Developer Guide

  • 2022.3
  • 10/25/2022
  • Public Content
Contents

Plane Model Segmentation

This tutorial shows how to use these optimizations inside a Docker* image. For the same functionality outside of Docker* images, see PCL Optimizations Outside of Docker* Images.
  1. Prepare the environment:
    cd <edge_insights_for_amr_path>/Edge_Insights_for_Autonomous_Mobile_Robots_<version>/AMR_containers ./run_interactive_docker.sh eiforamr-full-flavour-sdk:2022.3 root -c full_flavor mkdir one_api_segmentation && cd one_api_segmentation
  2. Create the file
    oneapi_segmentation.cpp
    :
    vim oneapi_segmentation.cpp
  3. Place the following inside the file:
    #include <pcl/oneapi/segmentation/segmentation.h> #include <pcl/io/pcd_io.h> #include <pcl/point_types.h> #include <pcl/pcl_config.h> int main (int argc, char **argv) { //Read Point Cloud pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_input (new pcl::PointCloud<pcl::PointXYZ> ()); //Load a standard PCD file from disk int result = pcl::io::loadPCDFile(argv[1], *cloud_input); if (result != 0) { pcl::console::print_info ("Load pcd file failed.\n"); return result; } //Create the oneapi_segmentation object pcl::oneapi::SACSegmentation seg; //Configure oneapi_segmentation class seg.setInputCloud(cloud_input); seg.setProbability(0.99); seg.setMaxIterations(50); seg.setDistanceThreshold(0.01); //Optional seg.setOptimizeCoefficients(true); //Set algorithm method and model type seg.setMethodType(pcl::oneapi::SAC_RANSAC); seg.setModelType (pcl::oneapi::SACMODEL_PLANE); //Out parameter declaration for getting inliers and model coefficients pcl::PointIndices::Ptr inliers (new pcl::PointIndices); double coeffs[4]={0,0,0,0}; //Getting inliers and model coefficients seg.segment(*inliers, coeffs); std::cout << "input cloud size : " << seg.getCloudSize() << std::endl; std::cout << "inliers size : " << seg.getInliersSize() << std::endl; std::cout << "model coefficients : " << coeffs[0] << ", " << coeffs[1] << ", " << coeffs[2] << ", " << coeffs[3] << std::endl; return 0; }
  4. Create a CMakeLists.txt file:
    vim CMakeLists.txt
  5. Place the following inside the file:
    cmake_minimum_required(VERSION 3.5 FATAL_ERROR) set(target oneapi_segmentation) set(CMAKE_CXX_COMPILER dpcpp) set(CMAKE_CXX_STANDARD 17) set(CMAKE_CXX_FLAGS "-Wall -Wpedantic -Wno-unknown-pragmas -Wno-pass-failed -Wno-unneeded-internal-declaration -Wno-unused-function -Wno-gnu-anonymous-struct -Wno-nested-anon-types -Wno-extra-semi -Wno-unused-local-typedef -fsycl -fsycl-unnamed-lambda -ferror-limit=1") project(${target}) find_package(PCL 1.12 REQUIRED) find_package(PCL-ONEAPI 1.12 REQUIRED) include_directories(${PCL_INCLUDE_DIRS} ${PCL-ONEAPI_INCLUDE_DIRS}) link_directories(${PCL_LIBRARY_DIRS} ${PCL-ONEAPI_LIBRARY_DIRS}) add_definitions(${PCL_DEFINITIONS} ${PCL-ONEAPI_DEFINITIONS}) add_executable (${target} oneapi_segmentation.cpp) target_link_libraries (${target} sycl pcl_oneapi_containers pcl_oneapi_segmentation ${PCL_LIBRARIES})
  6. Source the Intel® oneAPI Base Toolkit environment:
    export PATH=/home/eiforamr/workspace/lib/pcl/share/pcl-1.12:/home/eiforamr/workspace/lib/pcl/share/pcl-oneapi-1.12:$PATH source /opt/intel/oneapi/setvars.sh
  7. Build the code:
    cd /home/eiforamr/workspace/one_api_segmentation/ mkdir build && cd build cmake ../ make -j
  8. Download the test data from GitHub*:
    wget https://raw.githubusercontent.com/PointCloudLibrary/data/5c26bdd0591ba150b91858b5c9fe5e91cb39ae86/segmentation/mOSD/test/test59.pcd # if the binary is not downloaded try setting the proxies first and try again: export http_proxy="http://<http_proxy>:port" export https_proxy="http://<https_proxy>:port"
  9. Run the binary:
    ./oneapi_segmentation ./test59.pcd
Expected results example:
input cloud size : 307200 inliers size : 25332 model coefficients : -0.176599, -1.87228, -1.08408, 1

Code Explanation

Load the test data from GitHub* into a PointCloud<PointXYZ>.
//Read Point Cloud pcl::PointCloud<pcl::PointXYZ>::Ptr cloud_input (new pcl::PointCloud<pcl::PointXYZ> ());
Create the oneapi_segmentation object.
pcl::oneapi::SACSegmentation seg;
Configure the oneapi_segmentation class.
seg.setInputCloud(cloud_input); seg.setProbability(0.99); seg.setMaxIterations(50); seg.setDistanceThreshold(0.01); //Optional seg.setOptimizeCoefficients(true); //Set algorithm method and model type seg.setMethodType(pcl::oneapi::SAC_RANSAC); seg.setModelType (pcl::oneapi::SACMODEL_PLANE);
Set to true if a coefficient refinement is required.
seg.setOptimizeCoefficients(true);
Set the algorithm method and model type.
seg.setMethodType(pcl::oneapi::SAC_RANSAC); seg.setModelType (pcl::oneapi::SACMODEL_PLANE);
Declare output parameters for getting inliers and model coefficients.
pcl::PointIndices::Ptr inliers (new pcl::PointIndices); double coeffs[4]={0,0,0,0};
Get inliers and model coefficients by calling the segment() API.
seg.segment(*inliers, coeffs);
Result (output log):
std::cout << "input cloud size : " << seg.getCloudSize() << std::endl; std::cout << "inliers size : " << seg.getInliersSize() << std::endl; std::cout << "model coefficients : " << coeffs[0] << ", " << coeffs[1] << ", " << coeffs[2] << ", " << coeffs[3] << std::endl;

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.