Point Cloud Library (PCL)  1.14.0-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 {
53  if (tree->getInputCloud()->size() != cloud.size()) {
54  PCL_ERROR("[pcl::extractLabeledEuclideanClusters] Tree built for a different point "
55  "cloud dataset (%lu) than the input cloud (%lu)!\n",
56  tree->getInputCloud()->size(),
57  cloud.size());
58  return;
59  }
60  // Create a bool vector of processed point indices, and initialize it to false
61  std::vector<bool> processed(cloud.size(), false);
62 
63  Indices nn_indices;
64  std::vector<float> nn_distances;
65 
66  // Process all points in the indices vector
67  for (index_t i = 0; i < static_cast<index_t>(cloud.size()); ++i) {
68  if (processed[i])
69  continue;
70 
71  Indices seed_queue;
72  int sq_idx = 0;
73  seed_queue.push_back(i);
74 
75  processed[i] = true;
76 
77  while (sq_idx < static_cast<int>(seed_queue.size())) {
78  // Search for sq_idx
79  int ret = tree->radiusSearch(seed_queue[sq_idx],
80  tolerance,
81  nn_indices,
82  nn_distances,
83  std::numeric_limits<int>::max());
84  if (ret == -1)
85  PCL_ERROR("radiusSearch on tree came back with error -1");
86  if (!ret) {
87  sq_idx++;
88  continue;
89  }
90 
91  for (std::size_t j = 1; j < nn_indices.size();
92  ++j) // nn_indices[0] should be sq_idx
93  {
94  if (processed[nn_indices[j]]) // Has this point been processed before ?
95  continue;
96  if (cloud[i].label == cloud[nn_indices[j]].label) {
97  // Perform a simple Euclidean clustering
98  seed_queue.push_back(nn_indices[j]);
99  processed[nn_indices[j]] = true;
100  }
101  }
102 
103  sq_idx++;
104  }
105 
106  // If this queue is satisfactory, add to the clusters
107  if (seed_queue.size() >= min_pts_per_cluster &&
108  seed_queue.size() <= max_pts_per_cluster) {
110  r.indices.resize(seed_queue.size());
111  for (std::size_t j = 0; j < seed_queue.size(); ++j)
112  r.indices[j] = seed_queue[j];
113  // After clustering, indices are out of order, so sort them
114  std::sort(r.indices.begin(), r.indices.end());
115 
116  r.header = cloud.header;
117  labeled_clusters[cloud[i].label].push_back(
118  r); // We could avoid a copy by working directly in the vector
119  }
120  }
121 }
122 //////////////////////////////////////////////////////////////////////////////////////////////
123 //////////////////////////////////////////////////////////////////////////////////////////////
124 //////////////////////////////////////////////////////////////////////////////////////////////
125 
126 template <typename PointT>
127 void
129  std::vector<std::vector<PointIndices>>& labeled_clusters)
130 {
131  if (!initCompute() || (input_ && input_->empty()) ||
132  (indices_ && indices_->empty())) {
133  labeled_clusters.clear();
134  return;
135  }
136 
137  // Initialize the spatial locator
138  if (!tree_) {
139  if (input_->isOrganized())
140  tree_.reset(new pcl::search::OrganizedNeighbor<PointT>());
141  else
142  tree_.reset(new pcl::search::KdTree<PointT>(false));
143  }
144 
145  // Send the input dataset to the spatial locator
146  tree_->setInputCloud(input_);
148  tree_,
149  static_cast<float>(cluster_tolerance_),
150  labeled_clusters,
151  min_pts_per_cluster_,
152  max_pts_per_cluster_);
153 
154  // Sort the clusters based on their size (largest one first)
155  for (auto& labeled_cluster : labeled_clusters)
156  std::sort(labeled_cluster.rbegin(), labeled_cluster.rend(), comparePointClusters);
157 
158  deinitCompute();
159 }
160 
161 #define PCL_INSTANTIATE_LabeledEuclideanClusterExtraction(T) \
162  template class PCL_EXPORTS pcl::LabeledEuclideanClusterExtraction<T>;
163 #define PCL_INSTANTIATE_extractLabeledEuclideanClusters(T) \
164  template void PCL_EXPORTS pcl::extractLabeledEuclideanClusters<T>( \
165  const pcl::PointCloud<T>&, \
166  const typename pcl::search::Search<T>::Ptr&, \
167  float, \
168  std::vector<std::vector<pcl::PointIndices>>&, \
169  unsigned int, \
170  unsigned int);
171 
172 #endif // PCL_EXTRACT_CLUSTERS_IMPL_H_
void extract(std::vector< std::vector< PointIndices >> &labeled_clusters)
Cluster extraction in a PointCloud given by <setInputCloud (), setIndices ()>
PointCloud represents the base class in PCL for storing collections of 3D points.
Definition: point_cloud.h:173
pcl::PCLHeader header
The point cloud header.
Definition: point_cloud.h:392
std::size_t size() const
Definition: point_cloud.h:443
search::KdTree is a wrapper class which inherits the pcl::KdTree class for performing search function...
Definition: kdtree.h:62
OrganizedNeighbor is a class for optimized nearest neighbor search in organized projectable point clo...
Definition: organized.h:65
shared_ptr< pcl::search::Search< PointT > > Ptr
Definition: search.h:81
virtual PointCloudConstPtr getInputCloud() const
Get a pointer to the input point cloud dataset.
Definition: search.h:124
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.
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=1, unsigned int max_pts_per_cluster=std::numeric_limits< unsigned int >::max())
Decompose a region of space into clusters based on the Euclidean distance between points.
bool comparePointClusters(const pcl::PointIndices &a, const pcl::PointIndices &b)
Sort clusters method (for std::sort).
detail::int_type_t< detail::index_type_size, detail::index_type_signed > index_t
Type used for an index in PCL.
Definition: types.h:112
IndicesAllocator<> Indices
Type used for indices in PCL.
Definition: types.h:133
::pcl::PCLHeader header
Definition: PointIndices.h:18