Point Cloud Library (PCL)  1.11.1-dev
extract_labeled_clusters.hpp
1 /*
2  * Software License Agreement (BSD License)
3  *
4  * Copyright (c) 2011, Willow Garage, Inc.
5  * All rights reserved.
6  *
7  * Redistribution and use in source and binary forms, with or without
8  * modification, are permitted provided that the following conditions
9  * are met:
10  *
11  * * Redistributions of source code must retain the above copyright
12  * notice, this list of conditions and the following disclaimer.
13  * * Redistributions in binary form must reproduce the above
14  * copyright notice, this list of conditions and the following
15  * disclaimer in the documentation and/or other materials provided
16  * with the distribution.
17  * * Neither the name of the copyright holder(s) nor the names of its
18  * contributors may be used to endorse or promote products derived
19  * from this software without specific prior written permission.
20  *
21  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22  * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23  * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
24  * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
25  * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
26  * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
27  * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
28  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
29  * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
30  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
31  * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
32  * POSSIBILITY OF SUCH DAMAGE.
33  *
34  * $id $
35  */
36 
37 #ifndef PCL_SEGMENTATION_IMPL_EXTRACT_LABELED_CLUSTERS_H_
38 #define PCL_SEGMENTATION_IMPL_EXTRACT_LABELED_CLUSTERS_H_
39 
40 #include <pcl/segmentation/extract_labeled_clusters.h>
41 
42 //////////////////////////////////////////////////////////////////////////////////////////////
43 template <typename PointT>
44 void
46  const PointCloud<PointT>& cloud,
47  const typename search::Search<PointT>::Ptr& tree,
48  float tolerance,
49  std::vector<std::vector<PointIndices>>& labeled_clusters,
50  unsigned int min_pts_per_cluster,
51  unsigned int max_pts_per_cluster,
52  unsigned int)
53 {
54  pcl::extractLabeledEuclideanClusters<PointT>(cloud,
55  tree,
56  tolerance,
57  labeled_clusters,
58  min_pts_per_cluster,
59  max_pts_per_cluster);
60 }
61 
62 template <typename PointT>
63 void
65  const PointCloud<PointT>& cloud,
66  const typename search::Search<PointT>::Ptr& tree,
67  float tolerance,
68  std::vector<std::vector<PointIndices>>& labeled_clusters,
69  unsigned int min_pts_per_cluster,
70  unsigned int max_pts_per_cluster)
71 {
72  if (tree->getInputCloud()->size() != cloud.size()) {
73  PCL_ERROR("[pcl::extractLabeledEuclideanClusters] Tree built for a different point "
74  "cloud dataset (%lu) than the input cloud (%lu)!\n",
75  tree->getInputCloud()->size(),
76  cloud.size());
77  return;
78  }
79  // Create a bool vector of processed point indices, and initialize it to false
80  std::vector<bool> processed(cloud.size(), false);
81 
82  Indices nn_indices;
83  std::vector<float> nn_distances;
84 
85  // Process all points in the indices vector
86  for (index_t i = 0; i < static_cast<index_t>(cloud.size()); ++i) {
87  if (processed[i])
88  continue;
89 
90  Indices seed_queue;
91  int sq_idx = 0;
92  seed_queue.push_back(i);
93 
94  processed[i] = true;
95 
96  while (sq_idx < static_cast<int>(seed_queue.size())) {
97  // Search for sq_idx
98  int ret = tree->radiusSearch(seed_queue[sq_idx],
99  tolerance,
100  nn_indices,
101  nn_distances,
102  std::numeric_limits<int>::max());
103  if (ret == -1)
104  PCL_ERROR("radiusSearch on tree came back with error -1");
105  if (!ret) {
106  sq_idx++;
107  continue;
108  }
109 
110  for (std::size_t j = 1; j < nn_indices.size();
111  ++j) // nn_indices[0] should be sq_idx
112  {
113  if (processed[nn_indices[j]]) // Has this point been processed before ?
