Object-based supervised classification
From AWF-Wiki
(Difference between revisions)
(→Training phase) |
|||
| Line 2: | Line 2: | ||
==Segmentation== | ==Segmentation== | ||
* In the search engine of Processing Toolbox, type {{typed|text=segmentation}} and double click '''Segmentation'''. | * In the search engine of Processing Toolbox, type {{typed|text=segmentation}} and double click '''Segmentation'''. | ||
| − | |||
* Select the input image: '''Subset_S2A_MSIL2A_20170619T_MUL.tif ''' (data type uint 16bit). | * Select the input image: '''Subset_S2A_MSIL2A_20170619T_MUL.tif ''' (data type uint 16bit). | ||
| + | * Set {{button|text=Segmentation algorithm}} to '''meanshift''' | ||
* The {{button|text=Range radius}} value can be set to {{typed|text=600}}. The optimal value depends on datatype dynamic range of the input image and requires experimental trials for the specific classifcation objectives. | * The {{button|text=Range radius}} value can be set to {{typed|text=600}}. The optimal value depends on datatype dynamic range of the input image and requires experimental trials for the specific classifcation objectives. | ||
* Set {{button|text=Minimum Region size}} (in pixels) to {{typed|text=16}}. | * Set {{button|text=Minimum Region size}} (in pixels) to {{typed|text=16}}. | ||
* {{button|text=Processing mode}} '''Vector''' | * {{button|text=Processing mode}} '''Vector''' | ||
| − | * Set the {{button|text=Mask image}} to blank (top of | + | * Set the {{button|text=Mask image}} to blank (top of drop-down list). |
| − | + | ||
* Check {{button|text=8-neighborhood connectivity}} on. | * Check {{button|text=8-neighborhood connectivity}} on. | ||
| + | * The {{button|text=Minimum object size}} (in pixels) can be set to {{typed|text=16}} depending on minimum mapping size. | ||
* Change {{button|text=Output pixel type}} to '''uint32'''. | * Change {{button|text=Output pixel type}} to '''uint32'''. | ||
| − | * Name the {{button|text=Output vector file}} e.g. ''' | + | * Name the {{button|text=Output vector file}} e.g. '''segments_meanshift.gpkg''' (GeoPackage). |
* Click {{button|text=Run}}. | * Click {{button|text=Run}}. | ||
| Line 17: | Line 17: | ||
* Evaluate the segmentation results: Load the output vector file '''segments_meanshift.gpkg''' into QGIS on top of the image ''Subset_S2A_MSIL2A_20170619T_Mul.tif'' | * Evaluate the segmentation results: Load the output vector file '''segments_meanshift.gpkg''' into QGIS on top of the image ''Subset_S2A_MSIL2A_20170619T_Mul.tif'' | ||
| − | Mark the vector layer in the Qgis Layers window. {{mitem|text= | + | Mark the vector layer in the Qgis Layers window. Right click {{mitem|text=Properties --> Symbology --> Simple Fill}}, {{mitem|text=Fill Style}}: ''No Brush'' and {{mitem|text=Stroke color}}:''white''. |
==Feature extraction== | ==Feature extraction== | ||
| Line 34: | Line 34: | ||
* In the field ''Field names for training features'' copy and paste | * In the field ''Field names for training features'' copy and paste | ||
<pre> "mean_2 stdev_0 mean_9 mean_7 mean_0" </pre> | <pre> "mean_2 stdev_0 mean_9 mean_7 mean_0" </pre> | ||
| + | * This is one of many variable sets as a result of a feature selection procedure. | ||
* The name of ''Field containing the class id for supervision" is {{button|text=C_ID}}. | * The name of ''Field containing the class id for supervision" is {{button|text=C_ID}}. | ||
* Classifier to use for training: {{button|text=libsvm}} | * Classifier to use for training: {{button|text=libsvm}} | ||
Revision as of 11:23, 21 December 2020
Contents |
Object-based image analysis (OBIA) with QGIS and OTB processing plugin
Segmentation
- In the search engine of Processing Toolbox, type segmentation and double click Segmentation.
- Select the input image: Subset_S2A_MSIL2A_20170619T_MUL.tif (data type uint 16bit).
- Set Segmentation algorithm to meanshift
- The Range radius value can be set to 600. The optimal value depends on datatype dynamic range of the input image and requires experimental trials for the specific classifcation objectives.
- Set Minimum Region size (in pixels) to 16.
- Processing mode Vector
- Set the Mask image to blank (top of drop-down list).
- Check 8-neighborhood connectivity on.
- The Minimum object size (in pixels) can be set to 16 depending on minimum mapping size.
- Change Output pixel type to uint32.
- Name the Output vector file e.g. segments_meanshift.gpkg (GeoPackage).
- Click Run.
- Evaluate the segmentation results: Load the output vector file segments_meanshift.gpkg into QGIS on top of the image Subset_S2A_MSIL2A_20170619T_Mul.tif
Mark the vector layer in the Qgis Layers window. Right click Properties --> Symbology --> Simple Fill, Fill Style: No Brush and Stroke color:white.
Feature extraction
In the search engine of Processing Toolbox, type zonalstats and open ZonalStatistics under Image Manipulation of OTB.
- Select the Input image: Subset_S2A_MSIL2A_20170619T_MUL.tif.
- Background value to ignore: 0
- For the Input vector data do not select a vector file from the file list which are already loaded in the QGIS Viewer. There is currently a bug in QGIS 3.16 which leads to failure because the full pathname is not parsed correctly. Instead, please select a vector file by clicking
and browse directly to the file containing the result from Segmentation: segment polygons in format GPKG segments_meanshift.gpkg.
- File name for the output vector data: segments_meanshift_zonal.gpkg.
- Click Run.
Training phase
- In the search engine of Processing Toolbox, type Train and double click TrainVectorClassifier.
- In the Input Vector Data List do not select a file from the list which is already loaded in the QGIS Viewer. There is currently a bug in QGIS 3.16 which leads to failure during file import. Instead please select a vector file clicking
and browse directly to the file containing training area polygons in format GPKG or SHP e.g. lucc_training_obia.gpkg.
- Output model filename is svm_obia.model
- In the field Field names for training features copy and paste
"mean_2 stdev_0 mean_9 mean_7 mean_0"
- This is one of many variable sets as a result of a feature selection procedure.
- The name of Field containing the class id for supervision" is C_ID.
- Classifier to use for training: libsvm
- SVM Kernel Type: linear
- SVM Model Type: csvc
- Click Parameters optimizationON.
- Click Run.
Info
- For more detailed information on the SVM algorithm visit the LibSVM website
Classification phase
- In the search engine of Processing Toolbox, type Vector and double click VectorClassifier.
- In the Input Vector Data do not select a file from the list which is already loaded in the QGIS Viewer. There is currently a bug in QGIS 3.16 which leads to failure during file import. Instead please select a vector file clicking and browse directly to the file containing segments and features for the whole image (result of Feature extaction)training area polygons in format GPKG segments_meanshift_zonal.gpkg.
- Name of the input model file is svm_obia.model.
- Output field containing the class is C_ID
- Copy and paste into the field Field names to be calculated have to be the same features for prediction as were defined before in the TrainVectorClassifier module:
"mean_2 stdev_0 mean_9 mean_7 mean_0"
- Output vector Data file is lucc_classified_obia.gpkg.
Run.
Load the output vector file manually into QGIS. Layer --> Layer properties --> Symbology > Style --> Load style.... Open the same QGIS style file which is already in use for the training data: lucc_training_obia.qml.
