Object-based classification (Tutorial)

From AWF-Wiki
(Difference between revisions)
Jump to: navigation, search
(Object-based classifcation using SVM algorithm)
Line 3: Line 3:
  
 
== Mean-shift segmentation of large size images ==
 
== Mean-shift segmentation of large size images ==
# Step. We perform a mean shift filtering on the preprocessed input image ''188_pca_cmask_8b.tif''. (3 principal components of Landsat-8 multispectral bands (B1 - B7), pansharpened with band B8, rescaled to 8bit. Clouds and cloud shadows are masked). We extract homogeneous objects on the basis of a filtered image. Go to {{mitem|text=Processing-Toolbox --> Orfeo Toolbox (image analysis) --> Image Filtering --> Exact Large-Scale Mean-Shift segmentation, step 1 (Smoothing)}}.  
+
# Step. Perform a mean shift filtering on the preprocessed input image ''188_pca_cmask_8b.tif''. (3 principal components of Landsat-8 multispectral bands (B1 - B7), pansharpened with band B8, rescaled to 8bit. Clouds and cloud shadows are masked). We extract homogeneous objects on the basis of a filtered image. Go to {{mitem|text=Processing-Toolbox --> Orfeo Toolbox (image analysis) --> Image Filtering --> Exact Large-Scale Mean-Shift segmentation, step 1 (Smoothing)}}.  
 
##* Set the ''188_pca_cmask_8b'' layer as {{button|text=Input image}}.
 
##* Set the ''188_pca_cmask_8b'' layer as {{button|text=Input image}}.
 
##* The {{button|text=Range radius}} should be set to 30.
 
##* The {{button|text=Range radius}} should be set to 30.
 
##* Leave all other configurations as they are and click {{button|text=Run}}. Have a look on the resulting filtered and spatial images.
 
##* Leave all other configurations as they are and click {{button|text=Run}}. Have a look on the resulting filtered and spatial images.
# Step. We convert the filtered image to one band image object. Go to {{mitem|text=Processing-Toolbox --> Orfeo Toolbox (image analysis) --> Segmentation --> Exact Large-Scale Mean-Shift segmentation, step 2}}.  
+
# Step. Convert the filtered image to one band image object. Go to {{mitem|text=Processing-Toolbox --> Orfeo Toolbox (image analysis) --> Segmentation --> Exact Large-Scale Mean-Shift segmentation, step 2}}.  
 
##* The ''Filtered image'' is {{button|text=Filter output}} from step 1.  
 
##* The ''Filtered image'' is {{button|text=Filter output}} from step 1.  
 
##* Leave the ''Spatial image'' as {{button|text= [not selected]}}.
 
##* Leave the ''Spatial image'' as {{button|text= [not selected]}}.
 
##* {{button|text=Range radius}} is set to 30.
 
##* {{button|text=Range radius}} is set to 30.
 
##* Leave all other configurations as they are and click {{button|text=Run}}. The Output image is a labeled image where neighbor pixels whose range distance is below range radius will be grouped together into the same cluster.
 
##* Leave all other configurations as they are and click {{button|text=Run}}. The Output image is a labeled image where neighbor pixels whose range distance is below range radius will be grouped together into the same cluster.
# Step. We adjust the image object size merging small regions with the module {{mitem|text=Processing-Orfeo Toolbox (image analysis) --> Segmentation-Exact --> Large-Scale Mean-Shift segmentation, step 3 (optional)}}.
+
# Step. Adjust the image object size merging small regions with the module {{mitem|text=Processing-Orfeo Toolbox (image analysis) --> Segmentation-Exact --> Large-Scale Mean-Shift segmentation, step 3 (optional)}}.
 
##* The ''Input image'' is the {{button|text=''188_pca_cmask_8b''}} layer.
 
##* The ''Input image'' is the {{button|text=''188_pca_cmask_8b''}} layer.
 
##* The ''Segmented image'' is {{button|text=Output image}} from step 2.
 
##* The ''Segmented image'' is {{button|text=Output image}} from step 2.
 
##* The {{button|text=Minimum Region size}} is set to 10.
 
##* The {{button|text=Minimum Region size}} is set to 10.
 
##* Leave all other configurations as they are and click {{button|text=Run}}.
 
##* Leave all other configurations as they are and click {{button|text=Run}}.
# Step. We convert the image segments from raster to polygon vectors. Label ID, mean and standard deviation, number of the pixels in an image polygon are calculated and added as additional columns in the resulting shapefile.{{mitem|text=Processing-Orfeo Toolbox (image analysis) --> Segmentation-Exact Large-Scale Mean-Shift segmentation, step 4}}
+
# Step. Convert the image segments from raster to polygon vectors. Label ID, mean and standard deviation, number of the pixels in an image polygon are calculated and added as additional columns in the resulting shapefile.{{mitem|text=Processing-Orfeo Toolbox (image analysis) --> Segmentation-Exact Large-Scale Mean-Shift segmentation, step 4}}
 
##* The ''Input image'' is the {{button|text=188_pca_cmask_8b}} layer.
 
