View source for Exercise 09: Segmentation algorithms

==Preparatory steps==
# Open image ''svm_classification.tif''
# Open the layer properties (right click in [[TOC]] or double click). In the {{button|text=Style}} tab, click {{button|text=Load style}} and browse for ''classification.qml''.
# Open {{mitem|text=Plugins --> Openlayers plugin --> Add Google Satellite Layer}} (figure '''A''').
# With the image ''svm_classification.tif'' on top (with transparency more than 50%) we can compare the classification with the information of the Google image and look for errors in the classification (figure '''B'''). 
# Improving the classification
## Open {{mitem|text=Processing tools --> Orfeo Toolbox --> Classification Regularization}}
## Using the ''svm_classification.tif'' as input image run the classification regularization. See figure '''C''' for the parameter configuration. Then you can compare the result to the image ''svm_classification.tif'' (figure '''D''').
# Installing Monteverdi
#* Open {{mitem|text=Start --> OSGeo4W --> Setup}}. Select {{button|text=Advanced Install}} and {{button|text=Install from internet}} in the following window and confirm the default settings in the next four dialogues until reaching the {{button|text=Select package dialogue}}. Select Monteverdi from the software list (figure '''D'''). Confirm with {{button|text=Next}}
<!--(Please refer to Pool of figures 3 for the selected parameters information)-->

==Segmentation in Monteverdi==
# Open Monteverdi by double-clicking the icon on the Desktop 
# Select {{mitem|text=File --> Open dataset}} and browse for ''188_pcs_indices.tif''
# Open the panchromatic image saved in ''landsat8/DOY88/SUB_LC81950242013188LGN00_B8.tif'' via {{mitem|text=File --> Open dataset}}. 
# In order to equalize the spatial extent and resolution of the two maps, select {{mitem|text=Geometry --> Superimpose two images}} Select image ''188_pcs_indices.tif)'' for reprojection and  ''SUB_LC81950242013188LGN00_B8.tif'' as reference image. Confirm with {{button|text=OK}}. 
# To generate an image with the characteristics of the multispectral image with the panchromatic resolution {{red|text=(I'm not sure I understand what this means. Please double-check. [[User:Lburgr|- Levent]] ([[User talk:Lburgr|talk]]))}}, select {{mitem|text=Filtering --> Pansharpening --> Simple RCA Pansharpening}} Select image to reproject (''188_pcs_indices.tif'') and the reference image for reprojection (''SUB_LC81950242013188LGN00_B8.tif''). Confirm with {{button|text=OK}}.
# Save the processed image: Right-click the file of the output image (Pan SharpenedImageOutput) and select {{mitem|text=Export dataset --> pansharpened188.tif (32 bit)}}. Confirm with {{button|text=OK}}.
# Load the generated image (''pansharpened188.tif'') into the [[QGIS]] project and compare it to the original multispectral image (''188_pcs_indices.tif'').
# As segmentation is a procedure that requires high computational capacity, it is recommended o select a subset of the sharpened images: Select {{mitem|text=File --> Extract ROI from dataset}} and select the image ''pansharpened188.tif'' as input. Draw a box in the {{button|text=select ROI}} window and confirm with {{button|text=OK}} (figure '''F'''). 
# Applying the segmentation algorithm:
# Open {{button|text=Filtering --> Mean shift clustering}} and select the ROI extracted from ''pansharpened188.tif''. Once you see the {{button|text=Mean shift module}} window you can change the parameters spectral value, spatial radius and opacity to find the pool of values that fit best to the characteristics of the image (e.g. figure '''G''').
# When the set of values that best fit to the image are found, the segmentation parameters can be applied to the whole image via {{button|text=Processing}}: Select {{mitem|text=Processing  --> Orfeo Toolbox --> Segmentation --> Mean Shift segmentation (large scale, vector output)}}. Use ''pansharpened188.tif'' as input map with the parameters selected in {{button|text=Mean Shift module}} from Monteverdi software.  

