Point Cloud Library (PCL)
1.7.0
|
00001 /* 00002 * Software License Agreement (BSD License) 00003 * 00004 * Point Cloud Library (PCL) - www.pointclouds.org 00005 * Copyright (c) 2010-2011, Willow Garage, Inc. 00006 * Copyright (c) 2012-, Open Perception, Inc. 00007 * 00008 * All rights reserved. 00009 * 00010 * Redistribution and use in source and binary forms, with or without 00011 * modification, are permitted provided that the following conditions 00012 * are met: 00013 * 00014 * * Redistributions of source code must retain the above copyright 00015 * notice, this list of conditions and the following disclaimer. 00016 * * Redistributions in binary form must reproduce the above 00017 * copyright notice, this list of conditions and the following 00018 * disclaimer in the documentation and/or other materials provided 00019 * with the distribution. 00020 * * Neither the name of the copyright holder(s) nor the names of its 00021 * contributors may be used to endorse or promote products derived 00022 * from this software without specific prior written permission. 00023 * 00024 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 00025 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 00026 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS 00027 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 00028 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 00029 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 00030 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 00031 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 00032 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 00033 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN 00034 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 00035 * POSSIBILITY OF SUCH DAMAGE. 00036 * 00037 * $Id$ 00038 * 00039 */ 00040 00041 #ifndef PCL_FEATURES_IMPL_MOMENT_INVARIANTS_H_ 00042 #define PCL_FEATURES_IMPL_MOMENT_INVARIANTS_H_ 00043 00044 #include <pcl/features/moment_invariants.h> 00045 #include <pcl/common/centroid.h> 00046 00047 ////////////////////////////////////////////////////////////////////////////////////////////// 00048 template <typename PointInT, typename PointOutT> void 00049 pcl::MomentInvariantsEstimation<PointInT, PointOutT>::computePointMomentInvariants ( 00050 const pcl::PointCloud<PointInT> &cloud, const std::vector<int> &indices, 00051 float &j1, float &j2, float &j3) 00052 { 00053 // Estimate the XYZ centroid 00054 compute3DCentroid (cloud, indices, xyz_centroid_); 00055 00056 // Initalize the centralized moments 00057 float mu200 = 0, mu020 = 0, mu002 = 0, mu110 = 0, mu101 = 0, mu011 = 0; 00058 00059 // Iterate over the nearest neighbors set 00060 for (size_t nn_idx = 0; nn_idx < indices.size (); ++nn_idx) 00061 { 00062 // Demean the points 00063 temp_pt_[0] = cloud.points[indices[nn_idx]].x - xyz_centroid_[0]; 00064 temp_pt_[1] = cloud.points[indices[nn_idx]].y - xyz_centroid_[1]; 00065 temp_pt_[2] = cloud.points[indices[nn_idx]].z - xyz_centroid_[2]; 00066 00067 mu200 += temp_pt_[0] * temp_pt_[0]; 00068 mu020 += temp_pt_[1] * temp_pt_[1]; 00069 mu002 += temp_pt_[2] * temp_pt_[2]; 00070 mu110 += temp_pt_[0] * temp_pt_[1]; 00071 mu101 += temp_pt_[0] * temp_pt_[2]; 00072 mu011 += temp_pt_[1] * temp_pt_[2]; 00073 } 00074 00075 // Save the moment invariants 00076 j1 = mu200 + mu020 + mu002; 00077 j2 = mu200*mu020 + mu200*mu002 + mu020*mu002 - mu110*mu110 - mu101*mu101 - mu011*mu011; 00078 j3 = mu200*mu020*mu002 + 2*mu110*mu101*mu011 - mu002*mu110*mu110 - mu020*mu101*mu101 - mu200*mu011*mu011; 00079 } 00080 00081 ////////////////////////////////////////////////////////////////////////////////////////////// 00082 template <typename PointInT, typename PointOutT> void 00083 pcl::MomentInvariantsEstimation<PointInT, PointOutT>::computePointMomentInvariants ( 00084 const pcl::PointCloud<PointInT> &cloud, float &j1, float &j2, float &j3) 00085 { 00086 // Estimate the XYZ centroid 00087 compute3DCentroid (cloud, xyz_centroid_); 00088 00089 // Initalize the centralized moments 00090 float mu200 = 0, mu020 = 0, mu002 = 0, mu110 = 0, mu101 = 0, mu011 = 0; 00091 00092 // Iterate over the nearest neighbors set 00093 for (size_t nn_idx = 0; nn_idx < cloud.points.size (); ++nn_idx ) 00094 { 00095 // Demean the points 00096 temp_pt_[0] = cloud.points[nn_idx].x - xyz_centroid_[0]; 00097 temp_pt_[1] = cloud.points[nn_idx].y - xyz_centroid_[1]; 00098 temp_pt_[2] = cloud.points[nn_idx].z - xyz_centroid_[2]; 00099 00100 mu200 += temp_pt_[0] * temp_pt_[0]; 00101 mu020 += temp_pt_[1] * temp_pt_[1]; 00102 mu002 += temp_pt_[2] * temp_pt_[2]; 00103 mu110 += temp_pt_[0] * temp_pt_[1]; 00104 mu101 += temp_pt_[0] * temp_pt_[2]; 00105 mu011 += temp_pt_[1] * temp_pt_[2]; 00106 } 00107 00108 // Save the moment invariants 00109 j1 = mu200 + mu020 + mu002; 00110 j2 = mu200*mu020 + mu200*mu002 + mu020*mu002 - mu110*mu110 - mu101*mu101 - mu011*mu011; 00111 j3 = mu200*mu020*mu002 + 2*mu110*mu101*mu011 - mu002*mu110*mu110 - mu020*mu101*mu101 - mu200*mu011*mu011; 00112 } 00113 00114 ////////////////////////////////////////////////////////////////////////////////////////////// 00115 template <typename PointInT, typename PointOutT> void 00116 pcl::MomentInvariantsEstimation<PointInT, PointOutT>::computeFeature (PointCloudOut &output) 00117 { 00118 // Allocate enough space to hold the results 00119 // \note This resize is irrelevant for a radiusSearch (). 00120 std::vector<int> nn_indices (k_); 00121 std::vector<float> nn_dists (k_); 00122 00123 output.is_dense = true; 00124 // Save a few cycles by not checking every point for NaN/Inf values if the cloud is set to dense 00125 if (input_->is_dense) 00126 { 00127 // Iterating over the entire index vector 00128 for (size_t idx = 0; idx < indices_->size (); ++idx) 00129 { 00130 if (this->searchForNeighbors ((*indices_)[idx], search_parameter_, nn_indices, nn_dists) == 0) 00131 { 00132 output.points[idx].j1 = output.points[idx].j2 = output.points[idx].j3 = std::numeric_limits<float>::quiet_NaN (); 00133 output.is_dense = false; 00134 continue; 00135 } 00136 00137 computePointMomentInvariants (*surface_, nn_indices, 00138 output.points[idx].j1, output.points[idx].j2, output.points[idx].j3); 00139 } 00140 } 00141 else 00142 { 00143 // Iterating over the entire index vector 00144 for (size_t idx = 0; idx < indices_->size (); ++idx) 00145 { 00146 if (!isFinite ((*input_)[(*indices_)[idx]]) || 00147 this->searchForNeighbors ((*indices_)[idx], search_parameter_, nn_indices, nn_dists) == 0) 00148 { 00149 output.points[idx].j1 = output.points[idx].j2 = output.points[idx].j3 = std::numeric_limits<float>::quiet_NaN (); 00150 output.is_dense = false; 00151 continue; 00152 } 00153 00154 computePointMomentInvariants (*surface_, nn_indices, 00155 output.points[idx].j1, output.points[idx].j2, output.points[idx].j3); 00156 } 00157 } 00158 } 00159 00160 #define PCL_INSTANTIATE_MomentInvariantsEstimation(T,NT) template class PCL_EXPORTS pcl::MomentInvariantsEstimation<T,NT>; 00161 00162 #endif // PCL_FEATURES_IMPL_MOMENT_INVARIANTS_H_ 00163