Object Based Classification

 Extract spectral bands

The multiband imagery of the Louisville neighborhood currently uses the natural color band combination to display the imagery the way the human eye would see it. I needed to change the band combination to better distinguish urban features such as concrete from natural features such as vegetation.

The bands I extracted include Near Infrared (Band 4), which emphasizes vegetation; Red (Band 1), which emphasizes human-made objects and vegetation; and Blue (Band 3), which emphasizes water bodies.




Configure the Classification Wizard

I needed to open the Classification Wizard and configure its default parameters. The Classification Wizard walked me through the steps for image segmentation and classification.

Segment the image

For Spectral detail, replace the default value with 8.

For Spatial detail, replace the default value with 2.

For Minimum segment size in pixels, confirm that the value is 20.


Classify the imagery

1. modify the default schema to contain two parent classes: Impervious and Pervious

2. remove each of the default classes

3. add new classes with proper value

Reclassify errors



















Comments

Post a Comment

Popular posts from this blog

Final project(UAS data mapping mission)

Image
Required for the mission:         Mobile device with supporting mission planning software          A UAS Platform/Sensor of your choice I was asked to fly an assigned mission plot at PWA with this parameter. Altitude: 122m Lateral and Frontal Overlap: 80% Use the search function to find and open the Add Z Information (3D Analyst Tools) tool. This tool calculates properties of 3D shapes and appends the result to the attribute table of the input feature class. In this step, you will calculate the length of each sight line. Set the following parameters: Input Features: LOS_Lines Output Property: 3-Dimensional Length      The purpose of this project is to conduct a UAV mission to collect aerial imagery and data for a specific area at PWA(Purdue wildlife Area). The mission area has been assigned and the goal was to fly the assigned mission area while ensuring that the flight boundaries are slightly larger than the assigned area to ensure complete coverage. The Pilot(Jinwook paek) and my v
Read more

Volumetric analysis with UAS Data

Image
In a previous lab, I completed some ESRI tutorials regarding raster data analysis. This time, I engaged in raster data analysis using UAS data gathered over the course of a mine dredging operation. I needed to draw upon what I've learned in the ESRI tutorials so far. ·        Extract by mask This tool extracts the cells of a raster that correspond to the areas defined by a mask. The mask is typically a raster dataset where cells with a certain value represent the areas I want to extract. ·          Resample Resampling is the process of changing the resolution of a raster dataset. ·          Surface volume The Surface Volume tool calculates the volume between two surfaces. I began on the 4 th of July to where the mine operation tells of the dredging to take place, and for me to establish a base dataset to know how much material was added. They are also concerned about slope failure and low lying flat areas where water will collect. Because the area flown is pretty large,
Read more

Performing Line of Sight Analysis by Esri

Image
Performing Line of Sight Analysis by Esri Use the search function to find and open the Construct Sight Lines (3D Analyst Tools) tool. In the Geoprocessing pane, set the following parameters: Observer Points: Observers Target Features: ParadeRoute Output: ..\EsriTraining\ProLineSight\MyData\MyData.gdb\ SightLines Observer Height Field: SHAPE.Z Target Height Field: SHAPE.Z Sampling Distance:  30 Use the search function to find and open the Line Of Sight (3D Analyst Tools) tool. Set the following parameters: Input Surface: Elevation Input Line Features: SightLines Input Features: Buildings_subset Output Feature Class: ..\EsriTraining\ProLineSight\MyData\MyData.gdb\ LOS_Lines Use the search function to find and open the Add Z Information (3D Analyst Tools) tool. This tool calculates properties of 3D shapes and appends the result to the attribute table of the input feature class. In this step, you will calculate the length of each sight line.  Set the following parameters: Input Features: L
Read more