Point Cloud Library (PCL)  1.15.1-dev
feature.hpp
1 /*
2  * Software License Agreement (BSD License)
3  *
4  * Point Cloud Library (PCL) - www.pointclouds.org
5  * Copyright (c) 2010-2011, 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_FEATURES_IMPL_FEATURE_H_
42 #define PCL_FEATURES_IMPL_FEATURE_H_
43 
44 #include <pcl/common/eigen.h> // for eigen33
45 #include <pcl/search/auto.h> // for autoSelectMethod
46 
47 
48 namespace pcl
49 {
50 
51 inline void
52 solvePlaneParameters (const Eigen::Matrix3f &covariance_matrix,
53  const Eigen::Vector4f &point,
54  Eigen::Vector4f &plane_parameters, float &curvature)
55 {
56  solvePlaneParameters (covariance_matrix, plane_parameters [0], plane_parameters [1], plane_parameters [2], curvature);
57 
58  plane_parameters[3] = 0;
59  // Hessian form (D = nc . p_plane (centroid here) + p)
60  plane_parameters[3] = -1 * plane_parameters.dot (point);
61 }
62 
63 
64 inline void
65 solvePlaneParameters (const Eigen::Matrix3f &covariance_matrix,
66  float &nx, float &ny, float &nz, float &curvature)
67 {
68  // Avoid getting hung on Eigen's optimizers
69 // for (int i = 0; i < 9; ++i)
70 // if (!std::isfinite (covariance_matrix.coeff (i)))
71 // {
72 // //PCL_WARN ("[pcl::solvePlaneParameters] Covariance matrix has NaN/Inf values!\n");
73 // nx = ny = nz = curvature = std::numeric_limits<float>::quiet_NaN ();
74 // return;
75 // }
76  // Extract the smallest eigenvalue and its eigenvector
77  EIGEN_ALIGN16 Eigen::Vector3f::Scalar eigen_value;
78  EIGEN_ALIGN16 Eigen::Vector3f eigen_vector;
79  pcl::eigen33 (covariance_matrix, eigen_value, eigen_vector);
80 
81  nx = eigen_vector [0];
82  ny = eigen_vector [1];
83  nz = eigen_vector [2];
84 
85  // Compute the curvature surface change
86  float eig_sum = covariance_matrix.coeff (0) + covariance_matrix.coeff (4) + covariance_matrix.coeff (8);
87  if (eig_sum != 0)
88  curvature = std::abs (eigen_value / eig_sum);
89  else
90  curvature = 0;
91 }
92 
93 
94 template <typename PointInT, typename PointOutT> bool
96 {
98  {
99  PCL_ERROR ("[pcl::%s::initCompute] Init failed.\n", getClassName ().c_str ());
100  return (false);
101  }
102 
103  // If the dataset is empty, just return
104  if (input_->points.empty ())
105  {
106  PCL_ERROR ("[pcl::%s::compute] input_ is empty!\n", getClassName ().c_str ());
107  // Cleanup
108  deinitCompute ();
109  return (false);
110  }
111 
112  // If no search surface has been defined, use the input dataset as the search surface itself
113  if (!surface_)
114  {
115  fake_surface_ = true;
116  surface_ = input_;
117  }
118 
119  // Check if a space search locator was given
120  if (!tree_)
121  {
122  tree_.reset (pcl::search::autoSelectMethod<PointInT>(surface_, false));
123  }
124 
125  if (tree_->getInputCloud () != surface_) { // Make sure the tree searches the surface
126  if(!tree_->setInputCloud (surface_)) {
127  PCL_ERROR ("[pcl::%s::compute] The given search method cannot work with the given input cloud/search surface.\n", getClassName ().c_str ());
128  return (false);
129  }
130  }
131 
132 
133  // Do a fast check to see if the search parameters are well defined
134  if (search_radius_ != 0.0)
135  {
136  if (k_ != 0)
137  {
138  PCL_ERROR ("[pcl::%s::compute] ", getClassName ().c_str ());
139  PCL_ERROR ("Both radius (%f) and K (%d) defined! ", search_radius_, k_);
140  PCL_ERROR ("Set one of them to zero first and then re-run compute ().\n");
141  // Cleanup
142  deinitCompute ();
143  return (false);
144  }
145  else // Use the radiusSearch () function
146  {
147  search_parameter_ = search_radius_;
148  // Declare the search locator definition
149  search_method_surface_ = [this] (const PointCloudIn &cloud, int index, double radius,
150  pcl::Indices &k_indices, std::vector<float> &k_distances)
151  {
152  return tree_->radiusSearch (cloud, index, radius, k_indices, k_distances, 0);
