Using ArcGIS Pro to engage in Value Added Data Analysis

Introduction:
The data collected by a UAS goes well beyond a pretty picture of what your house looks like from above. If gathered correctly, with the right sensor for the right job, your UAS data is a bountiful harvest waiting for you to exploit the value.  This lab goes through the steps of classifying an aerial image for different surface types using ArcGIS Pro.  The instructions for this lab were provided by ESRI Tutorial "Segment the Imagery"

Process:
The tutorial began with downloading the data and starting the ArcGIS Pro project file. The first step was to create a new layer by extracting bands 4, 1, and 3 from the imagery.  This created a false red image that shows vegitation as red and manmade objects like roads as grey.  This allows for easier classification later. The next step was to classify different segments of the image into groups based on spectral characteristics. To do this a Segment Mean Shift raster function was used. This new layer was saved as Lousiville_Segmented.  The next step of this process is to classify the different groups by specifying spectral signatures.  This is done with the image classification toolbar in ArcMap.  The user selects spectral signatures by drawing shapes in that signature then grouping like groupings together.  Then back in ArcGIS Pro, the groupings just created are imported into the classifier.  A few classifier tools are ran until a tif is created with all impervious and pervious objects on the image seperated  into two separate classes.  The next step is to determine if the new image accurately categorized objects into the proper classes, impervious or pervious.  The first step in this process is to create points then opening their attribute table and manually checking to make sure they were categorized correctly.  If they are not the user must make the appropriate adjustments. Then a confusion matrix was created to see the accuracy of the points added.  This resulted in a 92% overall confidence.  This allows the user to proceed in confidence. The next step was creating a graduated colors map to symbolize the areas with a high amount of impervious surface.  This was done by using a series of tools provided in the tutorial.

Final Map:

The Parcels with the highest area of impervious surfaces appear to be the ones that correspond to the location of the roads.  These parcels are large and are almost completely impervious.  The parcels with houses on are often an orange color due to the impervious surface like the house and the driveway mixed with an area of pervious surface like grass or ground.

Conclusions:
ArcGIS Pro makes data processing and analysis very streamlined.  It lays the process out for doing a task in a manner most people can easily understand.  The process for creating a map of impervious surfaces in the Louisville area was a simple procedure that resulted in a high quality map that could be useful in many situations.  The application of ArcGIS Pro with UAS Data is growing everyday.  It is growing increasingly easier to use UAS data in many everyday mapping platforms.