==Cloud detection in satellite images==
# Load the raster image file ''188_pca_indices.tif'' from the ''supervised'' folder of the [[course data]].
# Load the raster image file ''SUB_LC81950242013188LGN00_B1.tif'' from ''geodata/raster/landsat/landsat8/DOY188'' folder into the project. (Coastal Aerosol Band)
# Load the raster image file ''SUB_LC81950242013188LGN00_B11.tif'' from ''geodata/raster/landsat/landsat8/DOY188'' folder in QGis. (Thermal Infrared Band). Place the Band 11 image at the top in the [[TOC]].
# Generate a ratio channel with the raster calculator from {{mitem|text=Processing Toolbox -->  SAGA -->  Grid-Calculus --> Raster calculator}}. Select the raster images from Band 11 and 1. The formula must be a / b. Don't forget to enter the name for the image result. Start the calculation with {{button|text=Run}}.
# Open the ratio image ''ratio_band11_band1.tif'' in Monteverdi via {{mitem|text=File --> Open dataset}}. 
# For filtering the image, select {{mitem|text=Filtering --> Threshold}} and select the ratio image generated in the previous step. Confirm with {{button|text=OK}}.
# In the Threshold Module window select {{button|text=Binary Threshold}}; set outside value to {{typed|text=1}} and inside value to {{typed|text=0}}; Change the values of {{button|text=lower}} and {{button|text=upper}} threshold until the clouds are entirely covered (figure '''H'''). Save the threshold information.
# Export the image: Select the output image with right clicking and selecting {{button|text=Export dataset}}.  Save the output as ''cloud_mask.tif''.
# Open the ''cloud_mask.tif'' image in QGis
# Convert the image to shapefile: select {{mitem|text=Processing --> SAGA --> Shapes – Grid --> Vectorising Grid classes}}. Select the image.
# To calculate the area of the polygons in the shapefile: Select {{mitem|text=Vector --> Geometry tools  --> Export/ Add Geometry Columns}}
# Open the attribute table of the shapefile and shift to editing mode. Press the icon of {{button|text=Select features using an expression}} and enter {{typed|text=area < 30000}}. Select and delete the selection.
# Place the image and ''188_pca_indices.tif'' on top of each other to see the final result of the clouds delineated (figure '''I''').

==Figures==
{| class="wikitable" style="border:0pt"
|style="border:0pt"|[[Image:RemSens_Exercise09_01.png|thumb|450px|'''Figure A''': Land cover map with underlying Google satellite layer.]]
|style="border:0pt"|[[Image:RemSens_Exercise09_02.png|thumb|450px|'''Figure B''': Zoom in on land cover map with underlying Google satellite layer. Note how forested areas are classified as water.]]
|style="border:0pt"|[[Image:RemSens_Exercise09_03.png|thumb|450px|'''Figure C''': ''Classification Regularization'' algorithm of the Orfeo Toolbox in [[QGIS]].]]
|-
|style="border:0pt"|[[Image:RemSens_Exercise09_04.png|thumb|450px|'''Figure D''': Land cover map before and after processing with the ''Classification Regularization'' plugin.]]
|style="border:0pt"|[[Image:RemSens_Exercise09_05.png|thumb|450px|'''Figure E''': OSGeo4W setup dialogue for installing software from the internet with row for ''Monteverdi'' highlighted.]]
|style="border:0pt"|[[Image:Monteverdi_Select_ROI.png|thumb|450px|'''Figure F''': The ''Select ROI''  module menu in Monteverdi.]]
|-
|style="border:0pt"|[[Image:Monteverdi_Mean_shift.png|thumb|450px|'''Figure G''': The ''Mean shift'' module menu in Monteverdi.]]
|style="border:0pt"|[[Image:Monteverdi_Threshold.png|thumb|450px|'''Figure H''': The ''Threshold'' module menu in Monteverdi.]]
|style="border:0pt"|[[Image:RemSens_Exercise09_10.png|thumb|450px|'''Figure I''': PCA Indices map and cloud vector layer.]]
|}

[[Category:QGIS Tutorial]]