cpp-toolbox  0.0.1
A toolbox library for C++
Loading...
Searching...
No Matches
descriptors.hpp File Reference

描述子提取算法统一导出文件 / Unified export file for descriptor extraction algorithms More...

Include dependency graph for descriptors.hpp:

Go to the source code of this file.

Namespaces

namespace  toolbox
 
namespace  toolbox::pcl
 

Functions

template<typename Signature >
std::vector< std::pair< size_t, size_t > > toolbox::pcl::match_descriptors (const std::vector< Signature > &source_descriptors, const std::vector< Signature > &target_descriptors, typename Signature::data_type max_distance)
 描述子类型及其特点 / Descriptor types and their characteristics
 
template<typename Signature >
std::vector< std::pair< size_t, size_t > > toolbox::pcl::match_descriptors_ratio_test (const std::vector< Signature > &source_descriptors, const std::vector< Signature > &target_descriptors, float ratio_threshold=0.8f)
 使用比率测试的描述子匹配 / Descriptor matching with ratio test
 
template<typename Signature >
Signature toolbox::pcl::compute_descriptor_centroid (const std::vector< Signature > &descriptors)
 计算描述子集的统计信息 / Compute statistics of descriptor set
 
template<typename Signature >
std::pair< float, float > toolbox::pcl::evaluate_descriptor_matching (const std::vector< Signature > &descriptors1, const std::vector< Signature > &descriptors2, const std::vector< std::pair< size_t, size_t > > &ground_truth_matches, typename Signature::data_type max_distance)
 描述子性能评估辅助函数 / Descriptor performance evaluation helper
 

Detailed Description

描述子提取算法统一导出文件 / Unified export file for descriptor extraction algorithms

该文件提供了所有点云描述子提取算法的统一接口。描述子是用于描述点云局部几何特征的向量, 在点云配准、物体识别、场景理解等任务中起着关键作用。 This file provides a unified interface for all point cloud descriptor extraction algorithms. Descriptors are vectors that describe local geometric features of point clouds, playing a crucial role in tasks such as point cloud registration, object recognition, and scene understanding.

using namespace toolbox::pcl;
// 加载点云并检测关键点 / Load point cloud and detect keypoints
point_cloud_t<float> cloud = load_point_cloud("object.pcd");
auto keypoints = detect_keypoints(cloud);
// 使用FPFH描述子 / Using FPFH descriptor
fpfh.set_search_radius(0.05f);
std::vector<fpfh_signature_t<float>> descriptors;
fpfh.compute(cloud, keypoints, descriptors);
// 使用描述子进行匹配 / Use descriptors for matching
auto matches = match_descriptors(descriptors, target_descriptors);
FPFH (Fast Point Feature Histogram) descriptor extractor.
Definition fpfh_extractor.hpp:89
std::size_t set_search_radius(data_type radius)
Set the search radius for neighbor search.
Definition fpfh_extractor_impl.hpp:41
描述子提取算法统一导出文件 / Unified export file for descriptor extraction algorithms
Definition base_correspondence_generator.hpp:18