其他分享
首页 > 其他分享> > PCL:SIFT特征点估计(法线)

PCL:SIFT特征点估计(法线)

作者:互联网

介绍:SIFT
将法线视为强度进行计算,代码如下:
需要四个字段的点云才能计算。

// STL
#include <iostream>

// PCL
#include <pcl/io/pcd_io.h>
#include <pcl/point_types.h>
#include <pcl/common/io.h>
#include <pcl/keypoints/sift_keypoint.h>
#include <pcl/features/normal_3d.h>
// #include <pcl/visualization/pcl_visualizer.h>

/* This example shows how to estimate the SIFT points based on the
 * Normal gradients i.e. curvature than using the Intensity gradient
 * as usually used for SIFT keypoint estimation.
 */

int
main(int, char** argv)
{
  std::string filename = argv[1];
  std::cout << "Reading " << filename << std::endl;
  pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_xyz (new pcl::PointCloud<pcl::PointXYZ>);
  if(pcl::io::loadPCDFile<pcl::PointXYZ> (filename, *cloud_xyz) == -1) // load the file
  {
    PCL_ERROR ("Couldn't read file");
    return -1;
  }
  std::cout << "points: " << cloud_xyz->points.size () <<std::endl;
  
  // Parameters for sift computation
  const float min_scale = 0.01f;
  const int n_octaves = 3;
  const int n_scales_per_octave = 4;
  const float min_contrast = 0.001f;
  
  // Estimate the normals of the cloud_xyz
  pcl::NormalEstimation<pcl::PointXYZ, pcl::PointNormal> ne;
  pcl::PointCloud<pcl::PointNormal>::Ptr cloud_normals (new pcl::PointCloud<pcl::PointNormal>);
  pcl::search::KdTree<pcl::PointXYZ>::Ptr tree_n(new pcl::search::KdTree<pcl::PointXYZ>());

  ne.setInputCloud(cloud_xyz);
  ne.setSearchMethod(tree_n);
  ne.setRadiusSearch(0.2);
  ne.compute(*cloud_normals);

  // Copy the xyz info from cloud_xyz and add it to cloud_normals as the xyz field in PointNormals estimation is zero
  for(size_t i = 0; i<cloud_normals->points.size(); ++i)
  {
    cloud_normals->points[i].x = cloud_xyz->points[i].x;
    cloud_normals->points[i].y = cloud_xyz->points[i].y;
    cloud_normals->points[i].z = cloud_xyz->points[i].z;
  }

  // Estimate the sift interest points using normals values from xyz as the Intensity variants
  pcl::SIFTKeypoint<pcl::PointNormal, pcl::PointWithScale> sift;
  pcl::PointCloud<pcl::PointWithScale> result;
  pcl::search::KdTree<pcl::PointNormal>::Ptr tree(new pcl::search::KdTree<pcl::PointNormal> ());
  sift.setSearchMethod(tree);
  sift.setScales(min_scale, n_octaves, n_scales_per_octave);
  sift.setMinimumContrast(min_contrast);
  sift.setInputCloud(cloud_normals);
  sift.compute(result);

  std::cout << "No of SIFT points in the result are " << result.points.size () << std::endl;
  return 0;
  
}

也可以自定义SIFT选择的字段,下面代码说明选择Z字段作为强度信息进行处理:

// STL
#include <iostream>

// PCL
#include <pcl/io/pcd_io.h>
#include <pcl/point_types.h>
#include <pcl/common/io.h>
#include <pcl/keypoints/sift_keypoint.h>
#include <pcl/features/normal_3d.h>
// #include <pcl/visualization/pcl_visualizer.h>

/* This examples shows how to estimate the SIFT points based on the 
 * z gradient of the 3D points than using the Intensity gradient as
 * usually used for SIFT keypoint estimation.
 */

namespace pcl
{
  template<>
    struct SIFTKeypointFieldSelector<PointXYZ>
    {
      inline float
      operator () (const PointXYZ &p) const
      {
	return p.z;
      }
    };
}

int
main(int, char** argv)
{
  std::string filename = argv[1];
  std::cout << "Reading " << filename << std::endl;
  pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_xyz (new pcl::PointCloud<pcl::PointXYZ>);
  if(pcl::io::loadPCDFile<pcl::PointXYZ> (filename, *cloud_xyz) == -1) // load the file
  {
    PCL_ERROR ("Couldn't read file");
    return -1;
  }
  std::cout << "points: " << cloud_xyz->points.size () <<std::endl;
  
  // Parameters for sift computation
  const float min_scale = 0.005f;
  const int n_octaves = 6;
  const int n_scales_per_octave = 4;
  const float min_contrast = 0.005f;
  
  // Estimate the sift interest points using z values from xyz as the Intensity variants
  pcl::SIFTKeypoint<pcl::PointXYZ, pcl::PointWithScale> sift;
  pcl::PointCloud<pcl::PointWithScale> result;
  pcl::search::KdTree<pcl::PointXYZ>::Ptr tree(new pcl::search::KdTree<pcl::PointXYZ> ());
  sift.setSearchMethod(tree);
  sift.setScales(min_scale, n_octaves, n_scales_per_octave);
  sift.setMinimumContrast(min_contrast);
  sift.setInputCloud(cloud_xyz);
  sift.compute(result);

  std::cout << "No of SIFT points in the result are " << result.points.size () << std::endl;
  return 0;
  
}

来源:PCL官方示例

标签:PCL,xyz,sift,SIFT,点估计,pcl,include,cloud,points
来源: https://blog.csdn.net/com1098247427/article/details/120688904