点云随笔（四）点云统计误差计算

最新推荐文章于 2024-08-14 11:22:43 发布

North ship

最新推荐文章于 2024-08-14 11:22:43 发布

阅读量338

点赞数 4

文章标签：算法

本文链接：https://blog.csdn.net/qq_45861949/article/details/140078820

版权

基于机器学习预测点云数据与手动描绘的真实点云数据之间存在点重合以及不重合，本段代码主要是计算两者之间重合点数。

#include <algorithm>  
#include <string>
#include <cstdlib>
#include <cstdio>
#include <map>
#include <math.h>
#include <pcl/common/common.h>
#include <pcl/common/time.h>
#include <pcl/console/parse.h>
#include <pcl/io/pcd_io.h>
#include <pcl/filters/normal_space.h>
#include <pcl/kdtree/kdtree_flann.h>
#include <pcl/point_cloud.h>
#include <pcl/point_types.h>
#include <pcl/io/pcd_io.h>
#include <pcl/filters/extract_indices.h>
#include <pcl/filters/voxel_grid.h>
#include <pcl/features/normal_3d.h>
#include <pcl/kdtree/kdtree.h>
#include <pcl/segmentation/sac_segmentation.h>
#include <pcl/segmentation/extract_clusters.h>


using namespace std;

typedef pcl::PointXYZRGB PointT;
typedef pcl::PointCloud<PointT> PointCloudT;

int main_tongjiwucha() {
	
	
	pcl::PCDReader reader;
	pcl::PointCloud<pcl::PointXYZRGB>::Ptr cloud(new pcl::PointCloud<pcl::PointXYZRGB>), cloud2(new pcl::PointCloud<pcl::PointXYZRGB>), cloud3(new pcl::PointCloud<pcl::PointXYZRGB>);

	reader.read("D:\\learning\\ROADminus.pcd", *cloud);
	reader.read("D:\\learning\\road1.pcd", *cloud2);
	std::cout << "The cloud size is: " << cloud2->points.size() << " data points. " << "手描点云" << std::endl;
    std::cout << "The cloud size is: " << cloud->points.size() << " data points." <<" 预测点云" << std::endl;
	int p{ 0 };
	for (int i{ 0 }; i < cloud2->size(); i++)
	{
		bool pd{ TRUE };
		for (int j{ 0 }; j < cloud->size(); j++) 
		{
			double xx = cloud->points[j].x - cloud2->points[i].x, yy = cloud->points[j].y - cloud2->points[i].y, zz = cloud->points[j].z - cloud2->points[i].z;
			if ((xx < pow(10, -5)) && (yy < pow(10, -5)) && (zz < pow(10, -5)))
				pd = FALSE;
		}
		if (pd == FALSE) {
			p += 1;
			cloud3->push_back(cloud2->points[i]);
		}
			
	}
	cloud3->width = cloud3->size();
	cloud3->height = 1;
	cloud3->points.resize(cloud3->width * cloud3->height);
	pcl::PCDWriter writer;
	stringstream ss;
	ss << "D:\\learning\\after_fit_cluster"<<cloud3->size()<< ".pcd";
	pcl::io::savePCDFileASCII(ss.str(), *cloud3);
	cout << p << endl;
	return (0);
}