Point Cloud Library (PCL)  1.12.0-dev
msac.hpp
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 #ifndef PCL_SAMPLE_CONSENSUS_IMPL_MSAC_H_
42 #define PCL_SAMPLE_CONSENSUS_IMPL_MSAC_H_
43 
44 #include <pcl/sample_consensus/msac.h>
45 
46 //////////////////////////////////////////////////////////////////////////
47 template <typename PointT> bool
49 {
50  // Warn and exit if no threshold was set
51  if (threshold_ == std::numeric_limits<double>::max())
52  {
53  PCL_ERROR ("[pcl::MEstimatorSampleConsensus::computeModel] No threshold set!\n");
54  return (false);
55  }
56 
57  iterations_ = 0;
58  double d_best_penalty = std::numeric_limits<double>::max();
59  double k = 1.0;
60 
61  Indices selection;
62  Eigen::VectorXf model_coefficients (sac_model_->getModelSize ());
63  std::vector<double> distances;
64 
65  int n_inliers_count = 0;
66  unsigned skipped_count = 0;
67  // suppress infinite loops by just allowing 10 x maximum allowed iterations for invalid model parameters!
68  const unsigned max_skip = max_iterations_ * 10;
69 
70  // Iterate
71  while (iterations_ < k && skipped_count < max_skip)
72  {
73  // Get X samples which satisfy the model criteria
74  sac_model_->getSamples (iterations_, selection);
75 
76  if (selection.empty ()) break;
77 
78  // Search for inliers in the point cloud for the current plane model M
79  if (!sac_model_->computeModelCoefficients (selection, model_coefficients))
80  {
81  //iterations_++;
82  ++ skipped_count;
83  continue;
84  }
85 
86  double d_cur_penalty = 0;
87  // Iterate through the 3d points and calculate the distances from them to the model
88  sac_model_->getDistancesToModel (model_coefficients, distances);
89 
90  if (distances.empty () && k > 1.0)
91  continue;
92 
93  for (const double &distance : distances)
94  d_cur_penalty += (std::min) (distance, threshold_);
95 
96  // Better match ?
97  if (d_cur_penalty < d_best_penalty)
98  {
99  d_best_penalty = d_cur_penalty;
100 
101  // Save the current model/coefficients selection as being the best so far
102  model_ = selection;
103  model_coefficients_ = model_coefficients;
104 
105  n_inliers_count = 0;
106  // Need to compute the number of inliers for this model to adapt k
107  for (const double &distance : distances)
108  if (distance <= threshold_)
109  ++n_inliers_count;
110 
111  // Compute the k parameter (k=std::log(z)/std::log(1-w^n))
112  double w = static_cast<double> (n_inliers_count) / static_cast<double> (sac_model_->getIndices ()->size ());
113  double p_no_outliers = 1.0 - std::pow (w, static_cast<double> (selection.size ()));
114  p_no_outliers = (std::max) (std::numeric_limits<double>::epsilon (), p_no_outliers); // Avoid division by -Inf
115  p_no_outliers = (std::min) (1.0 - std::numeric_limits<double>::epsilon (), p_no_outliers); // Avoid division by 0.
116  k = std::log (1.0 - probability_) / std::log (p_no_outliers);
117  }
118 
119  ++iterations_;
120  if (debug_verbosity_level > 1)
121  PCL_DEBUG ("[pcl::MEstimatorSampleConsensus::computeModel] Trial %d out of %d. Best penalty is %f.\n", iterations_, static_cast<int> (std::ceil (k)), d_best_penalty);
122  if (iterations_ > max_iterations_)
123  {
124  if (debug_verbosity_level > 0)
125  PCL_DEBUG ("[pcl::MEstimatorSampleConsensus::computeModel] MSAC reached the maximum number of trials.\n");
126  break;
127  }
128  }
129 
130  if (model_.empty ())
131  {
132  if (debug_verbosity_level > 0)
133  PCL_DEBUG ("[pcl::MEstimatorSampleConsensus::computeModel] Unable to find a solution!\n");
134  return (false);
135  }
136 
137  // Iterate through the 3d points and calculate the distances from them to the model again
138  sac_model_->getDistancesToModel (model_coefficients_, distances);
139  Indices &indices = *sac_model_->getIndices ();
140 
141  if (distances.size () != indices.size ())
142  {
143  PCL_ERROR ("[pcl::MEstimatorSampleConsensus::computeModel] Estimated distances (%lu) differs than the normal of indices (%lu).\n", distances.size (), indices.size ());
144  return (false);
145  }
146 
147  inliers_.resize (distances.size ());
148  // Get the inliers for the best model found
149  n_inliers_count = 0;
150  for (std::size_t i = 0; i < distances.size (); ++i)
151  if (distances[i] <= threshold_)
152  inliers_[n_inliers_count++] = indices[i];
153 
154  // Resize the inliers vector
155  inliers_.resize (n_inliers_count);
156 
157  if (debug_verbosity_level > 0)
158  PCL_DEBUG ("[pcl::MEstimatorSampleConsensus::computeModel] Model: %lu size, %d inliers.\n", model_.size (), n_inliers_count);
159 
160  return (true);
161 }
162 
163 #define PCL_INSTANTIATE_MEstimatorSampleConsensus(T) template class PCL_EXPORTS pcl::MEstimatorSampleConsensus<T>;
164 
165 #endif // PCL_SAMPLE_CONSENSUS_IMPL_MSAC_H_
pcl::geometry::distance
float distance(const PointT &p1, const PointT &p2)
Definition: geometry.h:60
pcl::MEstimatorSampleConsensus::computeModel
bool computeModel(int debug_verbosity_level=0) override
Compute the actual model and find the inliers.
Definition: msac.hpp:48
pcl::Indices
IndicesAllocator<> Indices
Type used for indices in PCL.
Definition: types.h:133