CustomObjectDetectionProperties Struct Reference

Structure containing a set of runtime properties of a certain class ID for the object detection module using a custom model. More...

Attributes

int ClassID
 Index of the class represented by this set of properties. More...
 
bool enabled
 Whether the object object is kept or not. More...
 
float detectionConfidenceThreshold
 Confidence threshold. From 1 to 100, with 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 instance is tracked. More...
 
bool isGrounded
 Provide hypothesis about the object movements (degrees of freedom or DoF) to improve the object tracking. More...
 
bool isStatic
 Provide hypothesis about the object staticity to improve the object tracking. More...
 
float trackingTimeout
 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. More...
 
float trackingMaxDist
 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. More...
 
float maxBoxWidthNormalized
 Maximum allowed width normalized to the image size. Any prediction bigger than that will be filtered out. Default: -1 (no filtering) More...
 
float minBoxWidthNormalized
 Minimum allowed width normalized to the image size. Any prediction smaller than that will be filtered out. Default: -1 (no filtering) More...
 
float maxBoxHeightNormalized
 Maximum allowed height normalized to the image size. Any prediction bigger than that will be filtered out. Default: -1 (no filtering) More...
 
float minBoxHeightNormalized
 Minimum allowed height normalized to the image size. Any prediction smaller than that will be filtered out. Default: -1 (no filtering) More...
 
float maxBoxWidthMeters
 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) More...
 
float minBoxWidthMeters
 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) More...
 
float maxBoxHeightMeters
 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) More...
 
float minBoxHeightMeters
 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) More...
 
OBJECT_SUBCLASS nativeMappedClass
 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 More...
 
OBJECT_ACCELERATION_PRESET objectAccelerationPreset
 Preset defining the expected maximum acceleration of the tracked object. Determines how the ZED SDK interprets object acceleration, affecting tracking behavior and predictions. Default: OBJECT_ACCELERATION_PRESET.DEFAULT More...
 
float maxAllowedAcceleration
 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. Default: nan (no override) More...
 

Detailed Description

Structure containing a set of runtime properties of a certain class ID for the object detection module using a custom model.

Variables

◆ ClassID

int ClassID

Index of the class represented by this set of properties.

◆ enabled

bool enabled

Whether the object object is kept or not.

◆ detectionConfidenceThreshold

float detectionConfidenceThreshold

Confidence threshold. From 1 to 100, with 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 instance is tracked.

◆ isGrounded

bool isGrounded

Provide hypothesis about the object movements (degrees of freedom or DoF) to improve the object tracking.

  • true: 2 DoF projected alongside the floor plane. Case for object standing on the ground such as person, vehicle, etc. The projection implies that the objects cannot be superposed on multiple horizontal levels.
  • false: 6 DoF (full 3D movements are allowed).

◆ isStatic

bool isStatic

Provide hypothesis about the object staticity to improve the object tracking.

  • true: the object will be assumed to never move nor being moved.
  • false: the object will be assumed to be able to move or being moved.

◆ trackingTimeout

float trackingTimeout

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.

◆ trackingMaxDist

float trackingMaxDist

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.

◆ maxBoxWidthNormalized

float maxBoxWidthNormalized

Maximum allowed width normalized to the image size. Any prediction bigger than that will be filtered out. Default: -1 (no filtering)

◆ minBoxWidthNormalized

float minBoxWidthNormalized

Minimum allowed width normalized to the image size. Any prediction smaller than that will be filtered out. Default: -1 (no filtering)

◆ maxBoxHeightNormalized

float maxBoxHeightNormalized

Maximum allowed height normalized to the image size. Any prediction bigger than that will be filtered out. Default: -1 (no filtering)

◆ minBoxHeightNormalized

float minBoxHeightNormalized

Minimum allowed height normalized to the image size. Any prediction smaller than that will be filtered out. Default: -1 (no filtering)

◆ maxBoxWidthMeters

float maxBoxWidthMeters

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)

◆ minBoxWidthMeters

float minBoxWidthMeters

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)

◆ maxBoxHeightMeters

float maxBoxHeightMeters

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)

◆ minBoxHeightMeters

float minBoxHeightMeters

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)

◆ nativeMappedClass

OBJECT_SUBCLASS nativeMappedClass

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

◆ objectAccelerationPreset

OBJECT_ACCELERATION_PRESET objectAccelerationPreset

Preset defining the expected maximum acceleration of the tracked object. Determines how the ZED SDK interprets object acceleration, affecting tracking behavior and predictions. Default: OBJECT_ACCELERATION_PRESET.DEFAULT

◆ maxAllowedAcceleration

float maxAllowedAcceleration

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. Default: nan (no override)