to Manage Buy 3 Get 1 Free in Odoo 17
How to Manage Buy 3 Get 1 Free in Odoo 17How to Manage Buy 3 Get 1 Free in Odoo 17
How to Manage Buy 3 Get 1 Free in Odoo 17
 
ESP 4-EDITED.pdfmmcncncncmcmmnmnmncnmncmnnjvnnv
ESP 4-EDITED.pdfmmcncncncmcmmnmnmncnmncmnnjvnnvESP 4-EDITED.pdfmmcncncncmcmmnmnmncnmncmnnjvnnv
ESP 4-EDITED.pdfmmcncncncmcmmnmnmncnmncmnnjvnnv
 
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQ-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
 
Indexing Structures in Database Management system.pdf
Indexing Structures in Database Management system.pdfIndexing Structures in Database Management system.pdf
Indexing Structures in Database Management system.pdf
 
Beauty Amidst the Bytes_ Unearthing Unexpected Advantages of the Digital Wast...
Beauty Amidst the Bytes_ Unearthing Unexpected Advantages of the Digital Wast...Beauty Amidst the Bytes_ Unearthing Unexpected Advantages of the Digital Wast...
Beauty Amidst the Bytes_ Unearthing Unexpected Advantages of the Digital Wast...
 
Paradigm shift in nursing research by RS MEHTA
Paradigm shift in nursing research by RS MEHTAParadigm shift in nursing research by RS MEHTA
Paradigm shift in nursing research by RS MEHTA
 
MS4 level being good citizen -imperative- (1) (1).pdf
MS4 level   being good citizen -imperative- (1) (1).pdfMS4 level   being good citizen -imperative- (1) (1).pdf
MS4 level being good citizen -imperative- (1) (1).pdf
 
BIOCHEMISTRY-CARBOHYDRATE METABOLISM CHAPTER 2.pptx
BIOCHEMISTRY-CARBOHYDRATE METABOLISM CHAPTER 2.pptxBIOCHEMISTRY-CARBOHYDRATE METABOLISM CHAPTER 2.pptx
BIOCHEMISTRY-CARBOHYDRATE METABOLISM CHAPTER 2.pptx
 
Mythology Quiz-4th April 2024, Quiz Club NITW
Mythology Quiz-4th April 2024, Quiz Club NITWMythology Quiz-4th April 2024, Quiz Club NITW
Mythology Quiz-4th April 2024, Quiz Club NITW
 
Textual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSTextual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHS
 
Concurrency Control in Database Management system
Concurrency Control in Database Management systemConcurrency Control in Database Management system
Concurrency Control in Database Management system
 
4.11.24 Poverty and Inequality in America.pptx
4.11.24 Poverty and Inequality in America.pptx4.11.24 Poverty and Inequality in America.pptx
4.11.24 Poverty and Inequality in America.pptx
 
How to Make a Duplicate of Your Odoo 17 Database
How to Make a Duplicate of Your Odoo 17 DatabaseHow to Make a Duplicate of Your Odoo 17 Database
How to Make a Duplicate of Your Odoo 17 Database
 
4.11.24 Mass Incarceration and the New Jim Crow.pptx
4.11.24 Mass Incarceration and the New Jim Crow.pptx4.11.24 Mass Incarceration and the New Jim Crow.pptx
4.11.24 Mass Incarceration and the New Jim Crow.pptx
 
prashanth updated resume 2024 for Teaching Profession
prashanth updated resume 2024 for Teaching Professionprashanth updated resume 2024 for Teaching Profession
prashanth updated resume 2024 for Teaching Profession
 
ICS 2208 Lecture Slide Notes for Topic 6
ICS 2208 Lecture Slide Notes for Topic 6ICS 2208 Lecture Slide Notes for Topic 6
ICS 2208 Lecture Slide Notes for Topic 6
 
Oppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and FilmOppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and Film
 
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
 
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDecoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
 

