Point Cloud Library (PCL)  1.12.0
rf_face_utils.h
1 /*
2  * fanellis_face_detector.h
3  *
4  * Created on: 22 Sep 2012
5  * Author: Aitor Aldoma
6  */
7 
8 #pragma once
9 
10 #include "pcl/recognition/face_detection/face_common.h"
11 #include <pcl/ml/feature_handler.h>
12 #include <pcl/ml/stats_estimator.h>
13 #include <pcl/ml/branch_estimator.h>
14 
15 namespace pcl
16 {
17  namespace face_detection
18  {
19  template<class FT, class DataSet, class ExampleIndex>
20  class FeatureHandlerDepthAverage: public pcl::FeatureHandler<FT, DataSet, ExampleIndex>
21  {
22 
23  private:
24  int wsize_; //size of the window
25  int max_patch_size_; //max size of the smaller patches
26  int num_channels_; //the number of feature channels
27  float min_valid_small_patch_depth_; //percentage of valid depth in a small patch
28  public:
29 
31  {
32  wsize_ = 80;
33  max_patch_size_ = 40;
34  num_channels_ = 1;
35  min_valid_small_patch_depth_ = 0.5f;
36  }
37 
38  /** \brief Sets the size of the window to extract features.
39  * \param[in] w Window size.
40  */
41  void setWSize(int w)
42  {
43  wsize_ = w;
44  }
45 
46  /** \brief Sets the number of channels a feature has (i.e. 1 - depth, 4 - depth + normals)
47  * \param[in] nf Number of channels.
48  */
49  void setNumChannels(int nf)
50  {
51  num_channels_ = nf;
52  }
53 
54  /** \brief Create a set of random tests to evaluate examples.
55  * \param[in] w Number features to generate.
56  */
57  void setMaxPatchSize(int w)
58  {
59  max_patch_size_ = w;
60  }
61 
62  /** \brief Create a set of random tests to evaluate examples.
63  * \param[in] num_of_features Number features to generated.
64  * \param[out] features Generated features.
65  */
66  /*void createRandomFeatures(const std::size_t num_of_features, std::vector<FT> & features)
67  {
68  srand (time(NULL));
69  int min_s = 10;
70  float range_d = 0.03f;
71  for (std::size_t i = 0; i < num_of_features; i++)
72  {
73  FT f;
74 
75  f.row1_ = rand () % (wsize_ - max_patch_size_ - 1);
76  f.col1_ = rand () % (wsize_ / 2 - max_patch_size_ - 1);
77  f.wsizex1_ = min_s + (rand () % (max_patch_size_ - min_s - 1));
78  f.wsizey1_ = min_s + (rand () % (max_patch_size_ - min_s - 1));
79 
80  f.row2_ = rand () % (wsize_ - max_patch_size_ - 1);
81  f.col2_ = wsize_ / 2 + rand () % (wsize_ / 2 - max_patch_size_ - 1);
82  f.wsizex2_ = min_s + (rand () % (max_patch_size_ - 1 - min_s));
83  f.wsizey2_ = min_s + (rand () % (max_patch_size_ - 1 - min_s));
84 
85  f.used_ii_ = 0;
86  if(num_channels_ > 1)
87  f.used_ii_ = rand() % num_channels_;
88 
89  f.threshold_ = -range_d + (rand () / static_cast<float> (RAND_MAX)) * (range_d * 2.f);
90  features.push_back (f);
91  }
92  }*/
93 
94  void createRandomFeatures(const std::size_t num_of_features, std::vector<FT> & features) override
95  {
96  srand (static_cast<unsigned int>(time (nullptr)));
97  int min_s = 20;
98  float range_d = 0.05f;
99  float incr_d = 0.01f;
100 
101  std::vector < FT > windows_and_functions;
102 
103  for (std::size_t i = 0; i < num_of_features; i++)
104  {
105  FT f;
106 
107  f.row1_ = rand () % (wsize_ - max_patch_size_ - 1);
108  f.col1_ = rand () % (wsize_ / 2 - max_patch_size_ - 1);
109  f.wsizex1_ = min_s + (rand () % (max_patch_size_ - min_s - 1));
110  f.wsizey1_ = min_s + (rand () % (max_patch_size_ - min_s - 1));
111 
112  f.row2_ = rand () % (wsize_ - max_patch_size_ - 1);
113  f.col2_ = wsize_ / 2 + rand () % (wsize_ / 2 - max_patch_size_ - 1);
