Structure containing a set of runtime properties of a certain class ID for the object detection module using a custom model. More...
Data Fields | |
int | class_id |
Index of the class represented by this set of properties. | |
bool | enabled |
Whether the object object is kept or not. | |
float | detection_confidence_threshold |
Confidence threshold. More... | |
bool | is_grounded |
Provide hypothesis about the object movements (degrees of freedom or DoF) to improve the object tracking. More... | |
bool | is_static |
Provide hypothesis about the object staticity to improve the object tracking. More... | |
float | tracking_timeout |
Maximum tracking time threshold (in seconds) before dropping the tracked object when unseen for this amount of time. More... | |
float | tracking_max_dist |
Maximum tracking distance threshold (in meters) before dropping the tracked object when unseen for this amount of meters. More... | |
float | max_box_width_normalized |
Maximum allowed width normalized to the image size. More... | |
float | min_box_width_normalized |
Minimum allowed width normalized to the image size. More... | |
float | max_box_height_normalized |
Maximum allowed height normalized to the image size. More... | |
float | min_box_height_normalized |
Minimum allowed height normalized to the image size. More... | |
float | max_box_width_meters |
Maximum allowed 3D width. More... | |
float | min_box_width_meters |
Minimum allowed 3D width. More... | |
float | max_box_height_meters |
Maximum allowed 3D height. More... | |
float | min_box_height_meters |
Minimum allowed 3D height. More... | |
enum SL_OBJECT_SUBCLASS | native_mapped_class |
For increased accuracy, the native sl::OBJECT_SUBCLASS mapping, if any. More... | |
enum SL_OBJECT_ACCELERATION_PRESET | object_acceleration_preset |
Preset defining the expected maximum acceleration of the tracked object. More... | |
float | max_allowed_acceleration |
Manually override the acceleration preset. More... | |
Structure containing a set of runtime properties of a certain class ID for the object detection module using a custom model.
The default constructor sets all parameters to their default settings.
float SL_CustomObjectDetectionProperties::detection_confidence_threshold |
Confidence threshold.
From 1 to 100, with 1 meaning a low threshold, more uncertain objects and 99 very few but very precise objects.
Default: 20.f
bool SL_CustomObjectDetectionProperties::is_grounded |
Provide hypothesis about the object movements (degrees of freedom or DoF) to improve the object tracking.
bool SL_CustomObjectDetectionProperties::is_static |
Provide hypothesis about the object staticity to improve the object tracking.
float SL_CustomObjectDetectionProperties::tracking_timeout |
Maximum tracking time threshold (in seconds) before dropping the tracked object when unseen for this amount of time.
By default, let the tracker decide internally based on the internal sub class of the tracked object.
float SL_CustomObjectDetectionProperties::tracking_max_dist |
Maximum tracking distance threshold (in meters) before dropping the tracked object when unseen for this amount of meters.
By default, do not discard tracked object based on distance. Only valid for static object.
float SL_CustomObjectDetectionProperties::max_box_width_normalized |
Maximum allowed width normalized to the image size.
Any prediction bigger than that will be filtered out. Default: -1 (no filtering)
float SL_CustomObjectDetectionProperties::min_box_width_normalized |
Minimum allowed width normalized to the image size.
Any prediction smaller than that will be filtered out. Default: -1 (no filtering)
float SL_CustomObjectDetectionProperties::max_box_height_normalized |
Maximum allowed height normalized to the image size.
Any prediction bigger than that will be filtered out. Default: -1 (no filtering)
float SL_CustomObjectDetectionProperties::min_box_height_normalized |
Minimum allowed height normalized to the image size.
Any prediction smaller than that will be filtered out. Default: -1 (no filtering)
float SL_CustomObjectDetectionProperties::max_box_width_meters |
Maximum allowed 3D width.
Any prediction bigger than that will be either discarded (if object is tracked and in SEARCHING state) or clamped. Default: -1 (no filtering)
float SL_CustomObjectDetectionProperties::min_box_width_meters |
Minimum allowed 3D width.
Any prediction smaller than that will be either discarded (if object is tracked and in SEARCHING state) or clamped. Default: -1 (no filtering)
float SL_CustomObjectDetectionProperties::max_box_height_meters |
Maximum allowed 3D height.
Any prediction bigger than that will be either discarded (if object is tracked and in SEARCHING state) or clamped. Default: -1 (no filtering)
float SL_CustomObjectDetectionProperties::min_box_height_meters |
Minimum allowed 3D height.
Any prediction smaller than that will be either discarded (if object is tracked and in SEARCHING state) or clamped. Default: -1 (no filtering)
enum SL_OBJECT_SUBCLASS SL_CustomObjectDetectionProperties::native_mapped_class |
For increased accuracy, the native sl::OBJECT_SUBCLASS mapping, if any.
Native objects have refined internal parameters for better 3D projection and tracking accuracy. If one of the custom objects can be mapped to one the native sl::OBJECT_SUBCLASS, this can help to boost the tracking accuracy.
Default: no mapping
enum SL_OBJECT_ACCELERATION_PRESET SL_CustomObjectDetectionProperties::object_acceleration_preset |
Preset defining the expected maximum acceleration of the tracked object.
Determines how the ZED SDK interprets object acceleration, affecting tracking behavior and predictions.
float SL_CustomObjectDetectionProperties::max_allowed_acceleration |
Manually override the acceleration preset.
If set, this value takes precedence over the selected preset, allowing for a custom maximum acceleration. Unit is m/s^2. Defaults: NaN