SACSegmentation represents the Nodelet segmentation class for Sample Consensus methods and models, in the sense that it just creates a Nodelet wrapper for generic-purpose SAC-based segmentation. More...
#include <pcl/segmentation/sac_segmentation.h>
Inheritance diagram for pcl::SACSegmentation< PointT >:
Collaboration diagram for pcl::SACSegmentation< PointT >:
Public Types | |
| using | PointCloud = pcl::PointCloud< PointT > |
| using | PointCloudPtr = typename PointCloud::Ptr |
| using | PointCloudConstPtr = typename PointCloud::ConstPtr |
| using | SearchPtr = typename pcl::search::Search< PointT >::Ptr |
| using | SampleConsensusPtr = typename SampleConsensus< PointT >::Ptr |
| using | SampleConsensusModelPtr = typename SampleConsensusModel< PointT >::Ptr |
| Public Types inherited from pcl::PCLBase< PointT > | |
| using | PointCloud = pcl::PointCloud< PointT > |
| using | PointCloudPtr = typename PointCloud::Ptr |
| using | PointCloudConstPtr = typename PointCloud::ConstPtr |
| using | PointIndicesPtr = PointIndices::Ptr |
| using | PointIndicesConstPtr = PointIndices::ConstPtr |
Public Member Functions | |
| SACSegmentation (bool random=false) | |
| Empty constructor. More... | |
| ~SACSegmentation () override=default | |
| Empty destructor. More... | |
| void | setModelType (int model) |
| The type of model to use (user given parameter). More... | |
| int | getModelType () const |
| Get the type of SAC model used. More... | |
| SampleConsensusPtr | getMethod () const |
| Get a pointer to the SAC method used. More... | |
| SampleConsensusModelPtr | getModel () const |
| Get a pointer to the SAC model used. More... | |
| void | setMethodType (int method) |
| The type of sample consensus method to use (user given parameter). More... | |
| int | getMethodType () const |
| Get the type of sample consensus method used. More... | |
| void | setDistanceThreshold (double threshold) |
| Distance to the model threshold (user given parameter). More... | |
| double | getDistanceThreshold () const |
| Get the distance to the model threshold. More... | |
| void | setMaxIterations (int max_iterations) |
| Set the maximum number of iterations before giving up. More... | |
| int | getMaxIterations () const |
| Get maximum number of iterations before giving up. More... | |
| void | setProbability (double probability) |
| Set the probability of choosing at least one sample free from outliers. More... | |
| double | getProbability () const |
| Get the probability of choosing at least one sample free from outliers. More... | |
| void | setNumberOfThreads (const int nr_threads=-1) |
| Set the number of threads to use or turn off parallelization. More... | |
| void | setOptimizeCoefficients (bool optimize) |
| Set to true if a coefficient refinement is required. More... | |
| bool | getOptimizeCoefficients () const |
| Get the coefficient refinement internal flag. More... | |
| void | setRadiusLimits (const double &min_radius, const double &max_radius) |
| Set the minimum and maximum allowable radius limits for the model (applicable to models that estimate a radius) More... | |
| void | getRadiusLimits (double &min_radius, double &max_radius) |
| Get the minimum and maximum allowable radius limits for the model as set by the user. More... | |
| void | setSamplesMaxDist (const double &radius, SearchPtr search) |
| Set the maximum distance allowed when drawing random samples. More... | |
| void | getSamplesMaxDist (double &radius) |
| Get maximum distance allowed when drawing random samples. More... | |
| void | setAxis (const Eigen::Vector3f &ax) |
| Set the axis along which we need to search for a model perpendicular to. More... | |
| Eigen::Vector3f | getAxis () const |
| Get the axis along which we need to search for a model perpendicular to. More... | |
| void | setEpsAngle (double ea) |
| Set the angle epsilon (delta) threshold. More... | |
| double | getEpsAngle () const |
| Get the epsilon (delta) model angle threshold in radians. More... | |
| virtual void | segment (PointIndices &inliers, ModelCoefficients &model_coefficients) |
| Base method for segmentation of a model in a PointCloud given by <setInputCloud (), setIndices ()> More... | |
| Public Member Functions inherited from pcl::PCLBase< PointT > | |
| PCLBase () | |
| Empty constructor. More... | |
| PCLBase (const PCLBase &base) | |
| Copy constructor. More... | |
| virtual | ~PCLBase ()=default |