##* The ''Input image'' is the {{button|text=188_pca_cmask_8b}} layer.
 
##* ''Segmented image'' is  {{button|text=Output image}} from step 3.
 
##* ''Segmented image'' is  {{button|text=Output image}} from step 3.
Line 25: Line 25:
  
 
== Preparation of reference data ==
 
== Preparation of reference data ==
We join the Land use/cover (LUC) class attribute of manually digitized training areas with the image segments. {{mitem|text=Vector  --> Data Management Tools --> Join Attributes by Location ...}}.
+
Join the Land use/cover (LUC) class attribute of manually digitized training areas with the image segments. {{mitem|text=Vector  --> Data Management Tools --> Join Attributes by Location ...}}.
 
##* The ''Target vector file'' is the {{button|text=Output GIS vector file}} of step 4.
 
##* The ''Target vector file'' is the {{button|text=Output GIS vector file}} of step 4.
 
##* ''Join vector layer'' is  {{button|text=train_manual_poly.shp}}.
 
##* ''Join vector layer'' is  {{button|text=train_manual_poly.shp}}.
 
##* ''Output vector'' {{button|text=seg_188_pca_cmask_8b_train.shp}}.
 
##* ''Output vector'' {{button|text=seg_188_pca_cmask_8b_train.shp}}.
 
##* For the rest of parameters keep default values.{{button|text=OK}}.
 
##* For the rest of parameters keep default values.{{button|text=OK}}.
We need to rename the field names of the resulting output vector attribut table avoiding upper capitals and underslash using the ''Table Manager'' plugin.  
+
Rename the field names of the resulting output vector attribut table avoiding upper capitals and underslash using the ''Table Manager'' plugin. Rename the attribut field ''C_ID'' to ''class''.
  
 
== Object-based classifcation using SVM algorithm ==
 
== Object-based classifcation using SVM algorithm ==
The vector based supervised classifcation modules in QGIS 2.12.3 are under development and still not working. Alternativly we may use the windows command line.
+
The vector based supervised classifcation modules in QGIS 2.12.3 are under development and still not working. Alternativly, we may use the windows command line.
{{mitem|text=Start --> All Programs --> OSGeo4W --> OSGeo4W Shell}} or double click on the file 'C:\OSGeo4W64\OSGeo4W.bat'. A windows command shell opens.
+
{{mitem|text=Start --> All Programs --> OSGeo4W --> OSGeo4W Shell}} or double click on the file 'C:\OSGeo4W64\OSGeo4W.bat'.  
# Type ''otbgui_ComputeOGRLayersFeturesStatistics''
+
# A windows command shell opens, type ''otbgui_ComputeOGRLayersFeturesStatistics''.
##* ''Name of the input vector'' is the file {{button|text=seg_188_pca_cmask_8b_train.shp}}.
+
##* ''Name of the input vector'' is {{button|text=seg_188_pca_cmask_8b_train.shp}}.
 
##* ''XML file containing mean and variance of each feature'' is {{button|text=seg_188_pca_cmask_8b_train.shp.xml}}.
 
##* ''XML file containing mean and variance of each feature'' is {{button|text=seg_188_pca_cmask_8b_train.shp.xml}}.
 
##* In the ''List of features to consider for statistics'' mark the columns {{button|text=meanB0, meanB1, meanB2}}.{{button|text=Execute}}.
 
##* In the ''List of features to consider for statistics'' mark the columns {{button|text=meanB0, meanB1, meanB2}}.{{button|text=Execute}}.
 
ALso, calculate an XML file for vector file {{button|text=seg_188_pca_cmask_8b.shp}}.
 
ALso, calculate an XML file for vector file {{button|text=seg_188_pca_cmask_8b.shp}}.
  
# Type ''otbgui_TrainOGRLayersClassifier''
+
# Type ''otbgui_TrainOGRLayersClassifier''.
 
+
##* ''Name of the input shapefile'' is {{button|text=seg_188_pca_cmask_8b_train.shp}}.
 +
##* ''XML file containing mean and variance of each feature'' is {{button|text=seg_188_pca_cmask_8b_train.shp.xml}}.
 +
##* ''Output model filename'' is {{button|text=seg_188_pca_cmask_8b_train.model}}
 +
##* In the ''List of features to consider for statistics'' mark the columns {{button|text=meanB0, meanB1, meanB2}}.{{button|text=Execute}}.
 
