Supervised classification (Tutorial)

From AWF-Wiki
(Difference between revisions)
Jump to: navigation, search
Line 1: Line 1:
 
== Classification with Orfeo Toolbox ==
 
== Classification with Orfeo Toolbox ==
 
=== Image statistics ===
 
=== Image statistics ===
−
# Add the LandSat-8 imagery ''SUB_LC81950242013188LGN00_MUL.tif'' into a QGIS project. It should be available in the [[Course data|course data]].
+
# Add the LandSat-8 imagery ''Subset_S2A_MSIL2A_20170619T_B12_BOA.tif '' into a QGIS project.
−
# Calculate mean and standard error for each band of the LandSat-8 imagery.
+
# Calculate mean and standard error for each band of the Sentinel-2 imagery.
 
## Open {{mitem|text=Orfeo Toolbox --> Compute images second order statistics}} (see figure '''A''').
 
## Open {{mitem|text=Orfeo Toolbox --> Compute images second order statistics}} (see figure '''A''').
−
## Set ''SUB_LC81950242013188LGN00_MUL.tif'' as {{button|text=Input images}}.
+
## Set ''Subset_S2A_MSIL2A_20170619T_B12_BOA.tif'' as {{button|text=Input images}}.
−
## Save the {{button|text=Output XML file}} as ''SUB_LC81950242013188LGN00_mul.tif.xml''.
+
## Save the {{button|text=Output XML file}} as ''Subset_S2A_MSIL2A_20170619T_B12_BOA.tif.xml''.
  
 
=== Train image classifier ===
 
=== Train image classifier ===
−
# Add the training areas ''training_manual_poly.shp'' into QGIS. It should be available in the course data.
+
# Add the training areas ''lab_9_training_input.shp'' into QGIS. It should be available in the course data.
 
# Open {{mitem|text=Orfeo Toolbox --> TrainImageClassifier (libsvm)}} to use the Support Vector Machine SVM algorithm (see figure '''B''').
 
# Open {{mitem|text=Orfeo Toolbox --> TrainImageClassifier (libsvm)}} to use the Support Vector Machine SVM algorithm (see figure '''B''').
−
# Set ''SUB_LC81950242013188LGN00_MUL.tif'' as {{button|text=Input image list}}.
+
# Set ''Subset_S2A_MSIL2A_20170619T_B12_BOA.tif'' as {{button|text=Input image list}}.
 
# Set ''training_manual_poly.shp'' as {{button|text=Input vector list}}.
 
# Set ''training_manual_poly.shp'' as {{button|text=Input vector list}}.
−
# Set ''SUB_LC81950242013188LGN00_MUL.tif.xml'' as {{button|text=Input XML image statistics file}}.
+
# Set ''Subset_S2A_MSIL2A_20170619T_B12_BOA.tif.xml'' as {{button|text=Input XML image statistics file}}.
 
# Set {{button|text=Name of discrimination field}} to ''C_ID'' (C_ID refers to the column that contain the LUC classes code).
 
# Set {{button|text=Name of discrimination field}} to ''C_ID'' (C_ID refers to the column that contain the LUC classes code).
 
# Save the {{button|text=Output confusion matrix}} as ''ConfusionMatrixSVM.csv''.
 
# Save the {{button|text=Output confusion matrix}} as ''ConfusionMatrixSVM.csv''.
Line 21: Line 21:
 
# Add the cloud mask ''cloud_shadow_mask.tif'' into QGIS. It should be available in the course data.
 
# Add the cloud mask ''cloud_shadow_mask.tif'' into QGIS. It should be available in the course data.
 
# Open {{mitem|text=Orfeo Toolbox --> Image Classification}} (see figure '''C''').
 
# Open {{mitem|text=Orfeo Toolbox --> Image Classification}} (see figure '''C''').
−
# Set ''SUB_LC81950242013188LGN00_MUL.tif'' as {{button|text=Input image}}.
+
# Set ''Subset_S2A_MSIL2A_20170619T_B12_BOA.tif'' as {{button|text=Input image}}.
 
# Set ''cloud_shadow_mask.tif'' as {{button|text=Input mask}}.
 
# Set ''cloud_shadow_mask.tif'' as {{button|text=Input mask}}.
 
# Set ''SVM.model'' as {{button|text=Model file}}.
 
# Set ''SVM.model'' as {{button|text=Model file}}.

Revision as of 12:27, 11 December 2017

Contents

Classification with Orfeo Toolbox

Image statistics

  1. Add the LandSat-8 imagery Subset_S2A_MSIL2A_20170619T_B12_BOA.tif into a QGIS project.
  2. Calculate mean and standard error for each band of the Sentinel-2 imagery.
    1. Open Orfeo Toolbox --> Compute images second order statistics (see figure A).
    2. Set Subset_S2A_MSIL2A_20170619T_B12_BOA.tif as Input images.
    3. Save the Output XML file as Subset_S2A_MSIL2A_20170619T_B12_BOA.tif.xml.

Train image classifier

  1. Add the training areas lab_9_training_input.shp into QGIS. It should be available in the course data.
  2. Open Orfeo Toolbox --> TrainImageClassifier (libsvm) to use the Support Vector Machine SVM algorithm (see figure B).
  3. Set Subset_S2A_MSIL2A_20170619T_B12_BOA.tif as Input image list.
  4. Set training_manual_poly.shp as Input vector list.
  5. Set Subset_S2A_MSIL2A_20170619T_B12_BOA.tif.xml as Input XML image statistics file.
  6. Set Name of discrimination field to C_ID (C_ID refers to the column that contain the LUC classes code).
  7. Save the Output confusion matrix as ConfusionMatrixSVM.csv.
  8. Save the Output model as SVM.model.
  9. Calculation of accuracies :
    Open ConfusionMatrixSVM.csv in LibreOffice or MS Excel and calculate overall, producer and consumer accuracies.

Classification

  1. Add the cloud mask cloud_shadow_mask.tif into QGIS. It should be available in the course data.
  2. Open Orfeo Toolbox --> Image Classification (see figure C).
  3. Set Subset_S2A_MSIL2A_20170619T_B12_BOA.tif as Input image.
  4. Set cloud_shadow_mask.tif as Input mask.
  5. Set SVM.model as Model file.
  6. Set SUB_LC81950242013188LGN00_MUL.tif.xml as Statistical file.
  7. Save the Output image as su_svm.tif.
  8. Evaluate classification results.
    1. Add the classification result su_svm.tif to QGIS.
    2. Right click su_svm.tif in the TOC and select Properties --> Style --> Style --> Load Style.
    3. Load classifcation.qml, which should be available in the course data.
    4. Open the Google Maps Layer under Web --> ObenLayers plugin --> Add Google Satellite layer and look for misclassification.

Compute a confusion matrix with independent reference data

  1. Open Orfeo Toolbox --> ComputeConfusionMatrix (Vector) (see figure D).
  2. Set su_svm.tif as Input image.
  3. Set train_systematic_seg.shp as Input reference vector data.
  4. Set Field name to C_ID.



Figures

Figure A: Dialogues of the Compute images second order statistics
Figure B: Dialogues of the TrainImageClassifier (libsvm)
Figure C: Dialogues of the Image Classification
Figure D: Dialogues of the ComputeConfusionMatrix (Vector)
Retrieved from "http://wiki.awf.forst.uni-goettingen.de/wiki/index.php?title=Supervised_classification_(Tutorial)&oldid=13885"
Personal tools
Namespaces

Variants
Actions
Navigation
Development
Toolbox
Print/export