SL_ObjectDetectionRuntimeParameters Struct Reference

Data Fields
float	detection_confidence_threshold
	Defines the confidence threshold: interval between 1 and 99. A confidence of 1 meaning a low threshold, more uncertain objects and 99 very few but very precise objects. If the scene contains a lot of objects, increasing the confidence can slightly speed up the process, since every object instances are tracked. More...
int	object_class_filter [(int) SL_OBJECT_CLASS_LAST]
	Select which object types to detect and track. By default all classes are tracked. Fewer object types can slightly speed up the process, since every objects are tracked. Only the selected classes in the vector wilviewl be output. More...
int	object_confidence_threshold [(int) SL_OBJECT_CLASS_LAST]
	Defines a detection threshold for each classes, can be empty for some classes, ObjectDetectionRuntimeParameters::detection_confidence_threshold will be taken as fallback/default value.
int	minimum_keypoints_threshold
	Defines the minimum keypoints threshold. the SDK will outputs skeletons with more keypoints than this threshold it is useful for example to remove unstable fitting results when a skeleton is partially occluded.

Detailed Description

Sets the object detection runtime parameters.

Field Documentation

detection_confidence_threshold

float SL_ObjectDetectionRuntimeParameters::detection_confidence_threshold

Defines the confidence threshold: interval between 1 and 99. A confidence of 1 meaning a low threshold, more uncertain objects and 99 very few but very precise objects. If the scene contains a lot of objects, increasing the confidence can slightly speed up the process, since every object instances are tracked.

Default confidence threshold value, used as a fallback when ObjectDetectionRuntimeParameters::object_class_detection_confidence_threshold is partially set

object_class_filter

int SL_ObjectDetectionRuntimeParameters::object_class_filter[(int) SL_OBJECT_CLASS_LAST]

Select which object types to detect and track. By default all classes are tracked. Fewer object types can slightly speed up the process, since every objects are tracked. Only the selected classes in the vector wilviewl be output.

In order to get all the available classes, the filter vector must be empty.