Point Cloud Library (PCL) 1.14.0
Loading...
Searching...
No Matches
mlesac.h
1/*
2 * Software License Agreement (BSD License)
3 *
4 * Point Cloud Library (PCL) - www.pointclouds.org
5 * Copyright (c) 2009, Willow Garage, Inc.
6 * Copyright (c) 2012-, Open Perception, Inc.
7 *
8 * All rights reserved.
9 *
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
12 * are met:
13 *
14 * * Redistributions of source code must retain the above copyright
15 * notice, this list of conditions and the following disclaimer.
16 * * Redistributions in binary form must reproduce the above
17 * copyright notice, this list of conditions and the following
18 * disclaimer in the documentation and/or other materials provided
19 * with the distribution.
20 * * Neither the name of the copyright holder(s) nor the names of its
21 * contributors may be used to endorse or promote products derived
22 * from this software without specific prior written permission.
23 *
24 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
25 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
26 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
27 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
28 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
29 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
30 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
31 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
32 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
33 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
34 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
35 * POSSIBILITY OF SUCH DAMAGE.
36 *
37 * $Id$
38 *
39 */
40
41#pragma once
42
43#include <pcl/sample_consensus/sac.h>
44#include <pcl/sample_consensus/sac_model.h>
45#include <pcl/pcl_base.h>
46
47namespace pcl
48{
49 /** \brief @b MaximumLikelihoodSampleConsensus represents an implementation of the MLESAC (Maximum Likelihood
50 * Estimator SAmple Consensus) algorithm, as described in: "MLESAC: A new robust estimator with application to
51 * estimating image geometry", P.H.S. Torr and A. Zisserman, Computer Vision and Image Understanding, vol 78, 2000.
52 * \note MLESAC is useful in situations where most of the data samples belong to the model, and a fast outlier rejection algorithm is needed.
53 * \author Radu B. Rusu
54 * \ingroup sample_consensus
55 */
56 template <typename PointT>
58 {
59 using SampleConsensusModelPtr = typename SampleConsensusModel<PointT>::Ptr;
60 using PointCloudConstPtr = typename SampleConsensusModel<PointT>::PointCloudConstPtr;
61
62 public:
63 using Ptr = shared_ptr<MaximumLikelihoodSampleConsensus<PointT> >;
64 using ConstPtr = shared_ptr<const MaximumLikelihoodSampleConsensus<PointT> >;
65
74
75 /** \brief MLESAC (Maximum Likelihood Estimator SAmple Consensus) main constructor
76 * \param[in] model a Sample Consensus model
77 */
78 MaximumLikelihoodSampleConsensus (const SampleConsensusModelPtr &model) :
79 SampleConsensus<PointT> (model),
80 iterations_EM_ (3), // Max number of EM (Expectation Maximization) iterations
81 sigma_ (0)
82 {
83 max_iterations_ = 10000; // Maximum number of trials before we give up.
84 }
85
86 /** \brief MLESAC (Maximum Likelihood Estimator SAmple Consensus) main constructor
87 * \param[in] model a Sample Consensus model
88 * \param[in] threshold distance to model threshold
89 */
90 MaximumLikelihoodSampleConsensus (const SampleConsensusModelPtr &model, double threshold) :
91 SampleConsensus<PointT> (model, threshold),
92 iterations_EM_ (3), // Max number of EM (Expectation Maximization) iterations
93 sigma_ (0)
94 {
95 max_iterations_ = 10000; // Maximum number of trials before we give up.
96 }
97
98 /** \brief Compute the actual model and find the inliers
99 * \param[in] debug_verbosity_level enable/disable on-screen debug information and set the verbosity level
100 */
101 bool
102 computeModel (int debug_verbosity_level = 0) override;
103
104 /** \brief Set the number of EM iterations.