114  f.wsizex2_ = min_s + (rand () % (max_patch_size_ - 1 - min_s));
115  f.wsizey2_ = min_s + (rand () % (max_patch_size_ - 1 - min_s));
116 
117  f.used_ii_ = 0;
118  if (num_channels_ > 1)
119  f.used_ii_ = rand () % num_channels_;
120 
121  windows_and_functions.push_back (f);
122  }
123 
124  for (std::size_t i = 0; i < windows_and_functions.size (); i++)
125  {
126  FT f = windows_and_functions[i];
127  for (std::size_t j = 0; j <= 10; j++)
128  {
129  f.threshold_ = -range_d + static_cast<float> (j) * incr_d;
130  features.push_back (f);
131  }
132  }
133  }
134 
135  /** \brief Evaluates a feature on the specified set of examples.
136  * \param[in] feature The feature to evaluate.
137  * \param[in] data_set The data set on which the feature is evaluated.
138  * \param[in] examples The set of examples of the data set the feature is evaluated on.
139  * \param[out] results The destination for the results of the feature evaluation.
140  * \param[out] flags Flags that are supplied together with the results.
141  */
142  void evaluateFeature(const FT & feature, DataSet & data_set, std::vector<ExampleIndex> & examples, std::vector<float> & results,
143  std::vector<unsigned char> & flags) const override
144  {
145  results.resize (examples.size ());
146  for (std::size_t i = 0; i < examples.size (); i++)
147  {
148  evaluateFeature (feature, data_set, examples[i], results[i], flags[i]);
149  }
150  }
151 
152  /** \brief Evaluates a feature on the specified example.
153  * \param[in] feature The feature to evaluate.
154  * \param[in] data_set The data set on which the feature is evaluated.
155  * \param[in] example The example of the data set the feature is evaluated on.
156  * \param[out] result The destination for the result of the feature evaluation.
157  * \param[out] flag Flags that are supplied together with the results.
158  */
159  void evaluateFeature(const FT & feature, DataSet & data_set, const ExampleIndex & example, float & result, unsigned char & flag) const override
160  {
161  TrainingExample te = data_set[example];
162  int el_f1 = te.iimages_[feature.used_ii_]->getFiniteElementsCount (te.col_ + feature.col1_, te.row_ + feature.row1_, feature.wsizex1_,
163  feature.wsizey1_);
164  int el_f2 = te.iimages_[feature.used_ii_]->getFiniteElementsCount (te.col_ + feature.col2_, te.row_ + feature.row2_, feature.wsizex2_,
165  feature.wsizey2_);
166 
167  float sum_f1 = static_cast<float>(te.iimages_[feature.used_ii_]->getFirstOrderSum (te.col_ + feature.col1_, te.row_ + feature.row1_, feature.wsizex1_, feature.wsizey1_));
168  float sum_f2 = static_cast<float>(te.iimages_[feature.used_ii_]->getFirstOrderSum (te.col_ + feature.col2_, te.row_ + feature.row2_, feature.wsizex2_, feature.wsizey2_));
169 
170  float f = min_valid_small_patch_depth_;
171  if (el_f1 == 0 || el_f2 == 0 || (el_f1 <= static_cast<int> (f * static_cast<float>(feature.wsizex1_ * feature.wsizey1_)))
172  || (el_f2 <= static_cast<int> (f * static_cast<float>(feature.wsizex2_ * feature.wsizey2_))))
173  {
174  result = static_cast<float> (pcl_round (static_cast<float>(rand ()) / static_cast<float> (RAND_MAX)));
175  flag = 1;
176  } else
177  {
178  result = static_cast<float> ((sum_f1 / static_cast<float>(el_f1) - sum_f2 / static_cast<float>(el_f2)) > feature.threshold_);
179  flag = 0;
180  }
181 
182  }
183 
184  /** \brief Generates evaluation code for the specified feature and writes it to the specified stream.
