Class containing a set of runtime properties of a certain class ID for the object detection module using a custom model. More...
Functions | |
| CustomObjectDetectionProperties | __cinit__ (self, bool, enabled=True, float, detection_confidence_threshold=20., bool, is_grounded=True, bool, is_static=False, float, tracking_timeout=-1., float, tracking_max_dist=-1., float, max_box_width_normalized=-1., float, min_box_width_normalized=-1., float, max_box_height_normalized=-1., float, min_box_height_normalized=-1., float, max_box_width_meters=-1., float, min_box_width_meters=-1., float, max_box_height_meters=-1., float, min_box_height_meters=-1., OBJECT_SUBCLASS native_mapped_class=OBJECT_SUBCLASS.LAST, OBJECT_ACCELERATION_PRESET object_acceleration_preset=OBJECT_ACCELERATION_PRESET.DEFAULT, float, max_allowed_acceleration=NAN) |
| Default constructor. More... | |
| bool | enabled (self) |
| Whether the object object is kept or not. | |
| float | detection_confidence_threshold (self) |
| Confidence threshold. More... | |
| bool | is_grounded (self) |
| Provide hypothesis about the object movements (degrees of freedom or DoF) to improve the object tracking. More... | |
| bool | is_static (self) |
| Provide hypothesis about the object staticity to improve the object tracking. More... | |
| float | tracking_timeout (self) |
| Maximum tracking time threshold (in seconds) before dropping the tracked object when unseen for this amount of time. More... | |
| float | tracking_max_dist (self) |
| Maximum tracking distance threshold (in meters) before dropping the tracked object when unseen for this amount of meters. More... | |
| float | max_box_width_normalized (self) |
| Maximum allowed width normalized to the image size. More... | |
| float | min_box_width_normalized (self) |
| Minimum allowed width normalized to the image size. More... | |
| float | max_box_height_normalized (self) |
| Maximum allowed height normalized to the image size. More... | |
| float | min_box_height_normalized (self) |
| Minimum allowed height normalized to the image size. More... | |
| float | max_box_width_meters (self) |
| Maximum allowed 3D width. More... | |
| float | min_box_width_meters (self) |
| Minimum allowed 3D width. More... | |
| float | max_box_height_meters (self) |
| Maximum allowed 3D height. More... | |
| float | min_box_height_meters (self) |
| Minimum allowed 3D height. More... | |
| OBJECT_SUBCLASS | native_mapped_class (self) |
| For increased accuracy, the native sl.OBJECT_SUBCLASS mapping, if any. More... | |
| OBJECT_ACCELERATION_PRESET | object_acceleration_preset (self) |
| Preset defining the expected maximum acceleration of the tracked object. More... | |
| float | max_allowed_acceleration (self) |
| Manually override the acceleration preset. More... | |
Class 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.
| CustomObjectDetectionProperties __cinit__ | ( | self, | |
| bool, | |||
enabled = True, |
|||
| float, | |||
detection_confidence_threshold = 20., |
|||
| bool, | |||
is_grounded = True, |
|||
| bool, | |||
is_static = False, |
|||
| float, | |||
tracking_timeout = -1., |
|||
| float, | |||
tracking_max_dist = -1., |
|||
| float, | |||
max_box_width_normalized = -1., |
|||
| float, | |||
min_box_width_normalized = -1., |
|||
| float, | |||
max_box_height_normalized = -1., |
|||
| float, | |||
min_box_height_normalized = -1., |
|||
| float, | |||
max_box_width_meters = -1., |
|||
| float, | |||
min_box_width_meters = -1., |
|||
| float, | |||
max_box_height_meters = -1., |
|||
| float, | |||
min_box_height_meters = -1., |
|||
| OBJECT_SUBCLASS | native_mapped_class = OBJECT_SUBCLASS.LAST, |
||
| OBJECT_ACCELERATION_PRESET | object_acceleration_preset = OBJECT_ACCELERATION_PRESET.DEFAULT, |
||
| float, | |||
max_allowed_acceleration = NAN |
|||
| ) |
Default constructor.
All the parameters are set to their default values.
| detection_confidence_threshold | : Chosen detection_confidence_threshold |
| object_class_filter | : Chosen object_class_filter |
| object_class_detection_confidence_threshold | : Chosen object_class_detection_confidence_threshold |
| float detection_confidence_threshold | ( | self | ) |
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 is_grounded | ( | self | ) |
Provide hypothesis about the object movements (degrees of freedom or DoF) to improve the object tracking.
| bool is_static | ( | self | ) |
Provide hypothesis about the object staticity to improve the object tracking.
| float tracking_timeout | ( | self | ) |
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 tracking_max_dist | ( | self | ) |
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 max_box_width_normalized | ( | self | ) |
Maximum allowed width normalized to the image size.
Any prediction bigger than that will be filtered out. Default: -1 (no filtering)
| float min_box_width_normalized | ( | self | ) |
Minimum allowed width normalized to the image size.
Any prediction smaller than that will be filtered out. Default: -1 (no filtering)
| float max_box_height_normalized | ( | self | ) |
Maximum allowed height normalized to the image size.
Any prediction bigger than that will be filtered out. Default: -1 (no filtering)
| float min_box_height_normalized | ( | self | ) |
Minimum allowed height normalized to the image size.
Any prediction smaller than that will be filtered out. Default: -1 (no filtering)
| float max_box_width_meters | ( | self | ) |
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 min_box_width_meters | ( | self | ) |
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 max_box_height_meters | ( | self | ) |
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 min_box_height_meters | ( | self | ) |
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)
| OBJECT_SUBCLASS native_mapped_class | ( | self | ) |
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
| OBJECT_ACCELERATION_PRESET object_acceleration_preset | ( | self | ) |
Preset defining the expected maximum acceleration of the tracked object.
Determines how the ZED SDK interprets object acceleration, affecting tracking behavior and predictions. Default: Default
| float max_allowed_acceleration | ( | self | ) |
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.