153  };
154  }
155  }
156  else
157  {
158  if (k_ != 0) // Use the nearestKSearch () function
159  {
160  search_parameter_ = k_;
161  // Declare the search locator definition
162  search_method_surface_ = [this] (const PointCloudIn &cloud, int index, int k, pcl::Indices &k_indices,
163  std::vector<float> &k_distances)
164  {
165  return tree_->nearestKSearch (cloud, index, k, k_indices, k_distances);
166  };
167  }
168  else
169  {
170  PCL_ERROR ("[pcl::%s::compute] Neither radius nor K defined! ", getClassName ().c_str ());
171  PCL_ERROR ("Set one of them to a positive number first and then re-run compute ().\n");
172  // Cleanup
173  deinitCompute ();
174  return (false);
175  }
176  }
177  return (true);
178 }
179 
180 
181 template <typename PointInT, typename PointOutT> bool
183 {
184  // Reset the surface
185  if (fake_surface_)
186  {
187  surface_.reset ();
188  fake_surface_ = false;
189  }
190  return (true);
191 }
192 
193 
194 template <typename PointInT, typename PointOutT> void
196 {
197  if (!initCompute ())
198  {
199  output.width = output.height = 0;
200  output.clear ();
201  return;
202  }
203 
204  // Copy the header
205  output.header = input_->header;
206 
207  // Resize the output dataset
208  if (output.size () != indices_->size ())
209  output.resize (indices_->size ());
210 
211  // Check if the output will be computed for all points or only a subset
212  // If the input width or height are not set, set output width as size
213  if (indices_->size () != input_->points.size () || input_->width * input_->height == 0)
214  {
215  output.width = indices_->size ();
216  output.height = 1;
217  }
218  else
219  {
220  output.width = input_->width;
221  output.height = input_->height;
222  }
223  output.is_dense = input_->is_dense;
224 
225  // Perform the actual feature computation
226  computeFeature (output);
227 
228  deinitCompute ();
229 }
230 
231 
232 template <typename PointInT, typename PointNT, typename PointOutT> bool
234 {
236  {
237  PCL_ERROR ("[pcl::%s::initCompute] Init failed.\n", getClassName ().c_str ());
238  return (false);
239  }
240 
241  // Check if input normals are set
242  if (!normals_)
243  {
244  PCL_ERROR ("[pcl::%s::initCompute] No input dataset containing normals was given!\n", getClassName ().c_str ());
246  return (false);
247  }
248 
249  // Check if the size of normals is the same as the size of the surface
250  if (normals_->points.size () != surface_->points.size ())
251  {
252  PCL_ERROR ("[pcl::%s::initCompute] ", getClassName ().c_str ());
253  PCL_ERROR("The number of points in the surface dataset (%zu) differs from ",
254  static_cast<std::size_t>(surface_->points.size()));
255  PCL_ERROR("the number of points in the dataset containing the normals (%zu)!\n",
256  static_cast<std::size_t>(normals_->points.size()));
258  return (false);
259  }
260 
261  return (true);
262 }
263 
264 
265 template <typename PointInT, typename PointLT, typename PointOutT> bool
267 {
269  {
270  PCL_ERROR ("[pcl::%s::initCompute] Init failed.\n", getClassName ().c_str ());
271  return (false);
272  }
273 
274  // Check if input normals are set
275  if (!labels_)
276  {
277  PCL_ERROR ("[pcl::%s::initCompute] No input dataset containing labels was given!\n", getClassName ().c_str ());
279  return (false);
280  }
281 
282  // Check if the size of normals is the same as the size of the surface
283  if (labels_->points.size () != surface_->points.size ())
284  {
285  PCL_ERROR ("[pcl::%s::initCompute] The number of points in the input dataset differs from the number of points in the dataset containing the labels!\n", getClassName ().c_str ());
287  return (false);
288  }
289 
290  return (true);
291 }
292 
293 
294 template <typename PointInT, typename PointRFT> bool
296  const LRFEstimationPtr& lrf_estimation)
297 {
298  if (frames_never_defined_)