185  */
186  // param[in] feature The feature for which code is generated.
187  // param[out] stream The destination for the code.
188  void generateCodeForEvaluation(const FT &/*feature*/, ::std::ostream &/*stream*/) const override
189  {
190 
191  }
192  };
193 
194  /** \brief Statistics estimator for regression trees which optimizes information gain and pose parameters error. */
195  template<class LabelDataType, class NodeType, class DataSet, class ExampleIndex>
196  class PoseClassRegressionVarianceStatsEstimator: public pcl::StatsEstimator<LabelDataType, NodeType, DataSet, ExampleIndex>
197  {
198 
199  public:
200  /** \brief Constructor. */
202  branch_estimator_ (branch_estimator)
203  {
204  }
205 
206  /** \brief Destructor. */
208  {
209  }
210 
211  /** \brief Returns the number of branches the corresponding tree has. */
212  inline std::size_t getNumOfBranches() const override
213  {
214  return branch_estimator_->getNumOfBranches ();
215  }
216 
217  /** \brief Returns the label of the specified node.
218  * \param[in] node The node which label is returned.
219  */
220  inline LabelDataType getLabelOfNode(NodeType & node) const override
221  {
222  return node.value;
223  }
224 
225  /** \brief Computes the covariance matrix for translation offsets.
226  * \param[in] data_set The corresponding data set.
227  * \param[in] examples A set of examples from the dataset.
228  * \param[out] covariance_matrix The covariance matrix.
229  * \param[out] centroid The mean of the data.
230  */
231  inline unsigned int computeMeanAndCovarianceOffset(DataSet & data_set, std::vector<ExampleIndex> & examples, Eigen::Matrix3d & covariance_matrix,
232  Eigen::Vector3d & centroid) const
233  {
234  Eigen::Matrix<double, 1, 9, Eigen::RowMajor> accu = Eigen::Matrix<double, 1, 9, Eigen::RowMajor>::Zero ();
235  unsigned int point_count = static_cast<unsigned int> (examples.size ());
236 
237  for (std::size_t i = 0; i < point_count; ++i)
238  {
239  TrainingExample te = data_set[examples[i]];
240  accu[0] += te.trans_[0] * te.trans_[0];
241  accu[1] += te.trans_[0] * te.trans_[1];
242  accu[2] += te.trans_[0] * te.trans_[2];
243  accu[3] += te.trans_[1] * te.trans_[1];
244  accu[4] += te.trans_[1] * te.trans_[2];
245  accu[5] += te.trans_[2] * te.trans_[2];
246  accu[6] += te.trans_[0];
247  accu[7] += te.trans_[1];
248  accu[8] += te.trans_[2];
249  }
250 
251  if (point_count != 0)
252  {
253  accu /= static_cast<double> (point_count);
254  centroid.head<3> ().matrix () = accu.tail<3> ();
255  covariance_matrix.coeffRef (0) = accu[0] - accu[6] * accu[6];
256  covariance_matrix.coeffRef (1) = accu[1] - accu[6] * accu[7];
257  covariance_matrix.coeffRef (2) = accu[2] - accu[6] * accu[8];
258  covariance_matrix.coeffRef (4) = accu[3] - accu[7] * accu[7];
259  covariance_matrix.coeffRef (5) = accu[4] - accu[7] * accu[8];
260  covariance_matrix.coeffRef (8) = accu[5] - accu[8] * accu[8];
261  covariance_matrix.coeffRef (3) = covariance_matrix.coeff (1);
262  covariance_matrix.coeffRef (6) = covariance_matrix.coeff (2);
263  covariance_matrix.coeffRef (7) = covariance_matrix.coeff (5);
264  }
265 
266  return point_count;
267  }
268 
269  /** \brief Computes the covariance matrix for rotation values.
