Point Cloud Library (PCL)  1.9.1-dev
lmeds.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_LMEDS_H_
42 #define PCL_SAMPLE_CONSENSUS_IMPL_LMEDS_H_
43 
44 #include <pcl/sample_consensus/lmeds.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::LeastMedianSquares::computeModel] No threshold set!\n");
54  return (false);
55  }
56 
57  iterations_ = 0;
58  double d_best_penalty = std::numeric_limits<double>::max();
59 
60  std::vector<int> best_model;
61  std::vector<int> selection;
62  Eigen::VectorXf model_coefficients;
63  std::vector<double> distances;
64 
65  int n_inliers_count = 0;
66 
67  unsigned skipped_count = 0;
68  // suppress infinite loops by just allowing 10 x maximum allowed iterations for invalid model parameters!
69  const unsigned max_skip = max_iterations_ * 10;
70 
71  // Iterate
72  while (iterations_ < max_iterations_ && skipped_count < max_skip)
73  {
74  // Get X samples which satisfy the model criteria
75  sac_model_->getSamples (iterations_, selection);
76 
77  if (selection.empty ()) break;
78 
79  // Search for inliers in the point cloud for the current plane model M
80  if (!sac_model_->computeModelCoefficients (selection, model_coefficients))
81  {
82  //iterations_++;
83  ++skipped_count;
84  continue;
85  }
86 
87  double d_cur_penalty = 0;
88  // d_cur_penalty = sum (min (dist, threshold))
89 
90  // Iterate through the 3d points and calculate the distances from them to the model
91  sac_model_->getDistancesToModel (model_coefficients, distances);
92 
93  // No distances? The model must not respect the user given constraints
94  if (distances.empty ())
95  {
96  //iterations_++;
97  ++skipped_count;
98  continue;
99  }
100 
101  std::sort (distances.begin (), distances.end ());
102  // d_cur_penalty = median (distances)
103  size_t mid = sac_model_->getIndices ()->size () / 2;
104  if (mid >= distances.size ())
105  {
106  //iterations_++;
107  ++skipped_count;
108  continue;
109  }
110 
111  // Do we have a "middle" point or should we "estimate" one ?
112  if (sac_model_->getIndices ()->size () % 2 == 0)
113  d_cur_penalty = (sqrt (distances[mid-1]) + sqrt (distances[mid])) / 2;
114  else
115  d_cur_penalty = sqrt (distances[mid]);
116 
117  // Better match ?
118  if (d_cur_penalty < d_best_penalty)
119  {
120  d_best_penalty = d_cur_penalty;
121 
122  // Save the current model/coefficients selection as being the best so far
123  model_ = selection;
124  model_coefficients_ = model_coefficients;
125  }
126 
127  ++iterations_;
128  if (debug_verbosity_level > 1)
129  PCL_DEBUG ("[pcl::LeastMedianSquares::computeModel] Trial %d out of %d. Best penalty is %f.\n", iterations_, max_iterations_, d_best_penalty);
130  }
131 
132  if (model_.empty ())
133  {
134  if (debug_verbosity_level > 0)
135  PCL_DEBUG ("[pcl::LeastMedianSquares::computeModel] Unable to find a solution!\n");
136  return (false);
137  }
138 
139  // Classify the data points into inliers and outliers
140  // Sigma = 1.4826 * (1 + 5 / (n-d)) * sqrt (M)
141  // @note: See "Robust Regression Methods for Computer Vision: A Review"
142  //double sigma = 1.4826 * (1 + 5 / (sac_model_->getIndices ()->size () - best_model.size ())) * sqrt (d_best_penalty);
143  //double threshold = 2.5 * sigma;
144 
145  // Iterate through the 3d points and calculate the distances from them to the model again
146  sac_model_->getDistancesToModel (model_coefficients_, distances);
147  // No distances? The model must not respect the user given constraints
148  if (distances.empty ())
149  {
150  PCL_ERROR ("[pcl::LeastMedianSquares::computeModel] The model found failed to verify against the given constraints!\n");
151  return (false);
152  }
153 
154  std::vector<int> &indices = *sac_model_->getIndices ();
155 
156  if (distances.size () != indices.size ())
157  {
158  PCL_ERROR ("[pcl::LeastMedianSquares::computeModel] Estimated distances (%lu) differs than the normal of indices (%lu).\n", distances.size (), indices.size ());
159  return (false);
160  }
161 
162  inliers_.resize (distances.size ());
163  // Get the inliers for the best model found
164  n_inliers_count = 0;
165  for (size_t i = 0; i < distances.size (); ++i)
166  if (distances[i] <= threshold_)
167  inliers_[n_inliers_count++] = indices[i];
168 
169  // Resize the inliers vector
170  inliers_.resize (n_inliers_count);
171 
172  if (debug_verbosity_level > 0)
173  PCL_DEBUG ("[pcl::LeastMedianSquares::computeModel] Model: %lu size, %d inliers.\n", model_.size (), n_inliers_count);
174 
175  return (true);
176 }
177 
178 #define PCL_INSTANTIATE_LeastMedianSquares(T) template class PCL_EXPORTS pcl::LeastMedianSquares<T>;
179 
180 #endif // PCL_SAMPLE_CONSENSUS_IMPL_LMEDS_H_
181 
bool computeModel(int debug_verbosity_level=0) override
Compute the actual model and find the inliers.
Definition: lmeds.hpp:48