Anomaly Detection Workflow

Use the Anomaly Detection Workflow tool to identify the spectral or color differences between a test region and its neighboring pixels, or the entire dataset.

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

• Select Data
• Transform
• Reduce
• Detect
• Threshold
• Vectorize
• Review
• 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 > Anomaly Detection Workflow. The Select Data panel appears.
2. Select an input file and perform optional spatial and spectral subsetting and/or masking, then click OK.
3. Click Next.

Image Transform for Dimensionality Reduction

If you selected hyperspectral data for the input file, the Image Transform for Dimensionality Reduction panel appears (otherwise, for non-hyperspectral data the Detect Anomalies panel appears).

Hyperspectral data is largely redundant, with data from one band to the next generally changing very little. The Anomaly Detection Workflow provides the optional step of dimensionality reduction for reducing redundant spectral data, which can shorten processing time and improve detection accuracy. Dimensionality reduction generally refers to applying a mathematical transformation to the input dataset to create a new dataset in which the output bands are a linear combination of every input band. The leading bands in the transformed data generally contain the unique content in the image, while the latter bands contain mostly noise and otherwise redundant information.

1. Select one the following transforms to perform:

   • Forward Independent Component Analysis Transform: Performs an independent component analysis (ICA) procedure to transform a set of mixed, random signals into components that are mutually independent.

   • Forward Minimized Noise Fraction Transform: (default) Performs a minimum noise fraction (MNF) transform to determine the inherent dimensionality of image data, to segregate noise in the data, and to reduce the computational requirements for subsequent processing.

   • Forward Principal Component Analysis Transform: Performs a principal components analysis (PCA) transform to produce uncorrelated output bands, to segregate noise components, and to reduce the dimensionality of data sets.

2. Click Next.

Dimensionality Reduction

After you apply a transform, the Explained Variance plot and the Dimensionality Reduction panel appear.

The Explained Variance plot shows the sorted eigenvalue (or spatial coherence) contribution percentage of each band after image transform. Use the plot as a guidance for choosing number of bands to keep. For example, if you have a 200-band image and the plot indicates contributions from the first 14 bands contribute over 90% of the total variance. If this amount is suitable, you can use 14 as the number of bands to keep. The analysis after this step will use the first 14 bands of transformed image instead of all 200 bands, reducing dimensionality from 200 to 14.

1. In the Dimensionality Reduction panel, enter the Reduced Number of Bands.

2. Click Next.

Detect Anomalies

1. In the Detect Anomalies panel, select one of the following options from the Anomaly Detection Method drop-down list:
• RXD: (default) Uses the standard RXD algorithm.
• UTD: Uniform Target Detector, in which the anomaly is defined using (1 - μ) as the matched signature, rather than (r - μ). UTD and RXD work exactly the same, but instead of using a sample vector from the data (as with RXD), UTD uses the unit vector. UTD extracts background signatures as anomalies and provides a good estimate of the image background.
• RXD-UTD: A hybrid of the RXD and UTD methods, in which (r - 1) is used as the matched signature. This is a variant of the UTD approach. Subtracting UTD from RXD suppresses the background and enhances the anomalies of interest. The best condition to use RXD-UTD is when the anomalies have an energy level that is comparable to, or less than, that of the background. In this case, using UTD by itself does not detect the anomalies, but using RXD-UTD enhances them.
2. Select the Mean Calculation Method to use from the drop-down list. You can specify whether the mean spectrum should be derived from the full dataset (Global) or from a localized kernel around the pixel (Local).
3. If you choose Local, for the Mean Calculation Method, specify a Kernel Size, in pixels, around a given pixel that will be used to create a mean spectrum. The default value is 9. The allowable range is from 3 to 99, and the value must be an odd number (e.g., 9 = 9x9 pixels).
4. Select Yes or No to suppress vegetation anomalies in the RXD results. This option is best used when vegetation is a minor component of the image.
5. Click Next.

Threshold

The Threshold panel appears with a suggested threshold value applied to the image. The value shows the data range of the anomaly detection calculation result.

1. To change the threshold value, drag the bar, or type the desired value in the text box. Regions in the image that are red will be marked as anomalies, areas of interest for further review.
2. Click Next.

Vectorize Anomalies

In the Vectorize Anomalies panel, you will define how to create polygons around all the areas that were selected as anomalies.

1. Specify an odd number for the smoothing Kernel Size. The minimum value is 0 pixels (no smoothing), and the default value is 3.
2. 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.

Review Anomalies

The Review Anomalies panel appears with the vector threshold detection result. This step provides tools to review all detected anomalies. Click on a row to select it, or use the Ctrl or Shift keys to select multiple rows. Selected features will be highlighted and centered (as selected) in the view.

By default, all anomalies are initially flagged as “Pending.” You can flag features as “Approve”, “Reject”, or “Pending” using the color buttons provided. Polygons marked as “Approve” will be exported in the next step. If no features are marked as “Approve," then all “Pending” polygons will be exported.

Click Next.

Export Results

1. Enable the check box next to all results you wish to create, then enter a filename and location. The following are available:

   • Export Anomaly Detection Image

   • Export Anomaly Detection Vectors

   • Export Unthresholded Anomaly Detection Image

2. Click Finish.

See Also

Anomaly, Change, and Target Detection