| Destructor. More... | |
| virtual void | setInputCloud (const PointCloudConstPtr &cloud) |
| Provide a pointer to the input dataset. More... | |
| PointCloudConstPtr const | getInputCloud () const |
| Get a pointer to the input point cloud dataset. More... | |
| virtual void | setIndices (const IndicesPtr &indices) |
| Provide a pointer to the vector of indices that represents the input data. More... | |
| virtual void | setIndices (const IndicesConstPtr &indices) |
| Provide a pointer to the vector of indices that represents the input data. More... | |
| virtual void | setIndices (const PointIndicesConstPtr &indices) |
| Provide a pointer to the vector of indices that represents the input data. More... | |
| virtual void | setIndices (std::size_t row_start, std::size_t col_start, std::size_t nb_rows, std::size_t nb_cols) |
| Set the indices for the points laying within an interest region of the point cloud. More... | |
| IndicesPtr | getIndices () |
| Get a pointer to the vector of indices used. More... | |
| IndicesConstPtr const | getIndices () const |
| Get a pointer to the vector of indices used. More... | |
| const PointT & | operator[] (std::size_t pos) const |
| Override PointCloud operator[] to shorten code. More... | |
Protected Member Functions | |
| virtual bool | initSACModel (const int model_type) |
| Initialize the Sample Consensus model and set its parameters. More... | |
| virtual void | initSAC (const int method_type) |
| Initialize the Sample Consensus method and set its parameters. More... | |
| virtual std::string | getClassName () const |
| Class get name method. More... | |
| Protected Member Functions inherited from pcl::PCLBase< PointT > | |
| bool | initCompute () |
| This method should get called before starting the actual computation. More... | |
| bool | deinitCompute () |
| This method should get called after finishing the actual computation. More... | |
Protected Attributes | |
| SampleConsensusModelPtr | model_ {nullptr} |
| The model that needs to be segmented. More... | |
| SampleConsensusPtr | sac_ {nullptr} |
| The sample consensus segmentation method. More... | |
| int | model_type_ {-1} |
| The type of model to use (user given parameter). More... | |
| int | method_type_ {0} |
| The type of sample consensus method to use (user given parameter). More... | |
| double | threshold_ {0.0} |
| Distance to the model threshold (user given parameter). More... | |
| bool | optimize_coefficients_ {true} |
| Set to true if a coefficient refinement is required. More... | |
| double | radius_min_ {-std::numeric_limits<double>::max()} |
| The minimum and maximum radius limits for the model. More... | |
| double | radius_max_ {std::numeric_limits<double>::max()} |
| double | samples_radius_ {0.0} |
| The maximum distance of subsequent samples from the first (radius search) More... | |
| SearchPtr | samples_radius_search_ {nullptr} |
| The search object for picking subsequent samples using radius search. More... | |
| double | eps_angle_ {0.0} |
| The maximum allowed difference between the model normal and the given axis. More... | |
| Eigen::Vector3f | axis_ {Eigen::Vector3f::Zero()} |
| The axis along which we need to search for a model perpendicular to. More... | |
| int | max_iterations_ {50} |
| Maximum number of iterations before giving up (user given parameter). More... | |
| int | threads_ {-1} |
| The number of threads the scheduler should use, or a negative number if no parallelization is wanted. More... | |
| double | probability_ {0.99} |
| Desired probability of choosing at least one sample free from outliers (user given parameter). More... | |
| bool | random_ |
| Set to true if we need a random seed. More... | |
| Protected Attributes inherited from pcl::PCLBase< PointT > | |
| PointCloudConstPtr | input_ |
| The input point cloud dataset. More... | |
| IndicesPtr | indices_ |
| A pointer to the vector of point indices to use. More... | |
| bool | use_indices_ |
| Set to true if point indices are used. More... | |
| bool | fake_indices_ |
| If no set of indices are given, we construct a set of fake indices that mimic the input PointCloud. More... | |
Detailed Description
template<typename PointT>
class pcl::SACSegmentation< PointT >
SACSegmentation represents the Nodelet segmentation class for Sample Consensus methods and models, in the sense that it just creates a Nodelet wrapper for generic-purpose SAC-based segmentation.
