基于pcl库以已知点x1y1z1为起点进行欧式聚类的c++算法

以下是基于pcl库的C++算法，用于以已知点（x1, y1, z1）为起点进行欧式聚类。

#include <iostream>
#include <pcl/io/pcd_io.h>
#include <pcl/point_types.h>
#include <pcl/segmentation/extract_clusters.h>
#include <pcl/filters/extract_indices.h>
#include <pcl/kdtree/kdtree.h>

int main()
{
    // 读取点云数据
    pcl::PointCloud<pcl::PointXYZ>::Ptr cloud(new pcl::PointCloud<pcl::PointXYZ>);
    if (pcl::io::loadPCDFile<pcl::PointXYZ>("input_cloud.pcd", *cloud) == -1)
    {
        PCL_ERROR("Couldn't read file input_cloud.pcd\n");
        return -1;
    }

    // 创建kdtree对象
    pcl::search::KdTree<pcl::PointXYZ>::Ptr kdtree(new pcl::search::KdTree<pcl::PointXYZ>);
    kdtree->setInputCloud(cloud);

    // 定义聚类对象
    pcl::EuclideanClusterExtraction<pcl::PointXYZ> ec;
    ec.setClusterTolerance(0.2); // 设置聚类的欧式距离阈值
    ec.setMinClusterSize(10);    // 设置聚类的最小点数
    ec.setMaxClusterSize(25000); // 设置聚类的最大点数
    ec.setSearchMethod(kdtree);
    ec.setInputCloud(cloud);

    // 设置已知点（x1, y1, z1）为种子点
    pcl::PointXYZ seed_point;
    seed_point.x = x1;
    seed_point.y = y1;
    seed_point.z = z1;
    std::vector<int> seed_indices;
    std::vector<float> seed_distances;
    kdtree->nearestKSearch(seed_point, 1, seed_indices, seed_distances);

    // 提取聚类
    std::vector<pcl::PointIndices> cluster_indices;
    ec.setIndices(seed_indices);
    ec.extract(cluster_indices);

    // 输出聚类结果
    int cluster_id = 0;
    for (const auto &indices : cluster_indices)
    {
        std::cout << "Cluster " << cluster_id << ": ";
        for (const auto &index : indices.indices)
        {
            std::cout << "(" << cloud->points[index].x << ", "
                      << cloud->points[index].y << ", "
                      << cloud->points[index].z << ") ";
        }
        std::cout << std::endl;
        cluster_id++;
    }

    return 0;
}

请注意，代码中的x1，y1和z1是已知点的坐标，你需要将其替换为实际的值。此外，你还需要将input_cloud.pcd替换为你自己的点云文件路径。