Sets the object detection runtime parameters. More...
Functions | |
ObjectDetectionRuntimeParameters (float detection_confidence_threshold=20.f, std::vector< OBJECT_CLASS > object_class_filter={}, std::map< OBJECT_CLASS, float > object_class_detection_confidence_threshold=std::map< OBJECT_CLASS, float >(), int minimum_keypoints_threshold=0) | |
Default constructor. Set all parameters to their default values. More... | |
bool | operator== (const ObjectDetectionRuntimeParameters ¶m1) const |
bool | operator!= (const ObjectDetectionRuntimeParameters ¶m1) const |
Attributes | |
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... | |
std::vector< OBJECT_CLASS > | object_class_filter |
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 will be output. More... | |
std::map< OBJECT_CLASS, float > | object_class_detection_confidence_threshold |
Defines a detection threshold for each classes, can be empty for some classes, ObjectDetectionRuntimeParameters::detection_confidence_threshold will be taken as fallback/default value. More... | |
int | minimum_keypoints_threshold |
Defines the minimum keypoints threshold. the SDK will outputs skeleton with more keypoints than this threshold. it is useful for example to remove unstable fitting results when a skeleton is partially occluded. More... | |
Sets the object detection runtime parameters.
The default constructor sets all parameters to their default settings.
ObjectDetectionRuntimeParameters | ( | float | detection_confidence_threshold = 20.f , |
std::vector< OBJECT_CLASS > | object_class_filter = {} , |
||
std::map< OBJECT_CLASS, float > | object_class_detection_confidence_threshold = std::map< OBJECT_CLASS, float >() , |
||
int | minimum_keypoints_threshold = 0 |
||
) |
Default constructor. Set all parameters to their default values.
bool operator== | ( | const ObjectDetectionRuntimeParameters & | param1 | ) | const |
Comparison operator ==
ObjectDetectionRuntimeParameters | to compare |
bool operator!= | ( | const ObjectDetectionRuntimeParameters & | param1 | ) | const |
Comparison operator !=
ObjectDetectionRuntimeParameters | to compare |
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.
Default confidence threshold value, used as a fallback when ObjectDetectionRuntimeParameters::object_class_detection_confidence_threshold is partially set
std::vector<OBJECT_CLASS> object_class_filter |
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 will be output.
In order to get all the available classes, the filter vector must be empty :
To select a set of specific object classes, like vehicles, persons and animals for instance:
std::map<OBJECT_CLASS, float> object_class_detection_confidence_threshold |
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 skeleton with more keypoints than this threshold. it is useful for example to remove unstable fitting results when a skeleton is partially occluded.