Definition at line 64 of file sac_segmentation.h.
Member Typedef Documentation
◆ PointCloud
| using pcl::SACSegmentation< PointT >::PointCloud = pcl::PointCloud<PointT> |
Definition at line 73 of file sac_segmentation.h.
◆ PointCloudConstPtr
| using pcl::SACSegmentation< PointT >::PointCloudConstPtr = typename PointCloud::ConstPtr |
Definition at line 75 of file sac_segmentation.h.
◆ PointCloudPtr
| using pcl::SACSegmentation< PointT >::PointCloudPtr = typename PointCloud::Ptr |
Definition at line 74 of file sac_segmentation.h.
◆ SampleConsensusModelPtr
| using pcl::SACSegmentation< PointT >::SampleConsensusModelPtr = typename SampleConsensusModel<PointT>::Ptr |
Definition at line 79 of file sac_segmentation.h.
◆ SampleConsensusPtr
| using pcl::SACSegmentation< PointT >::SampleConsensusPtr = typename SampleConsensus<PointT>::Ptr |
Definition at line 78 of file sac_segmentation.h.
◆ SearchPtr
| using pcl::SACSegmentation< PointT >::SearchPtr = typename pcl::search::Search<PointT>::Ptr |
Definition at line 76 of file sac_segmentation.h.
Constructor & Destructor Documentation
◆ SACSegmentation()
|
inline |
Empty constructor.
- Parameters
-
[in] random if true set the random seed to the current time, else set to 12345 (default: false)
Definition at line 84 of file sac_segmentation.h.
◆ ~SACSegmentation()
|
overridedefault |
Empty destructor.
Member Function Documentation
◆ getAxis()
|
inline |
Get the axis along which we need to search for a model perpendicular to.
Definition at line 218 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::axis_.
◆ getClassName()
|
inlineprotectedvirtual |
Class get name method.
Reimplemented in pcl::SACSegmentationFromNormals< PointT, PointNT >.
Definition at line 297 of file sac_segmentation.h.
◆ getDistanceThreshold()
|
inline |
Get the distance to the model threshold.
Definition at line 127 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::threshold_.
◆ getEpsAngle()
|
inline |
Get the epsilon (delta) model angle threshold in radians.
Definition at line 228 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::eps_angle_.
◆ getMaxIterations()
|
inline |
Get maximum number of iterations before giving up.
Definition at line 137 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::max_iterations_.
◆ getMethod()
|
inline |
Get a pointer to the SAC method used.
Definition at line 103 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::sac_.
◆ getMethodType()
|
inline |
Get the type of sample consensus method used.
Definition at line 117 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::method_type_.
◆ getModel()
|
inline |
Get a pointer to the SAC model used.
Definition at line 107 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::model_.
◆ getModelType()
|
inline |
Get the type of SAC model used.
Definition at line 99 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::model_type_.
◆ getOptimizeCoefficients()
|
inline |
Get the coefficient refinement internal flag.
Definition at line 164 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::optimize_coefficients_.
◆ getProbability()
|
inline |
Get the probability of choosing at least one sample free from outliers.
Definition at line 147 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::probability_.
◆ getRadiusLimits()
|
inline |
Get the minimum and maximum allowable radius limits for the model as set by the user.
- Parameters
-
[out] min_radius the resultant minimum radius model [out] max_radius the resultant maximum radius model
Definition at line 183 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::radius_max_, and pcl::SACSegmentation< PointT >::radius_min_.
◆ getSamplesMaxDist()
|
inline |
Get maximum distance allowed when drawing random samples.
- Parameters
-
[out] radius the maximum distance (L2 norm)
Definition at line 205 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::samples_radius_.
◆ initSAC()
|
protectedvirtual |
Initialize the Sample Consensus method and set its parameters.
- Parameters
-
[in] method_type the type of SAC method to be used
Definition at line 298 of file sac_segmentation.hpp.
References pcl::SAC_LMEDS, pcl::SAC_MLESAC, pcl::SAC_MSAC, pcl::SAC_PROSAC, pcl::SAC_RANSAC, pcl::SAC_RMSAC, and pcl::SAC_RRANSAC.
