Use the model

This model can be used through the Classify Pixels Using Deep Learning tool available in the Image Analyst toolbox in ArcGIS Pro. Ensure that the input imagery meets the supported configuration and follow the steps below to extract land parcels from it.

Supported imagery

Orthorectified imagery (on-the-fly or persisted ortho products) with the following characteristics:

• Resolution—High-resolution (40-50 centimeters)
• Bands—Three bands (for example, red, green, and blue)

  Note:

  Off-nadir imagery or imagery with a high obliquity angle will not produce suitable results.

1. Download the Extract Land Parcels ArcGIS Pro Project Template to use the Extract Land Parcels pretrained model, or a fine-tuned model as needed.
2. Start ArcGIS Pro and from the project selection screen, choose the Select another project template option.

   

3. Browse to the downloaded template and click OK.

   

4. Provide a name for your new project and click OK.

   

5. Use the Add Data button under the Map tab to add to the Contents pane the imagery on which to predict.
6. Zoom to an area of interest.

   

7. Browse to <Project_name>.tbx under Toolboxes in the Catalog pane to access the Extract Parcels tool.

   

8. Set the variables under the Parameters tab as follows:
   1. Input Raster—Select the imagery.
   2. Road Features—Select the roads polyline feature class.
   3. Road Width (optional)—Set the road width parameter.

      The default value is 5 meters.

   4. Tolerance Between Adjacent Parcels—Set the tolerance.

      The default is 3 meters.

      Note:

      The x,y tolerance refers to the minimum distance between coordinates before they are considered equal. It is used by integrate tool to reduce slivers between extracted parcels polygons.

   5. Residential Zone (optional)—Select the urban or residential area polygon feature class.
   6. Output feature class—Set the output feature class that will contain the extracted parcels.
   7. Model Definition (optional)—Select the pretrained, fine-tuned model .dlpk file.
   8. Model Arguments (optional)—Change the values of the arguments if required.
   9. Save Intermediate Raster—Check the check box to save the raster predicted by the model.
   10. Regularize Parcels—Check the check box to get regularized parcels.
   11. Cell Size (optional)—Change if required.

       The expected resolution is 0.5 meters.

   12. Processor Type—Select CPU/GPU as needed.

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

       

9. Set the variables under the Environments tab.
   1. Processing Extent—Select Current Display Extent or any other option from the drop-down menu as needed.

      If the Residential Zone parameter is provided, Processing Extent should be set to Default or the same extent as the zone layer.

      

10. Click Run to execute.

    As soon as processing finishes, the output layer is added to the map.