105 * \param[in] iterations the number of EM iterations
106 */
107 inline void
108 setEMIterations (int iterations) { iterations_EM_ = iterations; }
109
110 /** \brief Get the number of EM iterations. */
111 inline int
112 getEMIterations () const { return (iterations_EM_); }
113
114
115 protected:
116 /** \brief Compute the median absolute deviation:
117 * \f[
118 * MAD = \sigma * median_i (| Xi - median_j(Xj) |)
119 * \f]
120 * \note Sigma needs to be chosen carefully (a good starting sigma value is 1.4826)
121 * \param[in] cloud the point cloud data message
122 * \param[in] indices the set of point indices to use
123 * \param[in] sigma the sigma value
124 */
125 double
126 computeMedianAbsoluteDeviation (const PointCloudConstPtr &cloud,
127 const IndicesPtr &indices,
128 double sigma) const;
129
130 /** \brief Determine the minimum and maximum 3D bounding box coordinates for a given set of points
131 * \param[in] cloud the point cloud message
132 * \param[in] indices the set of point indices to use
133 * \param[out] min_p the resultant minimum bounding box coordinates
134 * \param[out] max_p the resultant maximum bounding box coordinates
135 */
136 void
137 getMinMax (const PointCloudConstPtr &cloud,
138 const IndicesPtr &indices,
139 Eigen::Vector4f &min_p,
140 Eigen::Vector4f &max_p) const;
141
142 /** \brief Compute the median value of a 3D point cloud using a given set point indices and return it as a Point32.
143 * \param[in] cloud the point cloud data message
144 * \param[in] indices the point indices
145 * \param[out] median the resultant median value
146 */
147 void
148 computeMedian (const PointCloudConstPtr &cloud,
149 const IndicesPtr &indices,
150 Eigen::Vector4f &median) const;
151
152 private:
153 /** \brief Maximum number of EM (Expectation Maximization) iterations. */
154 int iterations_EM_;
155 /** \brief The MLESAC sigma parameter. */
156 double sigma_;
157 };
158}
159
160#ifdef PCL_NO_PRECOMPILE
161#include <pcl/sample_consensus/impl/mlesac.hpp>
162#endif
MaximumLikelihoodSampleConsensus represents an implementation of the MLESAC (Maximum Likelihood Estim...
Definition mlesac.h:58
void computeMedian(const PointCloudConstPtr &cloud, const IndicesPtr &indices, Eigen::Vector4f &median) const
Compute the median value of a 3D point cloud using a given set point indices and return it as a Point...
Definition mlesac.hpp:261
MaximumLikelihoodSampleConsensus(const SampleConsensusModelPtr &model)
MLESAC (Maximum Likelihood Estimator SAmple Consensus) main constructor.
Definition mlesac.h:78
MaximumLikelihoodSampleConsensus(const SampleConsensusModelPtr &model, double threshold)
MLESAC (Maximum Likelihood Estimator SAmple Consensus) main constructor.
Definition mlesac.h:90
int getEMIterations() const
Get the number of EM iterations.
Definition mlesac.h:112
shared_ptr< const MaximumLikelihoodSampleConsensus< PointT > > ConstPtr
Definition mlesac.h:64
void setEMIterations(int iterations)
Set the number of EM iterations.
Definition mlesac.h:108
shared_ptr< MaximumLikelihoodSampleConsensus< PointT > > Ptr
Definition mlesac.h:63
void getMinMax(const PointCloudConstPtr &cloud, const IndicesPtr &indices, Eigen::Vector4f &min_p, Eigen::Vector4f &max_p) const
Determine the minimum and maximum 3D bounding box coordinates for a given set of points.
Definition mlesac.hpp:237
bool computeModel(int debug_verbosity_level=0) override
Compute the actual model and find the inliers.
Definition mlesac.hpp:50
double computeMedianAbsoluteDeviation(const PointCloudConstPtr &cloud, const IndicesPtr &indices, double sigma) const
Compute the median absolute deviation:
Definition mlesac.hpp:212
SampleConsensus represents the base class.
Definition sac.h:61
double probability_
Desired probability of choosing at least one sample free from outliers.
Definition sac.h:332
Indices inliers_
The indices of the points that were chosen as inliers after the last computeModel () call.
Definition sac.h:326
int iterations_
Total number of internal loop iterations that we've done so far.
Definition sac.h:335
Indices model_
The model found after the last computeModel () as point cloud indices.
Definition sac.h:323
Eigen::VectorXf model_coefficients_
The coefficients of our model computed directly from the model found.
Definition sac.h:329
double threshold_
Distance to model threshold.
Definition sac.h:338
SampleConsensusModelPtr sac_model_
The underlying data model used (i.e.
Definition sac.h:320
int max_iterations_
Maximum number of iterations before giving up.
Definition sac.h:341
shared_ptr< SampleConsensusModel< PointT > > Ptr
Definition sac_model.h:78
typename PointCloud::ConstPtr PointCloudConstPtr
Definition sac_model.h:74
shared_ptr< Indices > IndicesPtr
Definition pcl_base.h:58
A point structure representing Euclidean xyz coordinates, and the RGB color.