114  continue;
115  if (cloud[i].label == cloud[nn_indices[j]].label) {
116  // Perform a simple Euclidean clustering
117  seed_queue.push_back(nn_indices[j]);
118  processed[nn_indices[j]] = true;
119  }
120  }
121 
122  sq_idx++;
123  }
124 
125  // If this queue is satisfactory, add to the clusters
126  if (seed_queue.size() >= min_pts_per_cluster &&
127  seed_queue.size() <= max_pts_per_cluster) {
129  r.indices.resize(seed_queue.size());
130  for (std::size_t j = 0; j < seed_queue.size(); ++j)
131  r.indices[j] = seed_queue[j];
132 
133  std::sort(r.indices.begin(), r.indices.end());
134  r.indices.erase(std::unique(r.indices.begin(), r.indices.end()), r.indices.end());
135 
136  r.header = cloud.header;
137  labeled_clusters[cloud[i].label].push_back(
138  r); // We could avoid a copy by working directly in the vector
139  }
140  }
141 }
142 //////////////////////////////////////////////////////////////////////////////////////////////
143 //////////////////////////////////////////////////////////////////////////////////////////////
144 //////////////////////////////////////////////////////////////////////////////////////////////
145 
146 template <typename PointT>
147 void
149  std::vector<std::vector<PointIndices>>& labeled_clusters)
150 {
151  if (!initCompute() || (input_ && input_->empty()) ||
152  (indices_ && indices_->empty())) {
153  labeled_clusters.clear();
154  return;
155  }
156 
157  // Initialize the spatial locator
158  if (!tree_) {
159  if (input_->isOrganized())
160  tree_.reset(new pcl::search::OrganizedNeighbor<PointT>());
161  else
162  tree_.reset(new pcl::search::KdTree<PointT>(false));
163  }
164 
165  // Send the input dataset to the spatial locator
166  tree_->setInputCloud(input_);
168  tree_,
169  static_cast<float>(cluster_tolerance_),
170  labeled_clusters,
171  min_pts_per_cluster_,
172  max_pts_per_cluster_);
173 
174  // Sort the clusters based on their size (largest one first)
175  for (auto& labeled_cluster : labeled_clusters)
176  std::sort(labeled_cluster.rbegin(), labeled_cluster.rend(), comparePointClusters);
177 
178  deinitCompute();
179 }
180 
181 #define PCL_INSTANTIATE_LabeledEuclideanClusterExtraction(T) \
182  template class PCL_EXPORTS pcl::LabeledEuclideanClusterExtraction<T>;
183 #define PCL_INSTANTIATE_extractLabeledEuclideanClusters_deprecated(T) \
184  template void PCL_EXPORTS pcl::extractLabeledEuclideanClusters<T>( \
185  const pcl::PointCloud<T>&, \
186  const typename pcl::search::Search<T>::Ptr&, \
187  float, \
188  std::vector<std::vector<pcl::PointIndices>>&, \
189  unsigned int, \
190  unsigned int, \
191  unsigned int);
192 #define PCL_INSTANTIATE_extractLabeledEuclideanClusters(T) \
193  template void PCL_EXPORTS pcl::extractLabeledEuclideanClusters<T>( \
194  const pcl::PointCloud<T>&, \
195  const typename pcl::search::Search<T>::Ptr&, \
196  float, \
197  std::vector<std::vector<pcl::PointIndices>>&, \
198  unsigned int, \
199  unsigned int);
200 
201 #endif // PCL_EXTRACT_CLUSTERS_IMPL_H_
pcl::search::Search::getInputCloud
virtual PointCloudConstPtr getInputCloud() const
Get a pointer to the input point cloud dataset.
Definition: search.h:125
pcl::PointIndices::indices
Indices indices
Definition: PointIndices.h:21
pcl::search::Search::radiusSearch
virtual int radiusSearch(const PointT &point, double radius, Indices &k_indices, std::vector< float > &k_sqr_distances, unsigned int max_nn=0) const =0
Search for all the nearest neighbors of the query point in a given radius.
pcl::PointIndices::header
::pcl::PCLHeader header
Definition: PointIndices.h:19
pcl::extractLabeledEuclideanClusters
void extractLabeledEuclideanClusters(const PointCloud< PointT > &cloud, const typename search::Search< PointT >::Ptr &tree, float tolerance, std::vector< std::vector< PointIndices >> &labeled_clusters, unsigned int min_pts_per_cluster, unsigned int max_pts_per_cluster, unsigned int max_label)
Decompose a region of space into clusters based on the Euclidean distance between points.
Definition: extract_labeled_clusters.hpp:45
pcl::PointCloud
PointCloud represents the base class in PCL for storing collections of 3D points.
Definition: distances.h:55
pcl::index_t
detail::int_type_t< detail::index_type_size, detail::index_type_signed > index_t
Type used for an index in PCL.
Definition: types.h:110
pcl::gpu::comparePointClusters
bool comparePointClusters(const pcl::PointIndices &a, const pcl::PointIndices &b)
Sort clusters method (for std::sort).
Definition: gpu_extract_clusters.h:161
pcl::search::KdTree< PointT >
pcl::search::Search::Ptr
shared_ptr< pcl::search::Search< PointT > > Ptr
Definition: search.h:81
pcl::PointIndices
Definition: PointIndices.h:11
pcl::PointCloud::header
pcl::PCLHeader header
The point cloud header.
Definition: point_cloud.h:386
pcl::Indices
IndicesAllocator<> Indices
Type used for indices in PCL.
Definition: types.h:131
pcl::search::OrganizedNeighbor
OrganizedNeighbor is a class for optimized nearest neigbhor search in organized point clouds.
Definition: organized.h:60
pcl::PointCloud::size
std::size_t size() const
Definition: point_cloud.h:437
pcl::LabeledEuclideanClusterExtraction::extract
void extract(std::vector< std::vector< PointIndices >> &labeled_clusters)
Cluster extraction in a PointCloud given by <setInputCloud (), setIndices ()>
Definition: extract_labeled_clusters.hpp:148