270  * \param[in] data_set The corresponding data set.
271  * \param[in] examples A set of examples from the dataset.
272  * \param[out] covariance_matrix The covariance matrix.
273  * \param[out] centroid The mean of the data.
274  */
275  inline unsigned int computeMeanAndCovarianceAngles(DataSet & data_set, std::vector<ExampleIndex> & examples, Eigen::Matrix3d & covariance_matrix,
276  Eigen::Vector3d & centroid) const
277  {
278  Eigen::Matrix<double, 1, 9, Eigen::RowMajor> accu = Eigen::Matrix<double, 1, 9, Eigen::RowMajor>::Zero ();
279  unsigned int point_count = static_cast<unsigned int> (examples.size ());
280 
281  for (std::size_t i = 0; i < point_count; ++i)
282  {
283  TrainingExample te = data_set[examples[i]];
284  accu[0] += te.rot_[0] * te.rot_[0];
285  accu[1] += te.rot_[0] * te.rot_[1];
286  accu[2] += te.rot_[0] * te.rot_[2];
287  accu[3] += te.rot_[1] * te.rot_[1];
288  accu[4] += te.rot_[1] * te.rot_[2];
289  accu[5] += te.rot_[2] * te.rot_[2];
290  accu[6] += te.rot_[0];
291  accu[7] += te.rot_[1];
292  accu[8] += te.rot_[2];
293  }
294 
295  if (point_count != 0)
296  {
297  accu /= static_cast<double> (point_count);
298  centroid.head<3> ().matrix () = accu.tail<3> ();
299  covariance_matrix.coeffRef (0) = accu[0] - accu[6] * accu[6];
300  covariance_matrix.coeffRef (1) = accu[1] - accu[6] * accu[7];
301  covariance_matrix.coeffRef (2) = accu[2] - accu[6] * accu[8];
302  covariance_matrix.coeffRef (4) = accu[3] - accu[7] * accu[7];
303  covariance_matrix.coeffRef (5) = accu[4] - accu[7] * accu[8];
304  covariance_matrix.coeffRef (8) = accu[5] - accu[8] * accu[8];
305  covariance_matrix.coeffRef (3) = covariance_matrix.coeff (1);
306  covariance_matrix.coeffRef (6) = covariance_matrix.coeff (2);
307  covariance_matrix.coeffRef (7) = covariance_matrix.coeff (5);
308  }
309 
310  return point_count;
311  }
312 
313  /** \brief Computes the information gain obtained by the specified threshold.
314  * \param[in] data_set The data set corresponding to the supplied result data.
315  * \param[in] examples The examples used for extracting the supplied result data.
316  * \param[in] label_data The label data corresponding to the specified examples.
317  * \param[in] results The results computed using the specified examples.
318  * \param[in] flags The flags corresponding to the results.
319  * \param[in] threshold The threshold for which the information gain is computed.