◆ initSACModel()
|
protectedvirtual |
Initialize the Sample Consensus model and set its parameters.
- Parameters
-
[in] model_type the type of SAC model that is to be used
Reimplemented in pcl::SACSegmentationFromNormals< PointT, PointNT >.
Definition at line 138 of file sac_segmentation.hpp.
References pcl::SampleConsensusModelParallelLine< PointT >::getAxis(), pcl::SampleConsensusModelParallelPlane< PointT >::getAxis(), pcl::SampleConsensusModelPerpendicularPlane< PointT >::getAxis(), pcl::SampleConsensusModelParallelLine< PointT >::getEpsAngle(), pcl::SampleConsensusModelParallelPlane< PointT >::getEpsAngle(), pcl::SampleConsensusModelPerpendicularPlane< PointT >::getEpsAngle(), pcl::SampleConsensusModel< PointT >::getRadiusLimits(), M_PI, pcl::SACMODEL_CIRCLE2D, pcl::SACMODEL_CIRCLE3D, pcl::SACMODEL_CONE, pcl::SACMODEL_CYLINDER, pcl::SACMODEL_ELLIPSE3D, pcl::SACMODEL_LINE, pcl::SACMODEL_NORMAL_PARALLEL_PLANE, pcl::SACMODEL_NORMAL_PLANE, pcl::SACMODEL_NORMAL_SPHERE, pcl::SACMODEL_PARALLEL_LINE, pcl::SACMODEL_PARALLEL_PLANE, pcl::SACMODEL_PERPENDICULAR_PLANE, pcl::SACMODEL_PLANE, pcl::SACMODEL_SPHERE, pcl::SACMODEL_STICK, pcl::SampleConsensusModelParallelLine< PointT >::setAxis(), pcl::SampleConsensusModelParallelPlane< PointT >::setAxis(), pcl::SampleConsensusModelPerpendicularPlane< PointT >::setAxis(), pcl::SampleConsensusModelParallelLine< PointT >::setEpsAngle(), pcl::SampleConsensusModelParallelPlane< PointT >::setEpsAngle(), pcl::SampleConsensusModelPerpendicularPlane< PointT >::setEpsAngle(), and pcl::SampleConsensusModel< PointT >::setRadiusLimits().
◆ segment()
|
virtual |
Base method for segmentation of a model in a PointCloud given by <setInputCloud (), setIndices ()>
- Parameters
-
[out] inliers the resultant point indices that support the model found (inliers) [out] model_coefficients the resultant model coefficients
Definition at line 80 of file sac_segmentation.hpp.
References pcl::ModelCoefficients::header, pcl::PointIndices::header, pcl::PointIndices::indices, and pcl::ModelCoefficients::values.
◆ setAxis()
|
inline |
Set the axis along which we need to search for a model perpendicular to.
- Parameters
-
[in] ax the axis along which we need to search for a model perpendicular to
Definition at line 214 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::axis_.
◆ setDistanceThreshold()
|
inline |
Distance to the model threshold (user given parameter).
- Parameters
-
[in] threshold the distance threshold to use
Definition at line 123 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::threshold_.
◆ setEpsAngle()
|
inline |
Set the angle epsilon (delta) threshold.
- Parameters
-
[in] ea the maximum allowed difference between the model normal and the given axis in radians.
Definition at line 224 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::eps_angle_.
◆ setMaxIterations()
|
inline |
Set the maximum number of iterations before giving up.
- Parameters
-
[in] max_iterations the maximum number of iterations the sample consensus method will run
Definition at line 133 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::max_iterations_.
◆ setMethodType()
|
inline |
The type of sample consensus method to use (user given parameter).
- Parameters
-
[in] method the method type (check method_types.h)
Definition at line 113 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::method_type_.
◆ setModelType()
|
inline |
The type of model to use (user given parameter).
- Parameters
-
[in] model the model type (check model_types.h)
Definition at line 95 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::model_type_.
◆ setNumberOfThreads()
|
inline |
Set the number of threads to use or turn off parallelization.
- Parameters
-
[in] nr_threads the number of hardware threads to use (0 sets the value automatically, a negative number turns parallelization off)
- Note
- Not all SAC methods have a parallel implementation. Some will ignore this setting.
