点云分割是根据空间，几何和纹理等特征对点云进行划分，使得同一划分内的点云拥有相似的特征，点云的有效分割往往是许多应用的前提，例如逆向工作，CAD领域对零件的不同扫描表面进行分割，然后才能更好的进行空洞修复曲面重建，特征描述和提取，进而进行基于3D内容的检索，组合重用等。
案例分析
用一组点云数据做简单的平面的分割：
planar_segmentation.cpp
#include <iostream> #include <pcl/ModelCoefficients.h> #include <pcl/io/pcd_io.h> #include <pcl/point_types.h> #include <pcl/sample_consensus/method_types.h> //随机参数估计方法头文件 #include <pcl/sample_consensus/model_types.h> //模型定义头文件 #include <pcl/segmentation/sac_segmentation.h> //基于采样一致性分割的类的头文件 int main (int argc, char** argv) { pcl::PointCloud<pcl::PointXYZ>::Ptr cloud(new pcl::PointCloud<pcl::PointXYZ>); // 填充点云 cloud->width = 15; cloud->height = 1; cloud->points.resize (cloud->width * cloud->height); // 生成数据，采用随机数填充点云的x,y坐标，都处于z为1的平面上 for (size_t i = 0; i < cloud->points.size (); ++i) { cloud->points[i].x = 1024 * rand () / (RAND_MAX + 1.0f); cloud->points[i].y = 1024 * rand () / (RAND_MAX + 1.0f); cloud->points[i].z = 1.0; } // 设置几个局外点，即重新设置几个点的z值，使其偏离z为1的平面 cloud->points[0].z = 2.0; cloud->points[3].z = -2.0; cloud->points[6].z = 4.0; std::cerr << "Point cloud data: " << cloud->points.size () << " points" << std::endl; //打印 for (size_t i = 0; i < cloud->points.size (); ++i) std::cerr << " " << cloud->points[i].x << " " << cloud->points[i].y << " " << cloud->points[i].z << std::endl; //创建分割时所需要的模型系数对象，coefficients及存储内点的点索引集合对象inliers pcl::ModelCoefficients::Ptr coefficients (new pcl::ModelCoefficients); pcl::PointIndices::Ptr inliers (new pcl::PointIndices); // 创建分割对象 pcl::SACSegmentation<pcl::PointXYZ> seg; // 可选择配置，设置模型系数需要优化 seg.setOptimizeCoefficients (true); // 必要的配置，设置分割的模型类型，所用的随机参数估计方法，距离阀值，输入点云 seg.setModelType (pcl::SACMODEL_PLANE); //设置模型类型 seg.setMethodType (pcl::SAC_RANSAC); //设置随机采样一致性方法类型 seg.setDistanceThreshold (0.01); //设定距离阀值，距离阀值决定了点被认为是局内点是必须满足的条件 //表示点到估计模型的距离最大值， seg.setInputCloud (cloud); //引发分割实现，存储分割结果到点几何inliers及存储平面模型的系数coefficients seg.segment (*inliers, *coefficients); if (inliers->indices.size () == 0) { PCL_ERROR ("Could not estimate a planar model for the given dataset."); return (-1); } //打印出平面模型 std::cerr << "Model coefficients: " << coefficients->values[0] << " " << coefficients->values[1] << " " << coefficients->values[2] << " " << coefficients->values[3] << std::endl; std::cerr << "Model inliers: " << inliers->indices.size () << std::endl; for (size_t i = 0; i < inliers->indices.size (); ++i) std::cerr << inliers->indices[i] << " " << cloud->points[inliers->indices[i]].x << " " << cloud->points[inliers->indices[i]].y << " " << cloud->points[inliers->indices[i]].z << std::endl; return (0); }
结果如下：开始打印的数据为手动添加的点云数据，并非都处于z为1的平面上，通过分割对象的处理后提取所有内点，即过滤掉z不等于1的点集
（2）实现圆柱体模型的分割：采用随机采样一致性估计从带有噪声的点云中提取一个圆柱体模型。
新建文件cylinder_segmentation.cpp
