关键点也称为兴趣点,它是 2D 图像或 3D 点云或曲面模型上,可以通过检测标准来获取的具有稳定性、区别性的点集。从技术上来说,关键点的数量比原始点云或图像的数据量少很多,其与局部特征描述子结合组成关键点描述子。常用来构成原始数据的紧凑表示 ,具有代表性与描述性,从而加快后续识别、追踪等对数据的处理速度 。
固而,关键点提取就成为 2D 与 3D 信息处理中不可或缺的关键技术 。
关键点概念及算法¶
NARF(Normal Aligned Radial Feature)关键点是为了从深度图像中识别物体而提出的,关键点探测的重要一步是减少特征提取时的搜索空间,把重点放在重要的结构上,对 NARF 关键点提取过程有以下要求:
- 提取的过程必须考虑边缘以及物体表面变化信息
- 即使换了不同的视角,关键点的位置必须稳定的可以被重复探测
- 关键点所在的位置必须有稳定的支持区域,可以计算描述子和估计唯一的法向量。
为了满足上述要求,可以通过以下探测步骤来进行关键点提取:
- 遍历每个深度图像点,通过寻找在近邻区域有深度突变的位置进行边缘检测;
- 历每个深度图像点,根据近邻区域的表面变化决定一测度表面变化的系数,以及变化的主方向;
- 根据第2步找到的主方向计算兴趣值,表征该方向与其他方向的不同,以及该处表面的变化情况,即该点有多稳定;
- 对兴趣值进行平滑过滤;
- 进行无最大值压缩找到最终的关键点,即为 NARF 关键点。
代码实现为(包含主要注释):
/**这个例子主要作用是采用NARF特征点提取算法,从深度图(rangimage)中,
* 提取矩形边缘的特征点
* 大致过程如下:
* 1. 导入点云文件(PCD)或生成一个点云文件
* 2. 将点云文件转化为深度图
* 3. 使用NARF特征点提取法,提取出特征
* 关于NARF特征点方法,可见链接**/
#include <iostream>
#include <pcl/range_image/range_image.h>
#include <pcl/io/pcd_io.h>
#include <pcl/visualization/range_image_visualizer.h>
#include <pcl/visualization/pcl_visualizer.h>
#include <pcl/features/range_image_border_extractor.h>
#include <pcl/keypoints/narf_keypoint.h>
#include <pcl/console/parse.h>
#include <pcl/common/file_io.h> // for getFilenameWithoutExtension
typedef pcl::PointXYZ PointType;
//Step1: 设置一些参数
float angular_resolution =0.5f; //angular_resolution为模拟的深度传感器的角度分辨率,即深度图像中一个像素对应的角度大小
float support_size = 0.2f; //点云大小的设置
pcl::RangeImage::CoordinateFrame coordinate_frame = pcl::RangeImage::CAMERA_FRAME;//设置深度图的相机视角
bool setUnseenToMaxRange = false; //!!重要:特征提取时,深度图的边缘是否作为边缘点进行识别
//Step2 根据命令行输入的参数,运行相应的功能; 并显示提示信息
void printUsage (const char* progName)
{
std::cout << "\n\nUsage: "<<progName<<" [options] <scene.pcd>\n\n"
<< "Options:\n"
<< "-------------------------------------------\n"
<< "-r <float> angular resolution in degrees (default "<<angular_resolution<<")\n"
<< "-c <int> coordinate frame (default "<< (int)coordinate_frame<<")\n"
<< "-m Treat all unseen points as maximum range readings\n"
<< "-s <float> support size for the interest points (diameter of the used sphere - "
<< "default "<<support_size<<")\n"
<< "-h this help\n"
<< "\n\n";
}
void setViewerPose(pcl::visualization::PCLVisualizer &viewer, const Eigen::Affine3f &viewer_pose) //设置视口的位姿
{
Eigen::Vector3f pos_vector = viewer_pose * Eigen::Vector3f(0, 0, 0);//列向量 //视口的原点pos_vector
Eigen::Vector3f look_at_vector = viewer_pose.rotation() * Eigen::Vector3f(0, 0, 1) + pos_vector; //旋转+平移look_at_vector
Eigen::Vector3f up_vector = viewer_pose.rotation() * Eigen::Vector3f(0, -1, 0); //up_vector
viewer.setCameraPosition(pos_vector[0], pos_vector[1], pos_vector[2], //设置照相机的位姿
look_at_vector[0], look_at_vector[1], look_at_vector[2],
up_vector[0], up_vector[1], up_vector[2]);
}
//Step3. 主函数
int main(int argc, char** argv){
//Step3.1 从命令行中读取输入参数!
