PCL learning: key points -SIFT

Class SIFTKeypoint after the two-dimensional image to SIFT algorithm implemented SIFT transplanted adjusted operator 3D space. Input point cloud with the XYZ coordinate values and intensity, the output for the SIFT key points in the point cloud.

class pcl :: SIFTKeypoint <PointlnT, PointOutT >

class SIFTKeypoint Key Function Description:

void setScales (float min_scale, int nr_octaves, int nr_scales_per_octave)

And scale parameters, min_scale standard deviation of the voxel cloud point scale when setting the search space, the minimum size of the point cloud corresponding to voxels of the voxel grid, nr_octaves key is detected number of voxels spatial scale, nr_scales_ per _ octave scale Gaussian required space is calculated at each voxel scale parameter space.

void setMinimumContrast (float min contrast)

The lower limit should be set the contrast of candidate keypoints.

void compute (PointCloudOut&.output)

The key point is calculated and stored in the output.

#include <iostream>
#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>
#include <pcl/console/time.h>
using namespace std;

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

int
main(int argc, char *argv[])
{

  pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_xyz (new pcl::PointCloud<pcl::PointXYZ>);
  pcl::io::loadPCDFile (argv[1], *cloud_xyz);

  const float min_scale = stof(argv[2]);             //设置尺度空间中最小尺度的标准偏差          
  const int n_octaves = stof(argv[3]);               //设置高斯金字塔组（octave）的数目            
  const int n_scales_per_octave = stof(argv[4]);     //设置每组（octave）计算的尺度  
  const float min_contrast = stof(argv[5]);          //设置限制关键点检测的阈值       
 
  pcl::SIFTKeypoint<pcl::PointXYZ, pcl::PointWithScale> sift;//创建sift关键点检测对象
  pcl::PointCloud<pcl::PointWithScale> result;
  sift.setInputCloud(cloud_xyz);//设置输入点云
  pcl::search::KdTree<pcl::PointXYZ>::Ptr tree(new pcl::search::KdTree<pcl::PointXYZ> ());
  sift.setSearchMethod(tree);//创建一个空的kd树对象tree，并把它传递给sift检测对象
  sift.setScales(min_scale, n_octaves, n_scales_per_octave);//指定搜索关键点的尺度范围
  sift.setMinimumContrast(min_contrast);//设置限制关键点检测的阈值
  sift.compute(result);//执行sift关键点检测，保存结果在result

  pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_temp (new pcl::PointCloud<pcl::PointXYZ>);
  copyPointCloud(result, *cloud_temp);//将点类型pcl::PointWithScale的数据转换为点类型pcl::PointXYZ的数据
 
  //可视化输入点云和关键点
  pcl::visualization::PCLVisualizer viewer("Sift keypoint");
  viewer.setBackgroundColor( 255, 255, 255 );
  viewer.addPointCloud(cloud_xyz, "cloud");
  viewer.setPointCloudRenderingProperties(pcl::visualization::PCL_VISUALIZER_COLOR,0,0,0,"cloud");
  viewer.addPointCloud(cloud_temp, "keypoints");
  viewer.setPointCloudRenderingProperties (pcl::visualization::PCL_VISUALIZER_POINT_SIZE, 9, "keypoints");
  viewer.setPointCloudRenderingProperties(pcl::visualization::PCL_VISUALIZER_COLOR,0,0,255,"keypoints");

  while(!viewer.wasStopped ())
  {
    viewer.spinOnce ();
  }
  return 0;
  
}

Excuting an order:

.\Siftdetect.exe ..\..\source\pig.pcd 0.01 6 4 0.01

As shown, the key point is detected (blue dots);

PCL learning: key points -SIFT

Guess you like