Use the Build Object Detection Raster from ROI tool to build an object detection raster that can be used for classification by a deep learning model. It accepts an input raster and polygon region of interest (ROI) file consisting of rectangular bounding boxes drawn around features of interest.

An object detection raster is the same as a deep learning raster, except that it contains additional GeoJSON information about bounding boxes, stored in the raster metadata.

You can also write a script to build an object detection raster using the BuildObjectDetectionRasterFromROI task.

Follow these steps:

  1. In the ENVI Toolbox, select Deep Learning > Object Detection > Build Object Detection Raster from ROI. Or, click this sequence of buttons in the Deep Learning Guide Map: Object Detection > Train a New Model > Build Object Detection Raster from ROI. The Build Object Detection Raster from ROI dialog appears.

  2. In the Input Raster field, specify a training raster that will be used for training an object detection model.

  3. In the Input ROI field, specify one or more polygon ROIs drawn around features of interest. The ROIs can have irregular or rectangular shapes.

  4. In the Output Raster field, select a location and filename for the object detection raster.

  5. Enable the Display result check box to display the output in the view when processing is complete.

  6. To reuse these task settings in future ENVI sessions, save them to a file. Click the down arrow next to the OK button and select Save Parameter Values, then specify the location and filename to save to. Note that some parameter types, such as rasters, vectors, and ROIs, will not be saved with the file. To apply the saved task settings, click the down arrow and select Restore Parameter Values, then select the file where you previously stored your settings.

  7. To run the process in the background, click the down arrow and select Run Task in the Background. If an ENVI Server has been set up on the network, the Run Task on remote ENVI Server name is also available. The ENVI Server Job Console will show the progress of the job and will provide a link to display the result when processing is complete. See the ENVI Servers topic in ENVI Help for more information.

  8. Click OK. ENVI adds the resulting output to the Data Manager and Layer Manager.

  9. Pass the object detection raster to the Train TensorFlow Object Model tool. See the Train Object Detection Models topic for instructions.

Once the object detection raster has been created, you can view its labels using the View Object Detection Raster Labels tool.

See Also

Build Object Detection Raster From Annotation, Object Detection, View Object Detection Raster Labels