//注意:以后可以用相同方法进行多选单编程
if (pcl::console::find_argument (argc, argv, "-h") >= 0)
{
printUsage (argv[0]);
return 0;
}
if (pcl::console::find_argument (argc, argv, "-m") >= 0)
{ //这个语句是将深度图的边缘作为识别边缘,即深度图边缘也将被识别成物体边缘
setUnseenToMaxRange = true;
std::cout << "Setting unseen values in range image to maximum range readings.\n";
}
int tmp_coordinate_frame;
if (pcl::console::parse (argc, argv, "-c", tmp_coordinate_frame) >= 0)
{
coordinate_frame = pcl::RangeImage::CoordinateFrame (tmp_coordinate_frame);
std::cout << "Using coordinate frame "<< (int)coordinate_frame<<".\n";
}
if (pcl::console::parse (argc, argv, "-s", support_size) >= 0)
std::cout << "Setting support size to "<<support_size<<".\n";
if (pcl::console::parse (argc, argv, "-r", angular_resolution) >= 0)
std::cout << "Setting angular resolution to "<<angular_resolution<<"deg.\n";
angular_resolution = pcl::deg2rad (angular_resolution);
//Step4 读取加载PCD文件或者新建一个点云对象
pcl::PointCloud<PointType>::Ptr point_cloud_ptr (new pcl::PointCloud<PointType>);
pcl::PointCloud<PointType> &point_cloud =*point_cloud_ptr;
pcl::PointCloud<pcl::PointWithViewpoint> far_ranges; //这个是什么作用-------->>>>>>
Eigen::Affine3f scene_sensor_pose(Eigen::Affine3f::Identity()); //设置一个仿射变换对象,用来进行相机位姿调整
std::vector<int> pcd_filename_indices = pcl::console::parse_file_extension_argument (argc, argv, "pcd");
//创建一个int类型vector,用来读取文件的拓展名
//需要注意的是:拓展名是存放在了这个vector里面的第[0]个元素里
//识别输入的文件拓展名是否为pcd点云
if (!pcd_filename_indices.empty ())
{
std::string filename = argv[pcd_filename_indices[0]];
if (pcl::io::loadPCDFile (filename, point_cloud) == -1)
{
std::cerr << "Was not able to open file \""<<filename<<"\".\n";
printUsage (argv[0]);
return 0;
}
//理解是:获取点云的sensor_origin+orientation,保存到scene_sensor_pose
scene_sensor_pose = Eigen::Affine3f (Eigen::Translation3f (point_cloud.sensor_origin_[0], //场景传感器的位置
point_cloud.sensor_origin_[1],
point_cloud.sensor_origin_[2])) *
Eigen::Affine3f (point_cloud.sensor_orientation_);
std::string far_ranges_filename = pcl::getFilenameWithoutExtension (filename)+"_far_ranges.pcd";
if (pcl::io::loadPCDFile (far_ranges_filename.c_str (), far_ranges) == -1)
std::cout << "Far ranges file \""<<far_ranges_filename<<"\" does not exists.\n";
}
else
{
setUnseenToMaxRange = true;
std::cout << "\nNo *.pcd file given => Generating example point cloud.\n\n";
for (float x=-0.5f; x<=0.5f; x+=0.01f)
{
for (float y=-0.5f; y<=0.5f; y+=0.01f)
{
PointType point; point.x = x; point.y = y; point.z = 2.0f - y;
point_cloud.points.push_back (point);
}
}
point_cloud.width = point_cloud.size ();
point_cloud.height = 1; //无序点云
}
//Step5 由PCD点云生成深度图
float noise_level = 0.0;
float min_range = 0.0f;
int border_size = 1; //设置深度图参数
pcl::RangeImage::Ptr range_image_ptr (new pcl::RangeImage);
pcl::RangeImage& range_image = *range_image_ptr; //创建深度图对象
//注意,下边的语句可以进行弧度角度转换
range_image.createFromPointCloud (point_cloud, angular_resolution, pcl::deg2rad (360.0f), pcl::deg2rad (180.0f),
