DeepLearning_DetectFeatures


Header:AVLDL.h
Namespace:avl

Performs feature classification using trained deep-learning model.

Syntax

void avl::DeepLearning_DetectFeatures
(
	const avl::Image& inImage,
	atl::Optional<const avl::Region&> inRoi,
	const avl::DeepModel_FeatureDetection& inDeepModel,
	const bool inOverlap,
	atl::Array<avl::Image>& outHeatmaps,
	atl::Optional<avl::Image&> outFeature1 = atl::NIL,
	atl::Optional<avl::Image&> outFeature2 = atl::NIL,
	atl::Optional<avl::Image&> outFeature3 = atl::NIL,
	atl::Optional<avl::Image&> outFeature4 = atl::NIL
)

Parameters

Name Type Default Description
inImage const Image& Input image
inRoi Optional<const Region&> NIL Area of interest
inDeepModel const DeepModel_FeatureDetection& Trained model
inOverlap const bool True Add tiles overlapping to improve results quality
outHeatmaps Array<Image>& Returns heatmaps for all classes
outFeature1 Optional<Image&> NIL Returns heatmap for first feature class
outFeature2 Optional<Image&> NIL Returns heatmap for second feature class or empty image if class is not specified
outFeature3 Optional<Image&> NIL Returns heatmap for third feature class or empty image if class is not specified
outFeature4 Optional<Image&> NIL Returns heatmap for fourth feature class or empty image if class is not specified

Requirements

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

Read more about pixel formats in Image documentation.

Optional Outputs

The computation of following outputs can be switched off by passing value atl::NIL to these parameters: outFeature1, outFeature2, outFeature3, outFeature4.

Read more about Optional Outputs.

Hints

Loading Deep Learning Model may take longer timer. Consider using DeepLearning_LoadModel_FeatureDetection for pre-loading model before execution starts.

Remarks

  • Model provided on inDeepModel input will be loaded automatically on first usage of this filter.
  • 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. However, if stopping Deep Learning Service is not an option (e.g. program uses other Deep Learning filters) it is advised that this filter should be executed before other Deep Learning filters. Such "warm up" execution does not have to use real image or roi as long as provided image and roi have similar size.

See Also

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