320  */
321  float computeInformationGain(DataSet & data_set, std::vector<ExampleIndex> & examples, std::vector<LabelDataType> & label_data,
322  std::vector<float> & results, std::vector<unsigned char> & flags, const float threshold) const override
323  {
324  const std::size_t num_of_examples = examples.size ();
325  const std::size_t num_of_branches = getNumOfBranches ();
326 
327  // compute variance
328  std::vector < LabelDataType > sums (num_of_branches + 1, 0.f);
329  std::vector < LabelDataType > sqr_sums (num_of_branches + 1, 0.f);
330  std::vector < std::size_t > branch_element_count (num_of_branches + 1, 0.f);
331 
332  for (std::size_t branch_index = 0; branch_index < num_of_branches; ++branch_index)
333  {
334  branch_element_count[branch_index] = 1;
335  ++branch_element_count[num_of_branches];
336  }
337 
338  for (std::size_t example_index = 0; example_index < num_of_examples; ++example_index)
339  {
340  unsigned char branch_index;
341  computeBranchIndex (results[example_index], flags[example_index], threshold, branch_index);
342 
343  LabelDataType label = label_data[example_index];
344 
345  ++branch_element_count[branch_index];
346  ++branch_element_count[num_of_branches];
347 
348  sums[branch_index] += label;
349  sums[num_of_branches] += label;
350  }
351 
352  std::vector<float> hp (num_of_branches + 1, 0.f);
353  for (std::size_t branch_index = 0; branch_index < (num_of_branches + 1); ++branch_index)
354  {
355  float pf = sums[branch_index] / static_cast<float> (branch_element_count[branch_index]);
356  float pnf = (static_cast<LabelDataType>(branch_element_count[branch_index]) - sums[branch_index] + 1.f)
357  / static_cast<LabelDataType> (branch_element_count[branch_index]);
358  hp[branch_index] -= static_cast<float>(pf * std::log (pf) + pnf * std::log (pnf));
359  }
360 
361  //use mean of the examples as purity
362  float purity = sums[num_of_branches] / static_cast<LabelDataType>(branch_element_count[num_of_branches]);
363  float tp = 0.8f;
364 
365  if (purity >= tp)
366  {
367  //compute covariance matrices from translation offsets and angles for the whole set and children
368  //consider only positive examples...
369  std::vector < std::size_t > branch_element_count (num_of_branches + 1, 0);
370  std::vector < std::vector<ExampleIndex> > positive_examples;
371  positive_examples.resize (num_of_branches + 1);
372 
373  std::size_t pos = 0;
374  for (std::size_t example_index = 0; example_index < num_of_examples; ++example_index)
375  {
376  unsigned char branch_index;
377  computeBranchIndex (results[example_index], flags[example_index], threshold, branch_index);
378 
379  LabelDataType label = label_data[example_index];
380 
381  if (label == 1 /*&& !flags[example_index]*/)
382  {
383  ++branch_element_count[branch_index];
384  ++branch_element_count[num_of_branches];
385 
386  positive_examples[branch_index].push_back (examples[example_index]);
387  positive_examples[num_of_branches].push_back (examples[example_index]);
388  pos++;
389  }
390  }
391 
392  //compute covariance from offsets and angles for all branchs
393  std::vector < Eigen::Matrix3d > offset_covariances;
394  std::vector < Eigen::Matrix3d > angle_covariances;
395 
396  std::vector < Eigen::Vector3d > offset_centroids;
397  std::vector < Eigen::Vector3d > angle_centroids;
398 
399  offset_covariances.resize (num_of_branches + 1);
400  angle_covariances.resize (num_of_branches + 1);
401  offset_centroids.resize (num_of_branches + 1);
402  angle_centroids.resize (num_of_branches + 1);
403 
404  for (std::size_t branch_index = 0; branch_index < (num_of_branches + 1); ++branch_index)
405  {
406  computeMeanAndCovarianceOffset (data_set, positive_examples[branch_index], offset_covariances[branch_index],
407  offset_centroids[branch_index]);
408  computeMeanAndCovarianceAngles (data_set, positive_examples[branch_index], angle_covariances[branch_index],
409  angle_centroids[branch_index]);
410  }
411 
412  //update information_gain
413  std::vector<float> hr (num_of_branches + 1, 0.f);
414  for (std::size_t branch_index = 0; branch_index < (num_of_branches + 1); ++branch_index)
415  {
416  hr[branch_index] = static_cast<float>(0.5f * std::log (std::pow (2 * M_PI, 3)
417  * offset_covariances[branch_index].determinant ())
418  + 0.5f * std::log (std::pow (2 * M_PI, 3)
419  * angle_covariances[branch_index].determinant ()));
420  }
421 
422  for (std::size_t branch_index = 0; branch_index < (num_of_branches + 1); ++branch_index)
423  {
424  hp[branch_index] += std::max (sums[branch_index] / static_cast<float> (branch_element_count[branch_index]) - tp, 0.f) * hr[branch_index];
425  }
426  }
427 
428  float information_gain = hp[num_of_branches + 1];
429  for (std::size_t branch_index = 0; branch_index < (num_of_branches); ++branch_index)
430  {
431  information_gain -= static_cast<float> (branch_element_count[branch_index]) / static_cast<float> (branch_element_count[num_of_branches])
432  * hp[branch_index];
433  }
434 
435  return information_gain;
436  }
437 
438  /** \brief Computes the branch indices for all supplied results.