#include <pcl/ModelCoefficients.h> #include <pcl/io/pcd_io.h> #include <pcl/point_types.h> #include <pcl/filters/extract_indices.h> #include <pcl/filters/passthrough.h> #include <pcl/features/normal_3d.h> #include <pcl/sample_consensus/method_types.h> #include <pcl/sample_consensus/model_types.h> #include <pcl/segmentation/sac_segmentation.h> typedef pcl::PointXYZ PointT; int main (int argc, char** argv) { // All the objects needed pcl::PCDReader reader; //PCD文件读取对象 pcl::PassThrough<PointT> pass; //直通滤波对象 pcl::NormalEstimation<PointT, pcl::Normal> ne; //法线估计对象 pcl::SACSegmentationFromNormals<PointT, pcl::Normal> seg; //分割对象 pcl::PCDWriter writer; //PCD文件读取对象 pcl::ExtractIndices<PointT> extract; //点提取对象 pcl::ExtractIndices<pcl::Normal> extract_normals; ///点提取对象 pcl::search::KdTree<PointT>::Ptr tree (new pcl::search::KdTree<PointT> ()); // Datasets pcl::PointCloud<PointT>::Ptr cloud (new pcl::PointCloud<PointT>); pcl::PointCloud<PointT>::Ptr cloud_filtered (new pcl::PointCloud<PointT>); pcl::PointCloud<pcl::Normal>::Ptr cloud_normals (new pcl::PointCloud<pcl::Normal>); pcl::PointCloud<PointT>::Ptr cloud_filtered2 (new pcl::PointCloud<PointT>); pcl::PointCloud<pcl::Normal>::Ptr cloud_normals2 (new pcl::PointCloud<pcl::Normal>); pcl::ModelCoefficients::Ptr coefficients_plane (new pcl::ModelCoefficients), coefficients_cylinder (new pcl::ModelCoefficients); pcl::PointIndices::Ptr inliers_plane (new pcl::PointIndices), inliers_cylinder (new pcl::PointIndices); // Read in the cloud data reader.read ("table_scene_mug_stereo_textured.pcd", *cloud); std::cerr << "PointCloud has: " << cloud->points.size () << " data points." << std::endl; // 直通滤波，将Z轴不在（0，1.5）范围的点过滤掉，将剩余的点存储到cloud_filtered对象中 pass.setInputCloud (cloud); pass.setFilterFieldName ("z"); pass.setFilterLimits (0, 1.5); pass.filter (*cloud_filtered); std::cerr << "PointCloud after filtering has: " << cloud_filtered->points.size () << " data points." << std::endl; // 过滤后的点云进行法线估计，为后续进行基于法线的分割准备数据 ne.setSearchMethod (tree); ne.setInputCloud (cloud_filtered); ne.setKSearch (50); ne.compute (*cloud_normals); // Create the segmentation object for the planar model and set all the parameters seg.setOptimizeCoefficients (true); seg.setModelType (pcl::SACMODEL_NORMAL_PLANE); seg.setNormalDistanceWeight (0.1); seg.setMethodType (pcl::SAC_RANSAC); seg.setMaxIterations (100); seg.setDistanceThreshold (0.03); seg.setInputCloud (cloud_filtered); seg.setInputNormals (cloud_normals); //获取平面模型的系数和处在平面的内点 seg.segment (*inliers_plane, *coefficients_plane); std::cerr << "Plane coefficients: " << *coefficients_plane << std::endl; // 从点云中抽取分割的处在平面上的点集 extract.setInputCloud (cloud_filtered); extract.setIndices (inliers_plane); extract.setNegative (false); // 存储分割得到的平面上的点到点云文件 pcl::PointCloud<PointT>::Ptr cloud_plane (new pcl::PointCloud<PointT> ()); extract.filter (*cloud_plane); std::cerr << "PointCloud representing the planar component: " << cloud_plane->points.size () << " data points." << std::endl; writer.write ("table_scene_mug_stereo_textured_plane.pcd", *cloud_plane, false); // Remove the planar inliers, extract the rest extract.setNegative (true); extract.filter (*cloud_filtered2); extract_normals.setNegative (true); extract_normals.setInputCloud (cloud_normals); extract_normals.setIndices (inliers_plane); extract_normals.filter (*cloud_normals2); // Create the segmentation object for cylinder segmentation and set all the parameters seg.setOptimizeCoefficients (true); //设置对估计模型优化 seg.setModelType (pcl::SACMODEL_CYLINDER); //设置分割模型为圆柱形 seg.setMethodType (pcl::SAC_RANSAC); //参数估计方法 seg.setNormalDistanceWeight (0.1); //设置表面法线权重系数 seg.setMaxIterations (10000); //设置迭代的最大次数10000 seg.setDistanceThreshold (0.05); //设置内点到模型的距离允许最大值 seg.setRadiusLimits (0, 0.1); //设置估计出的圆柱模型的半径的范围 seg.setInputCloud (cloud_filtered2); seg.setInputNormals (cloud_normals2); // Obtain the cylinder inliers and coefficients seg.segment (*inliers_cylinder, *coefficients_cylinder); std::cerr << "Cylinder coefficients: " << *coefficients_cylinder << std::endl; // Write the cylinder inliers to disk extract.setInputCloud (cloud_filtered2); extract.setIndices (inliers_cylinder); extract.setNegative (false); pcl::PointCloud<PointT>::Ptr cloud_cylinder (new pcl::PointCloud<PointT> ()); extract.filter (*cloud_cylinder); if (cloud_cylinder->points.empty ()) std::cerr << "Can't find the cylindrical component." << std::endl; else { std::cerr << "PointCloud representing the cylindrical component: " << cloud_cylinder->points.size () << " data points." << std::endl; writer.write ("table_scene_mug_stereo_textured_cylinder.pcd", *cloud_cylinder, false); } return (0); }
试验打印的结果如下
原始点云可视化的结果.三维场景中有平面，杯子，和其他物体
产生分割以后的平面和圆柱点云，查看的结果如下
（3）PCL中实现欧式聚类提取。对三维点云组成的场景进行分割
#include <pcl/ModelCoefficients.h> #include <pcl/point_types.h> #include <pcl/io/pcd_io.h> #include <pcl/filters/extract_indices.h> #include <pcl/filters/voxel_grid.h> #include <pcl/features/normal_3d.h> #include <pcl/kdtree/kdtree.h> #include <pcl/sample_consensus/method_types.h> #include <pcl/sample_consensus/model_types.h> #include <pcl/segmentation/sac_segmentation.h> #include <pcl/segmentation/extract_clusters.h> /****************************************************************************** 打开点云数据，并对点云进行滤波重采样预处理，然后采用平面分割模型对点云进行分割处理 提取出点云中所有在平面上的点集，并将其存盘 ******************************************************************************/ int main (int argc, char** argv) { // Read in the cloud data pcl::PCDReader reader; pcl::PointCloud<pcl::PointXYZ>::Ptr cloud (new pcl::PointCloud<pcl::PointXYZ>), cloud_f (new pcl::PointCloud<pcl::PointXYZ>); reader.read ("table_scene_lms400.pcd", *cloud); std::cout << "PointCloud before filtering has: " << cloud->points.size () << " data points." << std::endl; //* // Create the filtering object: downsample the dataset using a leaf size of 1cm pcl::VoxelGrid<pcl::PointXYZ> vg; pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_filtered (new pcl::PointCloud<pcl::PointXYZ>); vg.setInputCloud (cloud); vg.setLeafSize (0.01f, 0.01f, 0.01f); vg.filter (*cloud_filtered); std::cout << "PointCloud after filtering has: " << cloud_filtered->points.size () << " data points." << std::endl; //* //创建平面模型分割的对象并设置参数 pcl::SACSegmentation<pcl::PointXYZ> seg; pcl::PointIndices::Ptr