Use the model

You can use this model in the Classify Pixels Using Deep Learning tool available in the Image Analyst toolbox in ArcGIS Pro. Follow the steps below to use the model for classifying human settlements in images.

Supported imagery

This model can be used with the Sentinel-2 L1C Multispectral raster in the form of a raster product, mosaic dataset, or image service.

Ensure that you create a mosaic dataset using the Manage Sentinel-2 imagery tool. Once created, you can use the multispectral mosaic dataset generated by the tool. This mosaic dataset can also be published as an image service and used as an input.

Ensure that the processing template is set to None.

Classify human settlements

Use the following steps to classify human settlements from the imagery:

Data preparation:
1. Prepare data according to the following product type:
   • Raster Product
   1. Browse to the folder housing the Sentinel-2 L1C data. Expand the folder and locate the raster product.
   2. Expand the Raster Product provided as an MTD_MSIL1C.xml file and select the Multispectral derived raster dataset.

      

   • Mosaic Dataset
   1. Create a Mosaic Dataset using the Create Mosaic Dataset geoprocessing tool. Set the variables on the Parameters tab as follows:
      • Output Location—Select a geodatabase.
      • Mosaic Dataset Name—Set the mosaic dataset name.
      • Coordinate System—Select a coordinate system for the output mosaic dataset.
      • Product Definition—Select None.

      

   2. To add the raster to the mosaic dataset, open the Add Rasters To Mosaic Dataset geoprocessing tool. Set the variables on the Parameters tab as follows:
      • Mosaic Dataset—Select the input mosaic dataset.
      • Raster Type—Select Sentinel-2 from the drop-down list.
      • Processing Templates—Select Multispectral from the drop-down list.
      • Input Data—Select Folder from the drop-down list, browse and add the .SAFE files.

      

      Note: You can create a multiband image through either the Composite Bands geoprocessing tool or Composite Bands raster function if required, which can be used as input for inferencing.

Data processing:
2. Download the Human Settlements Classification (Sentinel-2) model and add the imagery layer in ArcGIS Pro.
3. Zoom to an area of interest.

   

4. Browse to Tools on the Analysis tab.

   

5. Click the Toolboxes tab in the Geoprocessing pane, select Image Analyst Tools, and browse to the Classify Pixels Using Deep Learning tool under Deep Learning.

   

6. Set the variables on the Parameters tab as follows:
   1. Input Raster—Select the imagery.
   2. Output Raster Dataset—Set the output feature class that will contain the classification results.
   3. Model Definition—Select the pretrained or fine-tuned model .dlpk file.
   4. Arguments (optional)—Change the values of the arguments if required.
      • padding—Number of pixels at the border of image tiles from which predictions are blended for adjacent tiles. Increase its value to smooth the output while reducing edge artifacts. The maximum value of the padding can be half of the tile size value.
      • batch_size—Number of image tiles processed in each step of the model inference. This depends on the memory of your graphic card.
      • predict_background—If set to True, background class is also classified.
      • test_time_augmentation—Performs test time augmentation while predicting. If true, predictions of flipped and rotated variants of the input image will be merged into the final output.
      • tile_size—The width and height of image tiles into which the imagery is split for prediction.
      • radiometric_offset_correction—Corrects radiometric offset of -1000 in imageries sensed after January 25, 2022, in Sentinel 2 L1C imagery. (Note: Verify whether your data provider has already applied the offset for post January 2022 data, ; sources such as Azure and Copernicus require the radiometric_offset_correction parameter set as True. Set the parameter to False for AWS data, as it is already radiometric offset corrected and doesn't require correction again.)

   

7. Set the variables on the Environments tab as follows:
   1. Processing Extent—Select Current Display Extent or any other option from the drop-down menu.
   2. Cell Size (required)—Set the value to 10.

      The expected raster resolution is 10 meters.

   3. Processor Type—Select CPU or GPU.

      It is recommended that you select GPU, if available, and set GPU ID to specify the GPU to be used.

   

8. Click Run.

   The output layer is added to the map.