移动网站开发 书,网络公司网站asp,php开发网站优势,新闻发布会视频后续使用了fpfh特征作为训练数据#xff0c;遇到了一些困难 首先是flann冲突#xff0c;这个将opcv中的flann都改成了flann2就可以运行 后面在将得到的33特征值进行训练的时候一直内存超限#xff0c;传输的不太好#xff0c;到现在还是不行#xff0c;改了三天还是没有改…后续使用了fpfh特征作为训练数据遇到了一些困难 首先是flann冲突这个将opcv中的flann都改成了flann2就可以运行 后面在将得到的33特征值进行训练的时候一直内存超限传输的不太好到现在还是不行改了三天还是没有改好先放这里吧等后续有时间进行修改我感觉是传输的问题。
#pragma warning(disable:4996)
#include iostream
#include pcl/io/pcd_io.h
#include pcl/point_types.h
#include pcl/visualization/pcl_visualizer.h
//点云显示
#include pcl/visualization/cloud_viewer.h
#include pcl/visualization/point_cloud_color_handlers.h
//数据组织
#include boost/thread/thread.hpp
#include boost/thread/thread_time.hpp
#includeflann/flann.h
#include thread
#include pcl/search/kdtree.h
//
#include omp.h
//补充点云特征
#include pcl/features/normal_3d.h
#include pcl/features/normal_3d_omp.h
#include pcl/features/shot_omp.h
#include pcl/features/shot.h
#include pcl/features/fpfh_omp.h
#include pcl/features/pfh.h
#include pcl/features/normal_3d.h#include opencv2/opencv.hppint main() {// 读取初始点云pcl::PointCloudpcl::PointXYZ::Ptr cloud(new pcl::PointCloudpcl::PointXYZ);pcl::PCDReader reader;reader.read(svmtest.pcd, *cloud);cout 初始点云读取完成 endl;// 读取带标签的点云pcl::PointCloudpcl::PointXYZL::Ptr labeledCloud(new pcl::PointCloudpcl::PointXYZL);reader.read(svmlearn_xyzl.pcd, *labeledCloud);cout 标签点云读取完成 endl;// 计算法线pcl::PointCloudpcl::Normal::Ptr normals(new pcl::PointCloudpcl::Normal);pcl::NormalEstimationpcl::PointXYZL, pcl::Normal normalEstimation;normalEstimation.setInputCloud(labeledCloud);pcl::search::KdTreepcl::PointXYZL::Ptr kdtree(new pcl::search::KdTreepcl::PointXYZL);normalEstimation.setSearchMethod(kdtree);normalEstimation.setKSearch(20); // 设置法线估计时近邻点的数量normalEstimation.compute(*normals); cout 发线计算完成 endl;将法线和原始点云拼接起来//pcl::PointCloudpcl::PointNormal::Ptr cloudWithNormals(new pcl::PointCloudpcl::PointNormal);//pcl::concatenateFields(*cloud, *normals, *cloudWithNormals);// 将法线和原始点云拼接起来//pcl::PointCloudpcl::PointNormal::Ptr cloudWithNormals(new pcl::PointCloudpcl::PointNormal);pcl::PointCloudpcl::PointXYZLNormal::Ptr cloudWithNormals(new pcl::PointCloudpcl::PointXYZLNormal);cloudWithNormals-resize(cloud-size());for (size_t i 0; i cloud-size(); i) {cloudWithNormals-points[i].x cloud-points[i].x;cloudWithNormals-points[i].y cloud-points[i].y;cloudWithNormals-points[i].z cloud-points[i].z;cloudWithNormals-points[i].normal_x normals-points[i].normal_x;cloudWithNormals-points[i].normal_y normals-points[i].normal_y;cloudWithNormals-points[i].normal_z normals-points[i].normal_z;}cout cloudWithNormals的点云数量为 cloudWithNormals-size() endl;cout 法线和原始点云合并完成 endl;// 读取法线和曲率特征// pcl::PointCloudpcl::FPFHSignature33::Ptr features(new pcl::PointCloudpcl::FPFHSignature33);// 计算带标签点云的FPFH特征pcl::FPFHEstimationOMPpcl::PointXYZL, pcl::Normal, pcl::FPFHSignature33 fpfh_src;fpfh_src.setInputCloud(labeledCloud);fpfh_src.setInputNormals(normals);fpfh_src.setNumberOfThreads(10);pcl::search::KdTreepcl::PointXYZL::Ptr kdtree2(new pcl::search::KdTreepcl::PointXYZL);fpfh_src.setSearchMethod(kdtree2);cout 开始计算点云特征 endl;pcl::PointCloudpcl::FPFHSignature33::Ptr features(new pcl::PointCloudpcl::FPFHSignature33());fpfh_src.setKSearch(20);fpfh_src.compute(*features);// 开始计算前上锁omp_lock_t lock;omp_init_lock(lock);// 使用 OpenMP 设置锁
