Back to Aurora Vision Deep Learning website

You are here: Start » Computer Vision » Deep Learning » DL_LocateObjects

DL_LocateObjects


Header: AVLDL.h
Namespace: avl
Module: DL_LO

Performs locating objects using a pretrained deep learning model.

Syntax

C++
C#
 
void avl::DL_LocateObjects
(
	const avl::Image& inImage,
	atl::Optional<const avl::Region&> inRoi,
	const avl::LocateObjectsModelId& inModelId,
	const float inMinDetectionScore,
	const float inMaxOverlap,
	atl::Array<avl::ClassifiedRectangle>& outObjects
)

Parameters

Name Type Default Description
Input value inImage const Image& Input image
Input value inRoi Optional<const Region&> NIL Limits the area where objects may be located
Input value inModelId const LocateObjectsModelId& Identifier of a LocateObjects model
Input value inMinDetectionScore const float 0.5f Sets a minimum required score for an object to be returned.
Input value inMaxOverlap const float 0.2f Maximum overlap factor of two object allowed.
Output value outObjects Array<ClassifiedRectangle>&

Requirements

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

Read more about pixel formats in Image documentation.

Errors

List of possible exceptions:

Error type Description
DomainError Empty image in DL_LocateObjects.
DomainError Empty ROI region in DL_LocateObjects
DomainError Size of ROI differs from size of image in DL_LocateObjects
DomainError Not supported inImage pixel format in DL_LocateObjects. Supported formats: 1xUInt8, 3xUInt8.