八叉树学习（Being_young部分博客参考加上书的内容）

1.octree是一种用于管理稀疏3D数据的树形数据结构，每个内部节点都正好有八个子节点，介绍如何用octree在点云数据中进行空间划分及近邻搜索，实现“体素内近邻搜索（Neighbors within VOxel Search）”,"K近邻搜索（K Nearest Neighbor Search）","半径内近邻搜索"（Neighbors within Radius Search）K近邻搜索（K Nearest Neighbor Search）。

所谓K近邻算法，即是给定一个训练数据集，对新的输入实例，在训练数据集中找到与该实例最邻近的K个实例（也就是上面所说的K个邻居）， 这K个实例的多数属于某个类，就把该输入实例分类到这个类中。网上可以查找KNN的算法，这里不介绍了

2.

#include <pcl/point_cloud.h>
#include <pcl/octree/octree.h>
#include <iostream>
#include <vector>
#include <ctime>

int
main (int argc, char**argv)
{
srand ((unsigned int) time (NULL));
pcl::PointCloud<pcl::PointXYZ>::Ptr cloud(new pcl::PointCloud<pcl::PointXYZ>);
// 创建点云数据
cloud->width =1000;
cloud->height =1;
cloud->points.resize (cloud->width * cloud->height);
for (size_t i=0; i< cloud->points.size (); ++i)
  {
cloud->points[i].x =1024.0f* rand () / (RAND_MAX +1.0f);
cloud->points[i].y =1024.0f* rand () / (RAND_MAX +1.0f);
cloud->points[i].z =1024.0f* rand () / (RAND_MAX +1.0f);
  }
float resolution =128.0f;
pcl::octree::OctreePointCloudSearch<pcl::PointXYZ> octree(resolution);
octree.setInputCloud (cloud);
octree.addPointsFromInputCloud ();
pcl::PointXYZ searchPoint;
searchPoint.x=1024.0f* rand () / (RAND_MAX +1.0f);
searchPoint.y=1024.0f* rand () / (RAND_MAX +1.0f);
searchPoint.z=1024.0f* rand () / (RAND_MAX +1.0f);
// 体素内近邻搜索
std::vector<int>pointIdxVec;
if (octree.voxelSearch (searchPoint, pointIdxVec))
  {
std::cout<<"Neighbors within voxel search at ("<<searchPoint.x
<<" "<<searchPoint.y
<<" "<<searchPoint.z<<")"
<<std::endl;
for (size_t i=0; i<pointIdxVec.size (); ++i)
std::cout<<"    "<< cloud->points[pointIdxVec[i]].x 
<<" "<< cloud->points[pointIdxVec[i]].y 
<<" "<< cloud->points[pointIdxVec[i]].z <<std::endl;
  }
//K近邻搜索
int K =10;
std::vector<int>pointIdxNKNSearch;
std::vector<float>pointNKNSquaredDistance;
std::cout<<"K nearest neighbor search at ("<<searchPoint.x
<<" "<<searchPoint.y
<<" "<<searchPoint.z
<<") with K="<< K <<std::endl;
if (octree.nearestKSearch (searchPoint, K, pointIdxNKNSearch, pointNKNSquaredDistance) >0)
  {
for (size_t i=0; i<pointIdxNKNSearch.size (); ++i)
std::cout<<"    "<<   cloud->points[ pointIdxNKNSearch[i] ].x 
<<" "<< cloud->points[pointIdxNKNSearch[i] ].y 
<<" "<< cloud->points[pointIdxNKNSearch[i] ].z 
<<" (squared distance: "<<pointNKNSquaredDistance[i] <<")"<<std::endl;
  }
//半径内近邻搜索
std::vector<int>pointIdxRadiusSearch;
std::vector<float>pointRadiusSquaredDistance;
float radius =256.0f* rand () / (RAND_MAX +1.0f);
std::cout<<"Neighbors within radius search at ("<<searchPoint.x
<<" "<<searchPoint.y
<<" "<<searchPoint.z
<<") with radius="<< radius <<std::endl;
if (octree.radiusSearch (searchPoint, radius, pointIdxRadiusSearch, pointRadiusSquaredDistance) >0)
  {
for (size_t i=0; i<pointIdxRadiusSearch.size (); ++i)
std::cout<<"    "<<   cloud->points[ pointIdxRadiusSearch[i] ].x 
<<" "<< cloud->points[pointIdxRadiusSearch[i] ].y 
<<" "<< cloud->points[pointIdxRadiusSearch[i] ].z 
<<" (squared distance: "<<pointRadiusSquaredDistance[i] <<")"<<std::endl;
  }
}

1.float resolution =128.0f;（大概是建立一个变量）

2.pcl::octree::OctreePointCloudSearch<pcl::PointXYZ> octree(resolution);（实现基于八叉树的点云近邻高效搜索）//初始化octree  学习一下如何初始化一个量

在书上是OctreePointCloudSearch（）主要是两个参数 一个给定点 ，然后通过点确定它所在的体素（什么是体素）最后返回体素中所有点的索引 返回 给第二个参数。

3.octree.setInputCloud (cloud);类似kd

4.octree.addPointsFromInputCloud (); 书上是显示调用点云到八叉树管理结构中。

5.octree.voxelSearch (searchPoint, pointIdxVec)主要是两个参数 一个给定点 ，然后通过点确定它所在的体素（什么是体素）最后返回体素中所有点的索引 返回 给第二个参数。多用于体素搜索

K近邻搜索：

1.octree.nearestKSearch (searchPoint, K, pointIdxNKNSearch, pointNKNSquaredDistance)类似kdtree

 

 

最后看一下结果吧哈哈哈

nice!!!