439  * \param[in] results The results the branch indices will be computed for.
440  * \param[in] flags The flags corresponding to the specified results.
441  * \param[in] threshold The threshold used to compute the branch indices.
442  * \param[out] branch_indices The destination for the computed branch indices.
443  */
444  void computeBranchIndices(std::vector<float> & results, std::vector<unsigned char> & flags, const float threshold,
445  std::vector<unsigned char> & branch_indices) const override
446  {
447  const std::size_t num_of_results = results.size ();
448 
449  branch_indices.resize (num_of_results);
450  for (std::size_t result_index = 0; result_index < num_of_results; ++result_index)
451  {
452  unsigned char branch_index;
453  computeBranchIndex (results[result_index], flags[result_index], threshold, branch_index);
454  branch_indices[result_index] = branch_index;
455  }
456  }
457 
458  /** \brief Computes the branch index for the specified result.
459  * \param[in] result The result the branch index will be computed for.
460  * \param[in] flag The flag corresponding to the specified result.
461  * \param[in] threshold The threshold used to compute the branch index.
462  * \param[out] branch_index The destination for the computed branch index.
463  */
464  inline void computeBranchIndex(const float result, const unsigned char flag, const float threshold, unsigned char & branch_index) const override
465  {
466  branch_estimator_->computeBranchIndex (result, flag, threshold, branch_index);
467  }
468 
469  /** \brief Computes and sets the statistics for a node.
470  * \param[in] data_set The data set which is evaluated.
471  * \param[in] examples The examples which define which parts of the data set are used for evaluation.
472  * \param[in] label_data The label_data corresponding to the examples.
473  * \param[out] node The destination node for the statistics.
474  */
475  void computeAndSetNodeStats(DataSet & data_set, std::vector<ExampleIndex> & examples, std::vector<LabelDataType> & label_data, NodeType & node) const override
476  {
477  const std::size_t num_of_examples = examples.size ();
478 
479  LabelDataType sum = 0.0f;
480  LabelDataType sqr_sum = 0.0f;
481  for (std::size_t example_index = 0; example_index < num_of_examples; ++example_index)
482  {
483  const LabelDataType label = label_data[example_index];
484 
485  sum += label;
486  sqr_sum += label * label;
487  }
488 
489  sum /= static_cast<float>(num_of_examples);
490  sqr_sum /= static_cast<float>(num_of_examples);
491 
492  const float variance = sqr_sum - sum * sum;
493 
494  node.value = sum;
495  node.variance = variance;
496 
497  //set node stats regarding pose regression
498  std::vector < ExampleIndex > positive_examples;
499 
500  for (std::size_t example_index = 0; example_index < num_of_examples; ++example_index)
501  {
502  LabelDataType label = label_data[example_index];
503 
504  if (label == 1)
505  positive_examples.push_back (examples[example_index]);
506 
507  }
508 
509  //compute covariance from offsets and angles
510  computeMeanAndCovarianceOffset (data_set, positive_examples, node.covariance_trans_, node.trans_mean_);
511  computeMeanAndCovarianceAngles (data_set, positive_examples, node.covariance_rot_, node.rot_mean_);
512  }
513 
514  /** \brief Generates code for branch index computation.
515  * \param[out] stream The destination for the generated code.
516  */
517  // param[in] node The node for which code is generated.
518  void generateCodeForBranchIndexComputation(NodeType & /*node*/, std::ostream & stream) const override
519  {
520  stream << "ERROR: RegressionVarianceStatsEstimator does not implement generateCodeForBranchIndex(...)";
521  }
522 
523  /** \brief Generates code for label output.
524  * \param[out] stream The destination for the generated code.