inliers (new pcl::PointIndices); pcl::ModelCoefficients::Ptr coefficients (new pcl::ModelCoefficients); pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_plane (new pcl::PointCloud<pcl::PointXYZ> ()); pcl::PCDWriter writer; seg.setOptimizeCoefficients (true); seg.setModelType (pcl::SACMODEL_PLANE); //分割模型 seg.setMethodType (pcl::SAC_RANSAC); //随机参数估计方法 seg.setMaxIterations (100); //最大的迭代的次数 seg.setDistanceThreshold (0.02); //设置阀值 int i=0, nr_points = (int) cloud_filtered->points.size (); while (cloud_filtered->points.size () > 0.3 * nr_points) { // Segment the largest planar component from the remaining cloud seg.setInputCloud (cloud_filtered); seg.segment (*inliers, *coefficients); if (inliers->indices.size () == 0) { std::cout << "Could not estimate a planar model for the given dataset." << std::endl; break; } pcl::ExtractIndices<pcl::PointXYZ> extract; extract.setInputCloud (cloud_filtered); extract.setIndices (inliers); extract.setNegative (false); // Get the points associated with the planar surface extract.filter (*cloud_plane); std::cout << "PointCloud representing the planar component: " << cloud_plane->points.size () << " data points." << std::endl; // // 移去平面局内点，提取剩余点云 extract.setNegative (true); extract.filter (*cloud_f); *cloud_filtered = *cloud_f; } // Creating the KdTree object for the search method of the extraction pcl::search::KdTree<pcl::PointXYZ>::Ptr tree (new pcl::search::KdTree<pcl::PointXYZ>); tree->setInputCloud (cloud_filtered); std::vector<pcl::PointIndices> cluster_indices; pcl::EuclideanClusterExtraction<pcl::PointXYZ> ec; //欧式聚类对象 ec.setClusterTolerance (0.02); // 设置近邻搜索的搜索半径为2cm ec.setMinClusterSize (100); //设置一个聚类需要的最少的点数目为100 ec.setMaxClusterSize (25000); //设置一个聚类需要的最大点数目为25000 ec.setSearchMethod (tree); //设置点云的搜索机制 ec.setInputCloud (cloud_filtered); ec.extract (cluster_indices); //从点云中提取聚类，并将点云索引保存在cluster_indices中 //迭代访问点云索引cluster_indices,直到分割处所有聚类 int j = 0; for (std::vector<pcl::PointIndices>::const_iterator it = cluster_indices.begin (); it != cluster_indices.end (); ++it) { pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_cluster (new pcl::PointCloud<pcl::PointXYZ>); for (std::vector<int>::const_iterator pit = it->indices.begin (); pit != it->indices.end (); ++pit) cloud_cluster->points.push_back (cloud_filtered->points[*pit]); //* cloud_cluster->width = cloud_cluster->points.size (); cloud_cluster->height = 1; cloud_cluster->is_dense = true; std::cout << "PointCloud representing the Cluster: " << cloud_cluster->points.size () << " data points." << std::endl; std::stringstream ss; ss << "cloud_cluster_" << j << ".pcd"; writer.write<pcl::PointXYZ> (ss.str (), *cloud_cluster, false); //* j++; } return (0); }
运行结果：
不再一一查看可视化的结果
为了更切合实际的应用我会在这些基本的程序的基础上，进行与实际结合的实例，因为这些都是官方给的实例，我是首先学习一下，至少过一面，这样在后期结合实际应用的过程中会更加容易一点。（因为我也是一边学习，然后回头再在基础上进行更修）
同时有很多在我的微信公众号上的同学后台与我交流，有时候不能即时回复敬请谅解，（之前，就有一个不知道哪个学校的关注后就一直问我问题，告诉它基本的案例，还要我告诉他怎么实现，本人不才，我也是入门者阿，）
请扫面二维码关注
