Setting up and running Segmentation

The first task in performing object-based classification is to divide a scene into homogeneous regions, or segments.

Setting up Segmentation consists of doing the following:

Select one or more source-image layers.
If necessary, constrain segmentation to a specific area of interest (AOI).
For more information about segmenting only an AOI, see Constraining segmentation to an area of interest.
Set up the parameters of the segmentation to perform, which consists of values for scale, shape, and compactness.
Enter a (path and) file name for the output file and, if necessary, the specific layer to which to write the segmentation.

Note: The segmentation algorithm respects NoData pixels in the source image. That is, a pixel defined as NoData by the NO_DATA_VALUE metadata tag will be excluded from the segmentation process. The file-level metadata tag is used as the default for each channel; however, channel-level tags, when available, will override the default. When metadata does not exist, each pixel in the input is considered valid.

To set up and run Segmentation

In the Object Analyst window, in the list under Operation, select Segmentation.
The display is refreshed to show the settings for segmentation.
Under Source Image Layers, click Select, and then in the Layer Selection window, do the following:
1. In the File box, type or select the file you want.
  If the file you want does not appear in the list, click Browse, and then select the file you want.
2. In the Select column of the table, click the row of each layer you want.
  To select all the available layers, click Select All. A check mark appears in the Select column for each layer you select.
3. Click OK.
Note: If you are working with SAR data, and you want to preprocess the image, beside SAR Preprocess, click Settings, and then see SAR preprocessing settings.
To constrain segmentation to a specific area of interest (AOI), do the following:
1. Switch to the Focus window, and then open the PCIDSK file (and layer) containing the polygons you want.
2. Switch to the Object Analyst window, select the Use area of interest check box, and then in the AOI layer list, select the PCIDSK file and layer containing the polygons you want.
Under Parameters, do the following:
1. In the Scale box, type or select a value to represent the scale that corresponds to the object size.
2. In the Shape box, type or select a value to represent the weight of the shape for the segmentation.
3. In the Compactness box, type or select a value to represent the compactness of the shape for the segmentation.
Some experimentation with these values may be necessary to achieve the result you want. A lower shape value, such as 0.1, places a high emphasis on color, which is typically the most important aspect of creating meaningful objects. A higher compactness weighting, such as 0.9, can produce object boundaries that are more compact, such as with crop fields or buildings.
Under Output, do the following:
1. In the File box, type or select the path and file name of the output file or, to select a folder, file name, or both, click Browse.
2. In the Layer box, type or select the layer you want.
Do one of the following:
- To add the operation to the Process Canvas box, click Add.
- To add the operation to the canvas and run the process, click Add and Run.