# Type ''OGRLayersClassifier''
 
# Type ''OGRLayersClassifier''
 
   
 
   

Revision as of 09:33, 25 January 2016

Contents

Determining segmentation parameters

Mean-shift segmentation of large size images

  1. Step. Perform a mean shift filtering on the preprocessed input image 188_pca_cmask_8b.tif. (3 principal components of Landsat-8 multispectral bands (B1 - B7), pansharpened with band B8, rescaled to 8bit. Clouds and cloud shadows are masked). We extract homogeneous objects on the basis of a filtered image. Go to Processing-Toolbox --> Orfeo Toolbox (image analysis) --> Image Filtering --> Exact Large-Scale Mean-Shift segmentation, step 1 (Smoothing).
      • Set the 188_pca_cmask_8b layer as Input image.
      • The Range radius should be set to 30.
      • Leave all other configurations as they are and click Run. Have a look on the resulting filtered and spatial images.
  2. Step. Convert the filtered image to one band image object. Go to Processing-Toolbox --> Orfeo Toolbox (image analysis) --> Segmentation --> Exact Large-Scale Mean-Shift segmentation, step 2.
      • The Filtered image is Filter output from step 1.
      • Leave the Spatial image as [not selected].
      • Range radius is set to 30.
      • Leave all other configurations as they are and click Run. The Output image is a labeled image where neighbor pixels whose range distance is below range radius will be grouped together into the same cluster.
  3. Step. Adjust the image object size merging small regions with the module Processing-Orfeo Toolbox (image analysis) --> Segmentation-Exact --> Large-Scale Mean-Shift segmentation, step 3 (optional).
      • The Input image is the 188_pca_cmask_8b layer.
      • The Segmented image is Output image from step 2.
      • The Minimum Region size is set to 10.
      • Leave all other configurations as they are and click Run.
  4. Step. Convert the image segments from raster to polygon vectors. Label ID, mean and standard deviation, number of the pixels in an image polygon are calculated and added as additional columns in the resulting shapefile.Processing-Orfeo Toolbox (image analysis) --> Segmentation-Exact Large-Scale Mean-Shift segmentation, step 4
      • The Input image is the 188_pca_cmask_8b layer.
      • Segmented image is Output image from step 3.
      • The name of Output GIS vector file is 1seg_188_pca_cmask_8b.shp
      • For the rest of parameters keep default values.Run.

Change Layer --> Properties Style --> Fill Style to No Brush and Colors --> Border to white. Overlay the vector file on top of the image 188_pca_cmask_8b.tif to evaluate the segmentation result.

Preparation of reference data

Join the Land use/cover (LUC) class attribute of manually digitized training areas with the image segments. Vector --> Data Management Tools --> Join Attributes by Location ....

      • The Target vector file is the Output GIS vector file of step 4.
      • Join vector layer is train_manual_poly.shp.
      • Output vector seg_188_pca_cmask_8b_train.shp.
      • For the rest of parameters keep default values.OK.

Rename the field names of the resulting output vector attribut table avoiding upper capitals and underslash using the Table Manager plugin. Rename the attribut field C_ID to class.

Object-based classifcation using SVM algorithm

The vector based supervised classifcation modules in QGIS 2.12.3 are under development and still not working. Alternativly, we may use the windows command line. Start --> All Programs --> OSGeo4W --> OSGeo4W Shell or double click on the file 'C:\OSGeo4W64\OSGeo4W.bat'.

  1. A windows command shell opens, type otbgui_ComputeOGRLayersFeturesStatistics.
      • Name of the input vector is seg_188_pca_cmask_8b_train.shp.
      • XML file containing mean and variance of each feature is seg_188_pca_cmask_8b_train.shp.xml.
      • In the List of features to consider for statistics mark the columns meanB0, meanB1, meanB2.Execute.

ALso, calculate an XML file for vector file seg_188_pca_cmask_8b.shp.

  1. Type otbgui_TrainOGRLayersClassifier.
      • Name of the input shapefile is seg_188_pca_cmask_8b_train.shp.
      • XML file containing mean and variance of each feature is seg_188_pca_cmask_8b_train.shp.xml.
      • Output model filename is seg_188_pca_cmask_8b_train.model
      • In the List of features to consider for statistics mark the columns meanB0, meanB1, meanB2.Execute.
  2. Type OGRLayersClassifier


info.png Info
For more detailed information on the SVM algorithm visit the library website
Personal tools
Namespaces

Variants
Actions
Navigation
Development
Toolbox
Print/export