Point Cloud Library (PCL)
1.7.0
|
00001 /* 00002 * Software License Agreement (BSD License) 00003 * 00004 * Point Cloud Library (PCL) - www.pointclouds.org 00005 * Copyright (c) 2009, Willow Garage, Inc. 00006 * Copyright (c) 2012-, Open Perception, Inc. 00007 * 00008 * All rights reserved. 00009 * 00010 * Redistribution and use in source and binary forms, with or without 00011 * modification, are permitted provided that the following conditions 00012 * are met: 00013 * 00014 * * Redistributions of source code must retain the above copyright 00015 * notice, this list of conditions and the following disclaimer. 00016 * * Redistributions in binary form must reproduce the above 00017 * copyright notice, this list of conditions and the following 00018 * disclaimer in the documentation and/or other materials provided 00019 * with the distribution. 00020 * * Neither the name of the copyright holder(s) nor the names of its 00021 * contributors may be used to endorse or promote products derived 00022 * from this software without specific prior written permission. 00023 * 00024 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 00025 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 00026 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS 00027 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 00028 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 00029 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 00030 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 00031 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 00032 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 00033 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN 00034 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 00035 * POSSIBILITY OF SUCH DAMAGE. 00036 * 00037 * $Id$ 00038 * 00039 */ 00040 00041 #ifndef PCL_SAMPLE_CONSENSUS_MLESAC_H_ 00042 #define PCL_SAMPLE_CONSENSUS_MLESAC_H_ 00043 00044 #include <pcl/sample_consensus/sac.h> 00045 #include <pcl/sample_consensus/sac_model.h> 00046 00047 namespace pcl 00048 { 00049 /** \brief @b MaximumLikelihoodSampleConsensus represents an implementation of the MLESAC (Maximum Likelihood 00050 * Estimator SAmple Consensus) algorithm, as described in: "MLESAC: A new robust estimator with application to 00051 * estimating image geometry", P.H.S. Torr and A. Zisserman, Computer Vision and Image Understanding, vol 78, 2000. 00052 * \note MLESAC is useful in situations where most of the data samples belong to the model, and a fast outlier rejection algorithm is needed. 00053 * \author Radu B. Rusu 00054 * \ingroup sample_consensus 00055 */ 00056 template <typename PointT> 00057 class MaximumLikelihoodSampleConsensus : public SampleConsensus<PointT> 00058 { 00059 typedef typename SampleConsensusModel<PointT>::Ptr SampleConsensusModelPtr; 00060 typedef typename SampleConsensusModel<PointT>::PointCloudConstPtr PointCloudConstPtr; 00061 00062 public: 00063 typedef boost::shared_ptr<MaximumLikelihoodSampleConsensus> Ptr; 00064 typedef boost::shared_ptr<const MaximumLikelihoodSampleConsensus> ConstPtr; 00065 00066 using SampleConsensus<PointT>::max_iterations_; 00067 using SampleConsensus<PointT>::threshold_; 00068 using SampleConsensus<PointT>::iterations_; 00069 using SampleConsensus<PointT>::sac_model_; 00070 using SampleConsensus<PointT>::model_; 00071 using SampleConsensus<PointT>::model_coefficients_; 00072 using SampleConsensus<PointT>::inliers_; 00073 using SampleConsensus<PointT>::probability_; 00074 00075 /** \brief MLESAC (Maximum Likelihood Estimator SAmple Consensus) main constructor 00076 * \param[in] model a Sample Consensus model 00077 */ 00078 MaximumLikelihoodSampleConsensus (const SampleConsensusModelPtr &model) : 00079 SampleConsensus<PointT> (model), 00080 iterations_EM_ (3), // Max number of EM (Expectation Maximization) iterations 00081 sigma_ (0) 00082 { 00083 max_iterations_ = 10000; // Maximum number of trials before we give up. 00084 } 00085 00086 /** \brief MLESAC (Maximum Likelihood Estimator SAmple Consensus) main constructor 00087 * \param[in] model a Sample Consensus model 00088 * \param[in] threshold distance to model threshold 00089 */ 00090 MaximumLikelihoodSampleConsensus (const SampleConsensusModelPtr &model, double threshold) : 00091 SampleConsensus<PointT> (model, threshold), 00092 iterations_EM_ (3), // Max number of EM (Expectation Maximization) iterations 00093 sigma_ (0) 00094 { 00095 max_iterations_ = 10000; // Maximum number of trials before we give up. 00096 } 00097 00098 /** \brief Compute the actual model and find the inliers 00099 * \param[in] debug_verbosity_level enable/disable on-screen debug information and set the verbosity level 00100 */ 00101 bool 00102 computeModel (int debug_verbosity_level = 0); 00103 00104 /** \brief Set the number of EM iterations. 00105 * \param[in] iterations the number of EM iterations 00106 */ 00107 inline void 00108 setEMIterations (int iterations) { iterations_EM_ = iterations; } 00109 00110 /** \brief Get the number of EM iterations. */ 00111 inline int 00112 getEMIterations () const { return (iterations_EM_); } 00113 00114 00115 protected: 00116 /** \brief Compute the median absolute deviation: 00117 * \f[ 00118 * MAD = \sigma * median_i (| Xi - median_j(Xj) |) 00119 * \f] 00120 * \note Sigma needs to be chosen carefully (a good starting sigma value is 1.4826) 00121 * \param[in] cloud the point cloud data message 00122 * \param[in] indices the set of point indices to use 00123 * \param[in] sigma the sigma value 00124 */ 00125 double 00126 computeMedianAbsoluteDeviation (const PointCloudConstPtr &cloud, 00127 const boost::shared_ptr <std::vector<int> > &indices, 00128 double sigma); 00129 00130 /** \brief Determine the minimum and maximum 3D bounding box coordinates for a given set of points 00131 * \param[in] cloud the point cloud message 00132 * \param[in] indices the set of point indices to use 00133 * \param[out] min_p the resultant minimum bounding box coordinates 00134 * \param[out] max_p the resultant maximum bounding box coordinates 00135 */ 00136 void 00137 getMinMax (const PointCloudConstPtr &cloud, 00138 const boost::shared_ptr <std::vector<int> > &indices, 00139 Eigen::Vector4f &min_p, 00140 Eigen::Vector4f &max_p); 00141 00142 /** \brief Compute the median value of a 3D point cloud using a given set point indices and return it as a Point32. 00143 * \param[in] cloud the point cloud data message 00144 * \param[in] indices the point indices 00145 * \param[out] median the resultant median value 00146 */ 00147 void 00148 computeMedian (const PointCloudConstPtr &cloud, 00149 const boost::shared_ptr <std::vector<int> > &indices, 00150 Eigen::Vector4f &median); 00151 00152 private: 00153 /** \brief Maximum number of EM (Expectation Maximization) iterations. */ 00154 int iterations_EM_; 00155 /** \brief The MLESAC sigma parameter. */ 00156 double sigma_; 00157 }; 00158 } 00159 00160 #ifdef PCL_NO_PRECOMPILE 00161 #include <pcl/sample_consensus/impl/mlesac.hpp> 00162 #endif 00163 00164 #endif //#ifndef PCL_SAMPLE_CONSENSUS_MLESAC_H_