Remote sensing e-course PCA and Classification Technique (40

  • 1. Remote sensing e-course PCA and Classification Technique Fatwa Ramdani Geoenvironment, Earth Science, Grad. School of Science
  • 2. Outline • This course will focus in Principal Component Analysis and Classification Technique based on remotely-sensed data, SPOT 6 & Landsat 8 OLI. The methods how to analyze and exploit the SPOT 6 Landsat 8 OLI information for Land Use mapping will be illustrated in GRASS 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 PCA • Understand formula module function in open source software • Understand the benefit of PCA in Classification Technique
  • 4. Intended Audience • University student with basic level of knowledge in Remote Sensing studies • Course Requirements: – – – – Internet access GRASS software (http://grass.osgeo.org/grass64/binary/mswindows/native/) QuantumGIS software (http://www.qgis.org/en/site/forusers/download.html) Download data here ()
  • 5. 1. What is SPOT6? Launched September 9, 2012, by India's Polar Satellite Launch Vehicle. It is run by Spot Image based in Toulouse, France. It was initiated by the CNES (Centre national d'études spatiales – the French space agency) in the 1970s and was developed in association with the SSTC (Belgian scientific, technical and cultural services) and the Swedish National Space Board (SNSB). Resources: • http://www.astrium-geo.com/en/143-spot-satellite-imagery
  • 6. SPOT6 Bands and Products PANCRO band: 1.5 m panchromatic (0.455 µm – 0.745 µm) 6 m multispectral, 4 bands: • blue (0.455 µm – 0.525 µm) • green (0.530 µm – 0.590 µm) • red (0.625 µm – 0.695 µm) • near-infrared (0.760 µm – 0.890 µm) Primary  Processing level closest to the image acquired by the sensor: it restores perfect collection conditions. The sensor is placed in rectilinear geometry, the image is clear of any radiometric distortion.  Optimal for clients familiar with satellite imagery processing techniques wishing to apply their own production methods (orthorectification or 3D modeling for example). Ortho • Georeferenced image in Earth geometry, corrected from off-nadir acquisition and terrain effects. • Optimal for simple and direct use of the image, and for immediate ingestion into a Geographic Information System. • The standard 3D model used for ground corrections is the worldwide Elevation30 dataset (also known as Reference3D).
  • 7. Principal Component Analysis (PCA) is a dimensionality reduction technique used extensively in Remote Sensing studies (e.g. in change detection studies, image enhancement tasks and more). PCA is in fact a linear transformation applied on (usually) highly correlated multidimensional (e.g. multispectral) data. The input dimensions are transformed in a new coordinate system in which the produced dimensions (called principal components) contain, in decreasing order, the greatest variance related with unchanged landscape features. We can guided purely by the statistical properties of the image itself. The new bands are called components. PCA has two algebraic solutions: • Eigenvectors of Covariance (or Correlation) of a given data matrix >> GRASS • Singular Value Decomposition of a given data matrix
  • 8. PCA & band ratio’s benefit in classification Classification based on the band ratio and subsequent supervised classification has the possibility of producing the best result if the spectra of LULC can be fully exploited (the reduction of data without loss of information, prior to classification). Resources: • Lillesand, T. M., and R. W. Kiefer. 2000. Remote Sensing and Image Interpretation, 736. New York: John Wiley and Sons. • Rogerson, P. A. 2002. “Change Detection Thresholds for Remotely Sensed Images.” Journal of Geographical Systems 4: 85–97.
