Detection3DSettings< OBJECT_FIT_METHOD::OBJECT_REFINEMENT >

3D detection for approximately known position

Refine the position of an object with approximately known position. This detection method should be used if we have completely rigid objects that always match a CAD model and are alway at the approximately same position. The maximum number of detections is the number of initial poses, set in refinementParameters. However not every initialPose has to result i a found object, depending on score threshold and filters in refinementParameters.

Member Functions

virtual OBJECT_FIT_METHOD type() const override

JSON Type: string +Requirement: Must be OBJECT_FIT_METHOD::OBJECT_REFINEMENT. Type of the 3D detection.

Member Variables

cadPath

std::filesystem::path, default: \{""\} JSON Type: (optional) string +Requirement: Must be a path to a regular file. File path to the CAD file of the object used for the matching. Either cadPath or pointcloudPath need to be set.

pointcloudPath

std::filesystem::path, default: \{""\} JSON Type: (optional) string +Requirement: Must be a path to a regular file. File path to the Pointcloud file of the object used for the matching. Either cadPath or pointcloudPath need to be set.

trainingParameters

ModelTrainingParameters JSON Type: (optional) ModelTrainingParameters object Parameters used for training a model. All values of this object are optional as well.

refinementParameters

ObjectRefinementParameters JSON Type: (optional) ObjectRefinementParameters object Parameters used for detecting a model. All values of this object are optional as well.

maxNumObjects

std::optional< int >, default: {100} JSON Type: (optional) int UNIMPLEMENTED +Requirement: Must be greater than zero. Maximum number of objects that should be computed in the 3D detection pipeline.

[[-2]] roiPercentage:: float, default: \{0.8f\} JSON Type: float +Requirement: Must be greater than zero. Dilate 2D object detection results by this factor. The resulting area is used to determine all points that are considered for the geometric fit.

[[-3]] minNumPoints:: int, default: {50} JSON Type: (optional) int +Requirement: Must be greater than zero. Minimum number of points required for the geometric fit.

Enumerations

Table 1. OBJECT_FIT_METHOD
Value Description

PLANE_FIT

See Detection3DSettings<OBJECT_FIT_METHOD::PLANE_FIT>.

RANSAC_PLANE_FIT

See Detection3DSettings<OBJECT_FIT_METHOD::RANSAC_PLANE_FIT>.

MIXED_PLANE_FIT

See Detection3DSettings<OBJECT_FIT_METHOD::MIXED_PLANE_FIT>.

LINE_FIT_LONG_AXIS

See Detection3DSettings<OBJECT_FIT_METHOD::LINE_FIT_LONG_AXIS>.

GRIP_FROM_ENVIRONMENT

See Detection3DSettings<OBJECT_FIT_METHOD::GRIP_FROM_ENVIRONMENT>.

RANSAC_CYLINDER_FIT

See Detection3DSettings<OBJECT_FIT_METHOD::RANSAC_CYLINDER_FIT>.

OBJECT_MATCHING

See Detection3DSettings<OBJECT_FIT_METHOD::OBJECT_MATCHING>.

OBJECT_REFINEMENT

See Detection3DSettings<OBJECT_FIT_METHOD::OBJECT_REFINEMENT>.