Header: AVLDL.h
Namespace: avl
Module: DeepLearning

Executes a Segment Instances model on a single input image.


void avl::DL_SegmentInstances
	const avl::Image& inImage,
	atl::Optional<const avl::Region&> inRoi,
	const avl::SegmentInstancesModelDirectory& inModelDirectory,
	const atl::Optional<float>& inMinDetectionScore,
	const atl::Optional<int>& inMaxObjectsCount,
	atl::Array<avl::Box>& outBoundingBoxes,
	atl::Array<int>& outClassIds,
	atl::Array<atl::String>& outClassNames,
	atl::Array<float>& outScores,
	atl::Array<avl::Region>& outMasks


Name Type Range Default Description
inImage const Image& Input image
inRoi Optional<const Region&> NIL Limits the area where objects may be located
inModelDirectory const SegmentInstancesModelDirectory& A Segment Instances model stored in a specific disk directory
inMinDetectionScore const Optional<float>& 0.0 - 1.0 NIL Sets a minimum required score for an object to be returned. If not set, a value determined during the training is used
inMaxObjectsCount const Optional<int>& 1 - NIL Limits maximum number of returned objects. If not set, a value determined during the training is used
outBoundingBoxes Array<Box>& Returns bounding boxes of the found objects
outClassIds Array<int>& Returns ids of the found object classes
outClassNames Array<String>& Returns names of the found objects classes
outScores Array<float>& Returns scores of the found objects
outMasks Array<Region>& 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 inModelDirectory 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 filters only communicates with service and cannot be used for a parallel computation.


List of possible exceptions:

Error type Description
DomainError Not supported inImage pixel format in DL_SegmentInstances.

See Also

  • Models for Deep Learning may be created using Adaptive Vision Deep Learning Editor or using Training Api.