  • 9. Activities! • Import file using GRASS • Explore basic statistics • Displaying the data: • Produce RGB composite image • PCA – Run i.pca module – Analyze the result • C
  • 10. PCA Analysis (for Landsat 8 OLI) PC has the most positive or negative contribution i.pca input=B1,B2,B3,B4,B5,B7 output_prefix=PCA • • • • • • PC1 2553.26 (-0.2998,-0.2313,-0.4177,-0.2342,-0.6702,-0.4221) [91.10%] PC2 168.11 (-0.4841,-0.2400,-0.3196, 0.6894, 0.3382,-0.1276) [ 6.00%] PC3 58.00 (-0.3717,-0.2467,-0.3222,-0.5897, 0.3657, 0.4645) [ 2.07%] PC4 16.27 ( 0.1545, 0.0497,-0.3195, 0.3426,-0.4678, 0.7317) [ 0.58%] PC5 6.27 (-0.6507, 0.0183, 0.6650, 0.0396,-0.2856, 0.2254) [ 0.22%] PC6 0.92 ( 0.3005,-0.9084, 0.2743, 0.0572,-0.0494, 0.0596) [ 0.03%] Eigen values, (vectors), and [percent importance]: The band ratio derived from PC1 is B5/B2. Similarly, the results for PC2–PC3 lead to the choice of the ratios B1/B4, and B4/B7, respectively
  • 11. PCA Analysis (continue for Landsat 8 OLI) • Thus, – PC_landsat_1= -0.2998*B1-0.2313*B2-0.4177*B3… – PC_landsat_2=-0.4841*B1-0.2400*B2-0.3196B3… – PC_landsat_3= -0.3717*B1-0.2467*B2-0.3222*B3… How to evaluate percent of importance? Used eigenvalue; 2553.26/2553.26+168.11+58+ 16.27 + 6.27 +0.92=91.09%
  • 12. PCA Analysis (continue for Landsat 8 OLI) • • • PC1 has the highest factor loading of -0.2313 from band 2 (blue), followed by band 4 (red), and then band 1 (coastal aerosol). Therefore, this component is suitable for mapping coastal environment, wetland, and lake environment. Also capable of differentiating soil and rock surfaces from vegetation PC2 has the highest factor loading of 0.6894 from band 4 (red), followed by band 5 (NIR), and then band 7 (SWIR). This component can be termed a healthy (dense, vigorous) vegetation component because healthy vegetation reflects highly in near infrared and also some mid infrared energy except in the water absorption zones in this region PC3 has the highest factor from band 7 (SWIR), followed by band 5 (NIR), and then band 2 (blue). PC3 can be termed a dark, dry land component due to the high mid infrared factor loading. Separated land and water sharply. Band 7 has strong water absorption region.
  • 13. Exercise! • Run i.pca for SPOT6! i.pca input=spot1,spot2,spot3,spot4 output_prefix=pca.spot 1. Eigen values, (vectors), and [percent importance]: 2. Band Ratio: ?
  • 14. LULC Classification #We use the bands ratio result from PCA output • i.group group=spot_group subgroup=spot_sub input=pc_spot1,pc_spot2,pc_spot3 • i.cluster group=spot_group subgroup=spot_sub sigfile=urban classes=7 report=urban_report.txt • remember name of file containing signatures: urban • i.maxlik group=spot_group subgroup=spot_sub sigfile=spot class=spot_class #Converting raster to vector • r.to.vect -s input=spot_class output=spot_class feature=area
  • 15. Application • Mapping coastal environment – Mangrove forests – Kelp forest in turbid water – Submerged vegetation • Mapping wetland environment • Mineral exploration in arid environment
  • 16. Resources • http://www.crisp.nus.edu.sg/~research/tutorial/opt_int.htm • http://www.astrium-geo.com/en/4594-spot-6-products • https://dl.dropboxusercontent.com/u/4437062/CasalPascual_ Gema_TD_2012.pdf • http://www.geocarto.com.hk/cgi-bin/pages1/sep04/p11.pdf
  • 17. Result; RGB PC123 d.rgb red=pca.spot.1 green=pca.spot.2 blue=pca.spot.3
  • 18. PCA; Vegetation and Urbanized Area
  • 20. Quiz? • Which bands has the most positive or negative contribution from SPOT6? • The band ratio derived from PC1 of SPOT6 is x. Similarly, the results for PC2–PC3 lead to the choice of the ratios y, and z. What is the band ratio of x, y, and z? • How to produce map pc_spot1, pc_spot2, and pc_spot3 as band ratio of SPOT6?