299  frames_.reset ();
300 
301  // Check if input frames are set
302  if (!frames_)
303  {
304  if (!lrf_estimation)
305  {
306  PCL_ERROR ("[initLocalReferenceFrames] No input dataset containing reference frames was given!\n");
307  return (false);
308  } else
309  {
310  //PCL_WARN ("[initLocalReferenceFrames] No input dataset containing reference frames was given! Proceed using default\n");
311  PointCloudLRFPtr default_frames (new PointCloudLRF());
312  lrf_estimation->compute (*default_frames);
313  frames_ = default_frames;
314  }
315  }
316 
317  // Check if the size of frames is the same as the size of the input cloud
318  if (frames_->points.size () != indices_size)
319  {
320  if (!lrf_estimation)
321  {
322  PCL_ERROR ("[initLocalReferenceFrames] The number of points in the input dataset differs from the number of points in the dataset containing the reference frames!\n");
323  return (false);
324  } else
325  {
326  //PCL_WARN ("[initLocalReferenceFrames] The number of points in the input dataset differs from the number of points in the dataset containing the reference frames! Proceed using default\n");
327  PointCloudLRFPtr default_frames (new PointCloudLRF());
328  lrf_estimation->compute (*default_frames);
329  frames_ = default_frames;
330  }
331  }
332 
333  return (true);
334 }
335 
336 } // namespace pcl
337 
338 #endif //#ifndef PCL_FEATURES_IMPL_FEATURE_H_
339 
virtual bool initCompute()
This method should get called before starting the actual computation.
Definition: feature.hpp:266
virtual bool initCompute()
This method should get called before starting the actual computation.
Definition: feature.hpp:233
Feature represents the base feature class.
Definition: feature.h:107
virtual bool initCompute()
This method should get called before starting the actual computation.
Definition: feature.hpp:95
virtual bool deinitCompute()
This method should get called after ending the actual computation.
Definition: feature.hpp:182
void compute(PointCloudOut &output)
Base method for feature estimation for all points given in <setInputCloud (), setIndices ()> using th...
Definition: feature.hpp:195
typename PointCloudLRF::Ptr PointCloudLRFPtr
Definition: feature.h:443
typename Feature< PointInT, PointRFT >::Ptr LRFEstimationPtr
Check if frames_ has been correctly initialized and compute it if needed.
Definition: feature.h:484
virtual bool initLocalReferenceFrames(const std::size_t &indices_size, const LRFEstimationPtr &lrf_estimation=LRFEstimationPtr())
Definition: feature.hpp:295
PCL base class.
Definition: pcl_base.h:70
bool is_dense
True if no points are invalid (e.g., have NaN or Inf values in any of their floating point fields).
Definition: point_cloud.h:404
void resize(std::size_t count)
Resizes the container to contain count elements.
Definition: point_cloud.h:463
std::uint32_t width
The point cloud width (if organized as an image-structure).
Definition: point_cloud.h:399
pcl::PCLHeader header
The point cloud header.
Definition: point_cloud.h:393
std::uint32_t height
The point cloud height (if organized as an image-structure).
Definition: point_cloud.h:401
void clear()
Removes all points in a cloud and sets the width and height to 0.
Definition: point_cloud.h:886
std::size_t size() const
Definition: point_cloud.h:444
void eigen33(const Matrix &mat, typename Matrix::Scalar &eigenvalue, Vector &eigenvector)
determines the eigenvector and eigenvalue of the smallest eigenvalue of the symmetric positive semi d...
Definition: eigen.hpp:295
void solvePlaneParameters(const Eigen::Matrix3f &covariance_matrix, const Eigen::Vector4f &point, Eigen::Vector4f &plane_parameters, float &curvature)
Solve the eigenvalues and eigenvectors of a given 3x3 covariance matrix, and estimate the least-squar...
Definition: feature.hpp:52
IndicesAllocator<> Indices
Type used for indices in PCL.
Definition: types.h:133