#pragma omp parallel{
#pragma omp single{
#pragma omp task{fpfh_src.compute(*features);}}}// 计算完成后解锁omp_destroy_lock(lock);cout 读取法线和曲率特征完成 endl;// 准备训练数据和标签cv::Mat trainingData(labeledCloud-size(), 33, CV_32FC1); // 注意特征的维度cv::Mat labels(labeledCloud-size(), 1, CV_32SC1);std::cout labeledCloud size: labeledCloud-size() std::endl;std::cout features size: features-size() std::endl;for (size_t i 0; i labeledCloud-size(); i){// 使用法线和曲率特征for (int j 0; j 33; j){if (i features-size()){ // 添加索引范围检查trainingData.atfloat(i, j) features-points[i].histogram[j];}else {std::cerr Index out of range for features at i i and j j std::endl;}}// 根据点的标签设置标签数据if (i labeledCloud-size()) { // 添加索引范围检查labels.atint(i, 0) labeledCloud-points[i].label;}else {std::cerr Index out of range for labeledCloud at i i std::endl;}}cout 根据点的标签设置标签数据完成 endl;// 创建并训练SVM分类器cv::Ptrcv::ml::SVM svm cv::ml::SVM::create();svm-setType(cv::ml::SVM::C_SVC);svm-setKernel(cv::ml::SVM::RBF);svm-setC(10);svm-setGamma(0.001);svm-train(trainingData, cv::ml::ROW_SAMPLE, labels);cout 创建并训练SVM分类器完成正在开始对点云进行分类 endl;// 对初始点云进行分类//cv::Mat testData(cloud-size(), 3, CV_32FC1);//for (size_t i 0; i cloud-size(); i) //{// testData.atfloat(i, 0) cloud-points[i].x;// testData.atfloat(i, 1) cloud-points[i].y;// testData.atfloat(i, 2) cloud-points[i].z;//}cv::Mat testData(cloud-size(), 33, CV_32FC1);for (size_t i 0; i cloud-size(); i){for (int j 0; j 33; j) {testData.atfloat(i, j) features-points[i].histogram[j];}}cv::Mat predictedLabels;/* svm-predict(testData, predictedLabels);*/try {svm-predict(testData, predictedLabels);}catch (cv::Exception e) {std::cerr OpenCV Exception: e.what() std::endl;}cout 正在将分类结果添加到点云中 endl;// 将分类结果添加到点云中pcl::PointCloudpcl::PointXYZL::Ptr classifiedCloud(new pcl::PointCloudpcl::PointXYZL);classifiedCloud-resize(cloud-size());for (size_t i 0; i cloud-size(); i) {classifiedCloud-points[i].x cloud-points[i].x;classifiedCloud-points[i].y cloud-points[i].y;classifiedCloud-points[i].z cloud-points[i].z;// 修正标签值假设标签是 0 或 1classifiedCloud-points[i].label static_castint(predictedLabels.atfloat(i, 0)) 1;}pcl::PCDWriter writer;writer.write(lable.pcd, *classifiedCloud);cout lable.pcd已完成储存请查看 endl;//----------------------------根据分类标签可视化-----------------------------boost::shared_ptrpcl::visualization::PCLVisualizer viewer(new pcl::visualization::PCLVisualizer(3D Viewer));pcl::visualization::PointCloudColorHandlerGenericFieldpcl::PointXYZLfildColor(classifiedCloud, label);viewer-setBackgroundColor(0, 0, 0);viewer-setWindowName(点云按分类标签显示);viewer-addText(Point clouds are shown by label, 50, 50, 0, 1, 0, v1_text);viewer-addPointCloudpcl::PointXYZL(classifiedCloud, fildColor, sample cloud);viewer-setPointCloudRenderingProperties(pcl::visualization::PCL_VISUALIZER_POINT_SIZE, 1, sample cloud);while (!viewer-wasStopped()){viewer-spinOnce(100);boost::this_thread::sleep(boost::posix_time::microseconds(100000));}return 0;
}
