Use the model

You can use the Pedestrian Infrastructure Classification model in the Classify Pixels Using Deep Learning tool available in the Image Analyst toolbox in ArcGIS Pro.

1. Download the model.
2. Add the imagery layer in ArcGIS Pro.
3. Add 8-bit, RGB high-resolution (10 - 30 centimeters) imagery and zoom in to an area of interest.
   
4. Click Tools under the Analysis tab on the ribbon to open the Geoprocessing pane.

   

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

   

6. Set the variables on the Parameters tab as follows:
   1. Input Raster—Raster, mosaic dataset, or image service (10 - 30 centimeters spatial resolution) that can be classified.
   2. Output Raster Dataset—The name of the raster that will contain the result.
   3. Model Definition—This parameter value can be an Esri model definition JSON file (.emd), a JSON string, or a deep learning model package (.dlpk).
   4. Arguments—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 the graphics card.
      • 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.

   

7. Set the variables on the Environments tab as follows:
   1. Processing Extent—Select Current Display Extent or any other option from the given options.
   2. Cell Size—Change if required.

      Note:

      0.10 - 0.30 meters is the expected spatial resolution.

   3. Processor Type—Select CPU or GPU as needed.

      Note:

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

   

8. Click Run.

   Once processing is complete, the classified output of the raster layer is added to the map.

   

9. Right-click the output layer and click Symbology to apply appropriate symbology on the output raster to view the classified features in a better way.

   

10. Select Unique Values under Primary symbology in the Symbology pane. Apply different colors to different features as per your preference. We have applied No color to the background class for better visualization.

    

    

11. Convert the raster to polygons. A polygon feature layer can be used for further analysis, which can be difficult with a raster output.
    1. To convert the classified raster to polygon features, you must first run the Int tool, which converts each cell value of a raster to an integer. Click the Toolboxes tab in the Geoprocessing pane, and go to Image Analyst Tools, then the Math toolset, then the Trigonometric toolset, and the Int tool. Click the Int tool.
       
    2. Set the variables on the Parameters tab as follows:
       1. Input raster or constant value—The input raster to be converted to integer. Give the output of the Classify Pixels Using Deep Learning tool generated in previous steps as input here.
       2. Output raster—The output raster name.
       
    3. Click Run. The raster with integer cell values will be added to the map once processing is completed.
       
    4. Click the Toolboxes tab in the Geoprocessing pane, expand Conversion Tools, and browse to the Raster to Polygon tool under From Raster.
       
    5. Set the variables on the Parameters tab as follows:
       1. Input raster—Add the output of the Int tool generated in previous steps as input here.
       2. Field—Set the field used to assign values from the cells in the input raster to the polygons in the output dataset. Use an integer or a string field.
       
    6. Click Run. The feature layer will be added to the map once processing is completed.
       
    7. Right-click the output layer and click Symbology to apply appropriate symbology on the output feature layer, to view the classified features in a better way.
    8. Select Unique Values under Primary symbology in the Symbology pane and select gridcode in Field 1. Apply different colors/patterns to different features as per your preference. We have applied No color to the background class for better visualization.
       
       
12. Smoothen the polygons.
    1. Click the Toolboxes tab in the Geoprocessing pane, expand Cartography Tools, and browse to the Smooth Polygon tool under Generalization.
       
    2. Set the variables on the Parameters tab as follows:
       1. Input Features—Add the output of the Raster to Polygon tool generated in previous steps as input here.
       2. Smoothing Tolerance—Specify a tolerance used by the Polynomial Approximation with Exponential Kernel (PAEK) algorithm.

          A tolerance must be specified, and it must be greater than zero. You can choose a preferred unit; the default is the feature unit.

       
    3. Click Run. Once processing is completed, the final output is added to the map as shown below.