Module: DL_IS

Executes a Segment Instances model on a single input image.

Name Type Range Description
Input value inImage Image Input image
Input value inRoi Region* Limits the area where objects may be located
Input value inModelId SegmentInstancesModelId Segment Instances model stored in a specific disk directory
Input value inMinDetectionScore Real* 0.0 - 1.0 Sets a minimum required score for an object to be returned. If not set, a value determined during the training is used
Input value inMaxObjectsCount Integer* 1 - Limits maximum number of returned objects. If not set, a value determined during the training is used
Output value outBoundingBoxes BoxArray Returns bounding boxes of the found objects
Output value outClassIds IntegerArray Returns ids of the found object classes
Output value outClassNames StringArray Returns names of the found objects classes
Output value outScores RealArray Returns scores of the found objects
Output value outMasks RegionArray Returns masks of the found objects


For input inImage only pixel formats are supported: 1⨯uint8, 3⨯uint8.

Read more about pixel formats in Image documentation.


  • It is recommended that the deep learning model is deployed with DL_SegmentInstances_Deploy first and connected through the inModelId input.
  • If one decides not to use DL_SegmentInstances_Deploy, then the model will be loaded in the first iteration. It will take up to several seconds.


This filter should not be executed along with running Deep Learning Service as it may result in degraded performance or even out-of-memory errors.


This filter can throw an exception to report error. Read how to deal with errors in Error Handling.

List of possible exceptions:

Error type Description
DomainError Not supported inImage pixel format in AvsFilter_DL_SegmentInstances. Supported formats: 1xUInt8, 3xUInt8.

Complexity Level

This filter is available on Basic Complexity Level.

Disabled in Lite Edition

This filter is disabled in Lite Edition. It is available only in full, Aurora Vision Studio Professional version.

See Also