Back to Adaptive Vision Studio website

You are here: Start » Filter Reference » Deep Learning » DeepLearning_LocatePoints


Performs points localization using a trained deep-learning model.

Name Type Range Description
inImage Image Input image
inRoi Region* Area of interest
inDeepModel DeepModel_PointLocation Trained model
inMinDetectionScore Real 0.0 - 1.0 Minimal score of found points
inMinDistanceRatio Real* 0.01 - 1.0 Minimal distance between found points defined as portion of Feature Size
inOverlap Bool Add tiles overlapping to improve results quality
outLocations LocationArray Locations of found points
outClassIds IntegerArray Ids of found point classes
outClassNames StringArray Names of found point classes
outScores RealArray Scores of found points


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

Read more about pixel formats in Image documentation.


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 Empty image in DeepLearning_LocatePoints.
DomainError Empty ROI region in DeepLearning_LocatePoints
DomainError Invalid DeepModel in DeepLearning_LocatePoints.
DomainError Size of ROI differs from size of image in DeepLearning_LocatePoints
IoError Invalid service response - missing class id
IoError Invalid service response - missing class name
IoError Invalid service response - missing score

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, Adaptive Vision Studio Professional version.