Kd树按空间划分生成叶子节点，各个叶子节点里存放点数据，其可以按半径搜索或邻区搜索。PCL中的Kd tree的基础数据结构使用了FLANN以便可以快速的进行邻区搜索。FLANN is a library for performing fast approximate nearest neighbor searches in high dimensional spaces。下面是一个最基本的例子，只寻找一个最近点：
#include <pcl/point_cloud.h> #include <pcl/kdtree/kdtree_flann.h>#include <iostream> #include <vector> #include <ctime>int main (int argc, char** argv) {srand (time (NULL)); //seeds rand() with the system time time_t begin,end;begin = clock(); //开始计时//-------------------------------------------------------------------------------pcl::PointCloud<pcl::PointXYZ>::Ptr cloud (new pcl::PointCloud<pcl::PointXYZ>);// Generate pointcloud datacloud->width = 400000;cloud->height = 1;cloud->points.resize (cloud->width * cloud->height);// fills a PointCloud with random datafor (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);}// creates kdtree objectpcl::KdTreeFLANN<pcl::PointXYZ> kdtree;// sets our randomly created cloud as the input kdtree.setInputCloud (cloud);//create a “searchPoint” which is assigned random coordinates 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);// K nearest neighbor searchint K = 1;std::vector<int> pointIdxNKNSearch(K);std::vector<float> pointNKNSquaredDistance(K);std::cout << "K nearest neighbor search at (" << searchPoint.x << " " << searchPoint.y << " " << searchPoint.z<< ") with K=" << K << std::endl;/***********************************************************************************************template<typename PointT> virtual int pcl::KdTree< PointT >::nearestKSearch ( const PointT & p_q, int k, std::vector< int > & k_indices, std::vector< float > & k_sqr_distances ) const [pure virtual] Search for k-nearest neighbors for the given query point. Parameters:[in] the given query point [in] k the number of neighbors to search for [out] the resultant indices of the neighboring points[out] the resultant squared distances to the neighboring pointsReturns:number of neighbors found ********************************************************************************************/if ( kdtree.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;}//--------------------------------------------------------------------------------------------end = clock(); //结束计时double Times = double(end - begin) / CLOCKS_PER_SEC; //将clock()函数的结果转化为以秒为单位的量 std::cout<<"time: "<<Times<<"s"<<std::endl;return 0; }
生成四十万个随机点，release版本下测试0.3s左右找到最近点，这比之前自己写的Kd树不知快到哪里去了。当然自己写只是为了更好的理解其中的原理，真要用的时候还得靠别人的轮子...
参考：
How to use a KdTree to search
Module kdtree