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 land cover in images.

Supported imagery

The recommended imagery configuration is as follows:

• Resolution—High resolution (80–120 centimeters)
• Dynamic Range—8-Bit Unsigned
• Bands—Three bands (for example, red, green, and blue)
• Imagery—Orthorectified imagery (both on-the-fly and persisted ortho products)

Note:

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

If your imagery is already in the recommended imagery configuration, you can skip preprocessing and go to the Classify land cover section.

Process Worldview-2 imagery

1. Open ArcGIS Pro and browse to the image product in the Contents pane.
2. Expand the product (.imd file) and add the Pansharpen layer to the map.

   

3. Right-click the newly added layer and select Edit Function Chain
4. Click Stretch Function in the function chain window to edit the stretch properties.

   

5. In the Stretch Properties pane, do the following:
   1. On the General tab, change Output Pixel Type to 8 Bit Unsigned.

      

   2. Keep the default settings on the Parameters tab.

      

6. Click the Apply button to apply the changes.

   Click the play button in the top menu of the tool to apply the changes.

   

Classify land cover

Use the following steps to classify land cover from the imagery:

1. Download the High Resolution Land Cover Classification - USA model and add the imagery layer in ArcGIS Pro.
2. Zoom to an area of interest.

   

3. Browse to Tools on the Analysis tab.

   

4. 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.

   

5. Set the variables on the Parameters tab as follows:
   1. Input Raster—Select the imagery.
   2. Output Classified Raster—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.
      • batch_size—Number of image tiles processed in each step of the model inference. This depends on the memory of your graphic card.
      • tile_size—The width and height of image tiles into which the imagery is split for prediction.
      • 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.
      • predict_background—If set to True, the 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.
      • detailed_classes—The Chesapeake Bay land cover classes of the output labels. The default value is True for an output of 9 land cover classes. Use False for an output of 7 land cover classes.

      

      Note:

      To access the model directly from ArcGIS Pro (supported in ArcGIS Pro 2.7 and later), click the browse button and search for the model.

      

6. 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 1 (in meters).

      The expected raster resolution is 1 meter.

   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.

      

7. Click Run.

   The output layer is added to the map.

   

Fine-tune the model

To fine-tune a model with specific configuration, load the Esri Model Definition (EMD) files as specified below:

• Output raster has 9 classes—Default case. Use the .dlpkfile directly.
• Output raster has 7 classes—Unzip the .dlpk file and use HighResolutionLandCoverClassification_USA/7class/7class.emd.