525  */
526  // param[in] node The node for which code is generated.
527  void generateCodeForOutput(NodeType & /*node*/, std::ostream & stream) const override
528  {
529  stream << "ERROR: RegressionVarianceStatsEstimator does not implement generateCodeForBranchIndex(...)";
530  }
531 
532  private:
533  /** \brief The branch estimator. */
534  pcl::BranchEstimator * branch_estimator_;
535  };
536  }
537 }
Interface for branch estimators.
virtual std::size_t getNumOfBranches() const =0
Returns the number of branches the corresponding tree has.
virtual void computeBranchIndex(const float result, const unsigned char flag, const float threshold, unsigned char &branch_index) const =0
Computes the branch index for the specified result.
Utility class interface which is used for creating and evaluating features.
Class interface for gathering statistics for decision tree learning.
void setWSize(int w)
Sets the size of the window to extract features.
Definition: rf_face_utils.h:41
void setMaxPatchSize(int w)
Create a set of random tests to evaluate examples.
Definition: rf_face_utils.h:57
void createRandomFeatures(const std::size_t num_of_features, std::vector< FT > &features) override
Create a set of random tests to evaluate examples.
Definition: rf_face_utils.h:94
void generateCodeForEvaluation(const FT &, ::std::ostream &) const override
Generates evaluation code for the specified feature and writes it to the specified stream.
void evaluateFeature(const FT &feature, DataSet &data_set, const ExampleIndex &example, float &result, unsigned char &flag) const override
Evaluates a feature on the specified example.
void setNumChannels(int nf)
Sets the number of channels a feature has (i.e.
Definition: rf_face_utils.h:49
void evaluateFeature(const FT &feature, DataSet &data_set, std::vector< ExampleIndex > &examples, std::vector< float > &results, std::vector< unsigned char > &flags) const override
Evaluates a feature on the specified set of examples.
Statistics estimator for regression trees which optimizes information gain and pose parameters error.
void computeAndSetNodeStats(DataSet &data_set, std::vector< ExampleIndex > &examples, std::vector< LabelDataType > &label_data, NodeType &node) const override
Computes and sets the statistics for a node.
void computeBranchIndices(std::vector< float > &results, std::vector< unsigned char > &flags, const float threshold, std::vector< unsigned char > &branch_indices) const override
Computes the branch indices for all supplied results.
unsigned int computeMeanAndCovarianceAngles(DataSet &data_set, std::vector< ExampleIndex > &examples, Eigen::Matrix3d &covariance_matrix, Eigen::Vector3d &centroid) const
Computes the covariance matrix for rotation values.
LabelDataType getLabelOfNode(NodeType &node) const override
Returns the label of the specified node.
PoseClassRegressionVarianceStatsEstimator(BranchEstimator *branch_estimator)
Constructor.
unsigned int computeMeanAndCovarianceOffset(DataSet &data_set, std::vector< ExampleIndex > &examples, Eigen::Matrix3d &covariance_matrix, Eigen::Vector3d &centroid) const
Computes the covariance matrix for translation offsets.
void generateCodeForBranchIndexComputation(NodeType &, std::ostream &stream) const override
Generates code for branch index computation.
void computeBranchIndex(const float result, const unsigned char flag, const float threshold, unsigned char &branch_index) const override
Computes the branch index for the specified result.
void generateCodeForOutput(NodeType &, std::ostream &stream) const override
Generates code for label output.
float computeInformationGain(DataSet &data_set, std::vector< ExampleIndex > &examples, std::vector< LabelDataType > &label_data, std::vector< float > &results, std::vector< unsigned char > &flags, const float threshold) const override
Computes the information gain obtained by the specified threshold.
std::size_t getNumOfBranches() const override
Returns the number of branches the corresponding tree has.
std::vector< pcl::IntegralImage2D< float, 1 >::Ptr > iimages_
Definition: face_common.h:16
__inline double pcl_round(double number)
Win32 doesn't seem to have rounding functions.
Definition: pcl_macros.h:239
#define M_PI
Definition: pcl_macros.h:201