scene_sensor_pose, coordinate_frame, noise_level, min_range, border_size);
range_image.integrateFarRanges (far_ranges);
if (setUnseenToMaxRange)
range_image.setUnseenToMaxRange ();
/*********************************************************************************************************
创建RangeImageBorderExtractor对象,它是用来进行边缘提取的,因为NARF的第一步就是需要探测出深度图像的边缘,
*********************************************************************************************************/
//Step6 :创建3D viewer并显示点云+深度图
pcl::visualization::PCLVisualizer viewer ("3D Viewer");
viewer.setBackgroundColor (1, 1, 1);
pcl::visualization::PointCloudColorHandlerCustom<pcl::PointWithRange> range_image_color_handler (range_image_ptr, 0, 0, 0);
viewer.addPointCloud (range_image_ptr, range_image_color_handler, "range image");
viewer.setPointCloudRenderingProperties (pcl::visualization::PCL_VISUALIZER_POINT_SIZE, 1, "range image");
//viewer.addCoordinateSystem (1.0f, "global");
//PointCloudColorHandlerCustom<PointType> point_cloud_color_handler (point_cloud_ptr, 150, 150, 150);
//viewer.addPointCloud (point_cloud_ptr, point_cloud_color_handler, "original point cloud");
viewer.initCameraParameters (); //??
//setViewerPose (viewer, range_image.getTransformationToWorldSystem ());
pcl::visualization::RangeImageVisualizer range_image_widget ("Range image");
range_image_widget.showRangeImage (range_image); //创建深度图显示对象,注意与PCD显示不一样
//STEP7!! 提取NARF关键点
pcl::RangeImageBorderExtractor range_image_border_extractor; 用来提取边缘
pcl::NarfKeypoint narf_keypoint_detector (&range_image_border_extractor); //用来检测关键点
narf_keypoint_detector.setRangeImage (&range_image);
narf_keypoint_detector.getParameters ().support_size = support_size;
//narf_keypoint_detector.getParameters ().add_points_on_straight_edges = true;
//narf_keypoint_detector.getParameters ().distance_for_additional_points = 0.5;
pcl::PointCloud<int> keypoint_indices;
narf_keypoint_detector.compute (keypoint_indices); //这个索引里都包含了什么??
std::cout << "Found "<<keypoint_indices.size ()<<" key points.\n";
//Step8 显示关键点 (将关键点存储成点云,并显示)
pcl::PointCloud<pcl::PointXYZ>::Ptr keypoints_ptr (new pcl::PointCloud<pcl::PointXYZ>);
pcl::PointCloud<pcl::PointXYZ>& keypoints = *keypoints_ptr;
keypoints.resize (keypoint_indices.size ());
for (std::size_t i=0; i<keypoint_indices.size (); ++i)
keypoints[i].getVector3fMap () = range_image[keypoint_indices[i]].getVector3fMap ();//!!
pcl::visualization::PointCloudColorHandlerCustom<pcl::PointXYZ> keypoints_color_handler (keypoints_ptr, 0, 255, 0);
viewer.addPointCloud<pcl::PointXYZ> (keypoints_ptr, keypoints_color_handler, "keypoints");
viewer.setPointCloudRenderingProperties (pcl::visualization::PCL_VISUALIZER_POINT_SIZE, 7, "keypoints");
//--------------------
// -----Main loop-----
//--------------------
while (!viewer.wasStopped ())
{
range_image_widget.spinOnce (); // process GUI events
viewer.spinOnce ();
pcl_sleep(0.01);
}
}