Definition at line 154 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::threads_.
◆ setOptimizeCoefficients()
|
inline |
Set to true if a coefficient refinement is required.
- Parameters
-
[in] optimize true for enabling model coefficient refinement, false otherwise
Definition at line 160 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::optimize_coefficients_.
◆ setProbability()
|
inline |
Set the probability of choosing at least one sample free from outliers.
- Parameters
-
[in] probability the model fitting probability
Definition at line 143 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::probability_.
◆ setRadiusLimits()
|
inline |
Set the minimum and maximum allowable radius limits for the model (applicable to models that estimate a radius)
- Parameters
-
[in] min_radius the minimum radius model [in] max_radius the maximum radius model
Definition at line 172 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::radius_max_, and pcl::SACSegmentation< PointT >::radius_min_.
◆ setSamplesMaxDist()
|
inline |
Set the maximum distance allowed when drawing random samples.
- Parameters
-
[in] radius the maximum distance (L2 norm) search
Definition at line 194 of file sac_segmentation.h.
References pcl::SACSegmentation< PointT >::samples_radius_, and pcl::SACSegmentation< PointT >::samples_radius_search_.
Member Data Documentation
◆ axis_
|
protected |
The axis along which we need to search for a model perpendicular to.
Definition at line 281 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getAxis(), and pcl::SACSegmentation< PointT >::setAxis().
◆ eps_angle_
|
protected |
The maximum allowed difference between the model normal and the given axis.
Definition at line 278 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getEpsAngle(), and pcl::SACSegmentation< PointT >::setEpsAngle().
◆ max_iterations_
|
protected |
Maximum number of iterations before giving up (user given parameter).
Definition at line 284 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getMaxIterations(), and pcl::SACSegmentation< PointT >::setMaxIterations().
◆ method_type_
|
protected |
The type of sample consensus method to use (user given parameter).
Definition at line 260 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getMethodType(), and pcl::SACSegmentation< PointT >::setMethodType().
◆ model_
|
protected |
The model that needs to be segmented.
Definition at line 251 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getModel().
◆ model_type_
|
protected |
The type of model to use (user given parameter).
Definition at line 257 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getModelType(), and pcl::SACSegmentation< PointT >::setModelType().
◆ optimize_coefficients_
|
protected |
Set to true if a coefficient refinement is required.
Definition at line 266 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getOptimizeCoefficients(), and pcl::SACSegmentation< PointT >::setOptimizeCoefficients().
◆ probability_
|
protected |
Desired probability of choosing at least one sample free from outliers (user given parameter).
Definition at line 290 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getProbability(), and pcl::SACSegmentation< PointT >::setProbability().
◆ radius_max_
|
protected |
Definition at line 269 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getRadiusLimits(), and pcl::SACSegmentation< PointT >::setRadiusLimits().
◆ radius_min_
|
protected |
The minimum and maximum radius limits for the model.
Applicable to all models that estimate a radius.
Definition at line 269 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getRadiusLimits(), and pcl::SACSegmentation< PointT >::setRadiusLimits().
◆ random_
|
protected |
Set to true if we need a random seed.
Definition at line 293 of file sac_segmentation.h.
◆ sac_
|
protected |
The sample consensus segmentation method.
Definition at line 254 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getMethod().
◆ samples_radius_
|
protected |
The maximum distance of subsequent samples from the first (radius search)
Definition at line 272 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getSamplesMaxDist(), and pcl::SACSegmentation< PointT >::setSamplesMaxDist().
◆ samples_radius_search_
|
protected |
The search object for picking subsequent samples using radius search.
Definition at line 275 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::setSamplesMaxDist().
◆ threads_
|
protected |
The number of threads the scheduler should use, or a negative number if no parallelization is wanted.
Definition at line 287 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::setNumberOfThreads().
◆ threshold_
|
protected |
Distance to the model threshold (user given parameter).
Definition at line 263 of file sac_segmentation.h.
Referenced by pcl::SACSegmentation< PointT >::getDistanceThreshold(), and pcl::SACSegmentation< PointT >::setDistanceThreshold().
The documentation for this class was generated from the following files:
- pcl/segmentation/sac_segmentation.h
- pcl/segmentation/impl/sac_segmentation.hpp