PCL-04-RANSAC拟合平面和球、表面法线估计和求解、PFH点特征直方图

1. 随机采样一致性 RANSAC,Random Sample Consensus拟合平面和球面

rand()    //的取值范围是[0 RAND_MAX]

// inliers为结果索引
// created RandomSampleConsensus object and compute the appropriated model
// 圆形
pcl::SampleConsensusModelSphere<pcl::PointXYZ>::Ptr
        model_s(new pcl::SampleConsensusModelSphere<pcl::PointXYZ>(cloud));
pcl::RandomSampleConsensus<pcl::PointXYZ> ransac(model_s);
ransac.setDistanceThreshold(.01);
ransac.computeModel();
ransac.getInliers(inliers);
// 平面
pcl::SampleConsensusModelPlane<pcl::PointXYZ>::Ptr
        model_p(new pcl::SampleConsensusModelPlane<pcl::PointXYZ>(cloud));
pcl::RandomSampleConsensus<pcl::PointXYZ> ransac(model_p);
ransac.setDistanceThreshold(.01);
ransac.computeModel();
ransac.getInliers(inliers);

2. 估计点云表面法线

// estimate normals
pcl::PointCloud<pcl::Normal>::Ptr normals(new pcl::PointCloud<pcl::Normal>);

// Object for normal estimation.
pcl::NormalEstimation<pcl::PointXYZ, pcl::Normal> normalEstimation;
//normalEstimation.setIndices()
normalEstimation.setInputCloud(cloud);
// For every point, use all neighbors in a radius of 3cm.
normalEstimation.setRadiusSearch(0.03);
// A kd-tree is a data structure that makes searches efficient. More about it later.
// The normal estimation object will use it to find nearest neighbors.
pcl::search::KdTree<pcl::PointXYZ>::Ptr kdtree(new pcl::search::KdTree<pcl::PointXYZ>);
normalEstimation.setSearchMethod(kdtree);
// Calculate the normals.
normalEstimation.compute(*normals);

// visualize normals
pcl::visualization::PCLVisualizer viewer("PCL Viewer");
viewer.setBackgroundColor(0.0, 0.0, 0.5);
viewer.addPointCloud<pcl::PointXYZ>(cloud, "cloud");
// 参数int level=2 表示每n个点绘制一个法向量
// 参数float scale=0.01 表示法向量长度缩放为0.01倍
viewer.addPointCloudNormals<pcl::PointXYZ, pcl::Normal>(cloud, normals, 2, 0.01, "normals");

3. 积分图估算点云法线

// 创建一个用于法线估计的对象并计算法线
pcl::IntegralImageNormalEstimation<pcl::PointXYZ, pcl::Normal> ne;
// 有以下可选的估算方式：
/**
enum NormalEstimationMethod
{
  COVARIANCE_MATRIX,
  AVERAGE_3D_GRADIENT,
  AVERAGE_DEPTH_CHANGE
};
 COVARIANCE_MATRIX模式创建9个积分图像，以根据其局部邻域的协方差矩阵为特定点计算法线。
 AVERAGE_3D_GRADIENT模式创建6个积分图像以计算水平和垂直3D渐变的平滑版本，并使用这两个渐变之间的叉积计算法线。
 AVERAGE_DEPTH_CHANGE模式仅创建单个积分图像，并根据平均深度变化计算法线。
 */
ne.setNormalEstimationMethod(ne.AVERAGE_3D_GRADIENT);
ne.setMaxDepthChangeFactor(0.02f);
ne.setNormalSmoothingSize(10.0f);
ne.setInputCloud(cloud);
ne.compute(*normals);

4. PFH，点特征直方图，针对计算出的法向量进行直方图统计。

// estimate normals 
pcl::PointCloud<pcl::Normal>::Ptr normals(new pcl::PointCloud<pcl::Normal>);
// Object for normal estimation.
pcl::NormalEstimation<pcl::PointXYZ, pcl::Normal> normalEstimation;
//normalEstimation.setIndices()
normalEstimation.setInputCloud(cloud);
// For every point, use all neighbors in a radius of 3cm.
normalEstimation.setRadiusSearch(0.03);

// A kd-tree is a data structure that makes searches efficient. More about it later.
// The normal estimation object will use it to find nearest neighbors.
pcl::search::KdTree<pcl::PointXYZ>::Ptr kdtree(new pcl::search::KdTree<pcl::PointXYZ>);
normalEstimation.setSearchMethod(kdtree);
// Calculate the normals.
normalEstimation.compute(*normals);

// Create the PFH estimation class, and pass the input dataset+normals to it ------计算PFH直方图
pcl::PFHEstimation<pcl::PointXYZ, pcl::Normal, pcl::PFHSignature125> pfh;
pfh.setInputCloud(cloud);
pfh.setInputNormals(normals);
// alternatively, if cloud is of tpe PointNormal, do pfh.setInputNormals (cloud);

// Create an empty kdtree representation, and pass it to the PFH estimation object.
// Its content will be filled inside the object, based on the given input dataset (as no other search surface is given).
pcl::search::KdTree<pcl::PointXYZ>::Ptr tree(new pcl::search::KdTree<pcl::PointXYZ>());
//pcl::KdTreeFLANN<pcl::PointXYZ>::Ptr tree (new pcl::KdTreeFLANN<pcl::PointXYZ> ()); -- older call for PCL 1.5-
pfh.setSearchMethod(tree);

// Output datasets
pcl::PointCloud<pcl::PFHSignature125>::Ptr pfhs(new pcl::PointCloud<pcl::PFHSignature125>());

// Use all neighbors in a sphere of radius 5cm
// 使用一个半径为5厘米的球体，作为搜索邻域
// IMPORTANT: the radius used here has to be larger than the radius used to estimate the surface normals!!!
// 重点： 半径必须要比用于估算法向量的邻域半径要大
pfh.setRadiusSearch(0.08);

// Compute the features
pfh.compute(*pfhs);