Change Detection Workflow

Use the Change Detection Workflow methods used to identify, describe, and quantify differences between images taken of the same scene at different times or under different conditions.

See the following for help on a particular step of the workflow:

• Select Data
• Image Registration
• Calculate Change
• Threshold
• Export

Workflow Tips

This workflow is not “modal,” meaning it will not block you from using other ENVI tools or working with additional data. This is useful in that the workflow will not prevent you from doing multiple things at a time. However, be aware that if you close all of your files in the middle of the workflow process, you might not be able to continue the workflow and will need to start over.

Navigating Workflow Steps

The number of steps provided in the workflow will depend on the input image data. For example, not all images will contain the data needed for every step; therefore, some steps will be skipped automatically.

Some steps can be optional; in those cases, the Perform this step radio button is selected by default. To skip that step and go to the next step in the workflow, select the Skip this step radio button, then click Next.

The timeline at the bottom of the workflow will display the order of steps available for the workflow and your data, and the title of your current location in the workflow will flash. The title is also an active link that you can click, to jump backward or forward to a desired step in the workflow.

Preview/Display Result

Some workflow steps provide options to preview the settings and/or to display the processed result.

• Enable the Preview check box to see a preview of the settings before you click OK and process the data. The preview is calculated only on the area in the view and uses the resolution level at which you are viewing the image. See Preview for details on the results. To preview a different area in your image, pan and zoom to the area of interest and re-enable the Preview option.
• Enable the Display result check box to display the raster in the view when processing is complete.

Open Workflow in Modeler

On the last step of the workflow, the Open Workflow in Modeler link will take your full workflow - the exact data, choices, and parameter values that you selected - and create a Model that can be manipulated in the ENVI Modeler. For example, you could create a Model to perform batch processing with multiple similar input datasets.

Select Data

1. From the Toolbox, select Workflows > Change Detection Workflow. The Select Data panel appears.
2. Select Input Raster 1 to represent the initial state and perform optional spatial and spectral subsetting and/or masking. Click OK.
3. Select Input Raster 2 to represent the final state and perform optional spatial and spectral subsetting and/or masking. Click OK.
4. Click Next.

Image Registration

The Image Registration panel appears after you select the input rasters for change detection. Select one of the following:

• If the images have already been registered, use the default option of Skip this step and click Next.

• If the images have not been registered, select Perform this step and click Next. ENVI will perform a series of ENVITasks to register the images.

Calculate Change

The Calculate Change panel appears after you perform (or skip) image registration.

1. Select one of the following methods:

   • Band Difference: Calculates the difference using the selected band of the input rasters. By default, the first band will be used. To use a different band, choose from Select Band drop-down list.

   • Vegetation Index Difference: Calculates the difference based on the selected vegetation index for the input rasters, then calculates the difference of the vegetation indices. By default, the first available index will be used. To use a different index, choose from the Vegetation Index drop-down list.

   • SAM Image Difference: Performs Spectral Angle Mapper (SAM) classification on the input rasters. The spectral angle for each pixel is measured, then similarity between the rasters is determined by calculating the angle between the spectra and treating them as vectors in space, with dimensionality equal to the number of bands.

   • ICA Difference: Performs Independent Component Analysis (ICA) on the input rasters, then calculates the difference on the selected band of the transformed images. By default, the first band of the transformed images will be used. To use a different band, choose from Select Band drop-down list.

   • MNF Difference: Performs Minimum Noise Fraction (MNF) analysis on the input rasters, then calculates the difference on the selected band of the transformed images. By default, the first band of the transformed images will be used. To use a different band, choose from Select Band drop-down list.

   • PCA Difference: Performs Principal Component Analysis (PCA) on the input rasters, then calculates the difference on the selected band of the transformed images. By default, the first band of the transformed images will be used. To use a different band, choose from Select Band drop-down list.

2. Click Next.

Threshold

The Threshold panel appears, showing the data range of the change detection calculation result. Use the thresholding step to highlight the areas of significant change and remove the pixels of small change.

If you selected the SAM Image Difference method in the Calculate Change panel, the plot will have one color region to show changes, with a single Value field and plot bar that you can adjust accordingly. If you selected any other calculation method, two-way thresholding will be available for the plot. The plot will have two color regions (one for positive changes, one for negative changes), with two Value fields and plot bars that you can adjust accordingly. Positive changes display in shades of blue, grading from gray (no change) to bright blue (largest positive change). Negative changes display in shades of red, grading from gray (no change) to bright red (largest negative change).

1. To change the threshold value, drag the bar(s) in the plot, or type the desired value(s) in the text box. Regions in the image that are black will be masked as areas of no interest.
2. Click Next.

Vectorize Changes

In the Vectorize Changes panel, you can define how to create polygons around all the areas that were changed.

1. Specify an odd number for the Minimum Pixels to consider. Regions with fewer pixels than this value will be discarded in the output shapefile. The minimum value is 0 pixels, and the default value is 3.
2. Specify an odd number for the smoothing Smooth Kernel Size. The minimum value is 0 pixels (no smoothing), and the default value is 3.
3. Click Next.

Export Results

Select the products to create in the Export Results panel.

1. Enable check boxes for the desired exports. A Filename field will appear for the exports you enable; enter a filename and location for each. The options are:

   • Export Classification Raster

   • Export Shapefile

   • Export ROIs

   • Export GeoJSON

   • Export KML

   • Export Difference Image

2. Click Finish.

See Also

Change Detection Analysis, Anomaly, Change, and Target Detection