pcl 学习离群点删除

最新推荐文章于 2025-06-21 08:41:23 发布

阿廖沙JackWant

最新推荐文章于 2025-06-21 08:41:23 发布

阅读量7.5k

点赞数 1

CC 4.0 BY-SA版权

分类专栏：学习教程文章标签： pcl点云库

本文链接：https://blog.youkuaiyun.com/u013351270/article/details/68941821

学习教程专栏收录该内容

13 篇文章

订阅专栏

官方教程 http://pointclouds.org/documentation/tutorials/statistical_outlier.php#statistical-outlier-re

离群点是按照K个近邻点的标准方差*Threshold 来定义的，假如K=50,*Threshold =1. 那么某一个点是否是离群点。是这么确定的。首先求出这个点附近的50个点之间距离的标准方差dev，然后计算这个点到这些点的距离d，如果d>dev*threshold 那么这个点就是离群点。
附上源代码。在官方教程上加了一点点注释，并且把点云显示了一下，红色的是离群点。点云文件青岛上面的链接下载

#include <iostream>
#include <pcl/io/pcd_io.h>
#include <pcl/point_types.h>
#include <pcl/filters/statistical_outlier_removal.h>
#include <pcl/visualization/cloud_viewer.h>
#include <pcl/visualization/pcl_visualizer.h>
int main(int argc, char** argv)
{
    pcl::PointCloud<pcl::PointXYZ>::Ptr cloud(new pcl::PointCloud<pcl::PointXYZ>);
    pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_inliner(new pcl::PointCloud<pcl::PointXYZ>);
    pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_outliner(new pcl::PointCloud<pcl::PointXYZ>);
    // Fill in the cloud data
    pcl::PCDReader reader;
    // Replace the path below with the path where you saved your file
    reader.read<pcl::PointXYZ>("table_scene_lms400.pcd", *cloud);

    std::cerr << "Cloud before filtering: " << std::endl;
    std::cerr << *cloud << std::endl;

    // Create the filtering object
    pcl::StatisticalOutlierRemoval<pcl::PointXYZ> sor;
    sor.setInputCloud(cloud);
    sor.setMeanK(50);//50个临近点
    sor.setStddevMulThresh(1.0);//距离大于1倍标准方差

    sor.filter(*cloud_inliner);

    std::cerr << "Cloud after filtering: " << std::endl;
    std::cerr << *cloud_inliner << std::endl;

    pcl::PCDWriter writer;
    writer.write<pcl::PointXYZ>("table_scene_lms400_inliers.pcd", *cloud_inliner, false);

    sor.setNegative(true);
    sor.filter(*cloud_outliner);
    writer.write<pcl::PointXYZ>("table_scene_lms400_outliers.pcd", *cloud_outliner, false);
    pcl::visualization::PCLVisualizer viewer("demo");
    int v1(0);
    int v2(1);
    viewer.createViewPort(0.0, 0.0, 1.0, 1.0, v1);
    // The color we will be using
    float bckgr_gray_level = 0.0;  // Black
    float txt_gray_lvl = 1.0 - bckgr_gray_level;

    // Original point cloud is white
    pcl::visualization::PointCloudColorHandlerCustom<pcl::PointXYZ> cloud_in_color_h(cloud, (int)255 * txt_gray_lvl, (int)255 * txt_gray_lvl, (int)255 * txt_gray_lvl);
    viewer.addPointCloud(cloud, cloud_in_color_h, "cloud_in_v1", v1);       //viewer.addPointCloud(cloud_in, cloud_in_color_h, "cloud_in_v2", v2);
    pcl::visualization::PointCloudColorHandlerCustom<pcl::PointXYZ> cloud_out_green(cloud_inliner, 20, 180, 20);
    viewer.addPointCloud(cloud_inliner, cloud_out_green, "cloud_out", v1);
    pcl::visualization::PointCloudColorHandlerCustom<pcl::PointXYZ> Final_red(cloud_outliner, 180, 10, 20);
    viewer.addPointCloud(cloud_outliner, Final_red, "cloud_Final", v1);
        viewer.setBackgroundColor(bckgr_gray_level, bckgr_gray_level, bckgr_gray_level, v1);
    //  viewer.setBackgroundColor(bckgr_gray_level, bckgr_gray_level, bckgr_gray_level, v2);     
    viewer.setSize(1280, 1024);  // Visualiser window size
    //viewer.showCloud(cloud_out);
    while (!viewer.wasStopped())
    {
        viewer.spinOnce();
    }

    return (0);
}