關鍵點也稱為興趣點，它是2D圖像或是3D點雲或者曲面模型上，可以通過定義檢測標准來獲取的具有穩定性，區別性的點集，從技術上來說，關鍵點的數量相比於原始點雲或圖像的數據量減小很多，與局部特征描述子結合在一起，組成關鍵點描述子常用來形成原始數據的表示，而且不失代表性和描述性，從而加快了后續的識別，追蹤等對數據的處理了速度，故而，關鍵點技術成為在2D和3D 信息處理中非常關鍵的技術
NARF(Normal Aligned Radial Feature)關鍵點是為了從深度圖像中識別物體而提出的，對NARF關鍵點的提取過程有以下要求：
a) 提取的過程考慮邊緣以及物體表面變化信息在內；
b)在不同視角關鍵點可以被重復探測；
c)關鍵點所在位置有足夠的支持區域，可以計算描述子和進行唯一的估計法向量。
其對應的探測步驟如下：
(1) 遍歷每個深度圖像點，通過尋找在近鄰區域有深度變化的位置進行邊緣檢測。
(2) 遍歷每個深度圖像點，根據近鄰區域的表面變化決定一測度表面變化的系數，及變化的主方向。
(3) 根據step(2)找到的主方向計算興趣點，表征該方向和其他方向的不同，以及該處表面的變化情況，即該點有多穩定。
(4) 對興趣值進行平滑濾波。
(5) 進行無最大值壓縮找到的最終關鍵點，即為NARF關鍵點。
關於NARF的更為具體的描述請查看這篇博客www.cnblogs.com/ironstark/p/5051533.html。
PCL中keypoints模塊及類的介紹
（1）class pcl::Keypoint<PointInT,PointOutT> 類keypoint是所有關鍵點檢測相關類的基類，定義基本接口，具體實現由子類來完成，其繼承關系時下圖：
具體介紹：
Public Member Functions |
|
| virtual void | setSearchSurface (const PointCloudInConstPtr &cloud) |
| 設置搜索時所用搜索點雲，cloud為指向點雲對象的指針引用 | |
| void | setSearchMethod (const KdTreePtr &tree) 設置內部算法實現時所用的搜索對象，tree為指向kdtree或者octree對應的指針 |
| void | setKSearch (int k) 設置K近鄰搜索時所用的K參數 |
| void | setRadiusSearch (double radius) 設置半徑搜索的半徑的參數 |
| int | searchForNeighbors (int index, double parameter, std::vector< int > &indices, std::vector< float > &distances) const |
| 采用setSearchMethod設置搜索對象，以及setSearchSurface設置搜索點雲，進行近鄰搜索，返回近鄰在點雲中的索引向量， indices以及對應的距離向量distance其中為查詢點的索引，parameter為搜索時所用的參數半徑或者K |
|
（2）class pcl::HarrisKeypoint2D<PointInT,PointOutT,IntensityT>
類HarrisKeypoint2D實現基於點雲的強度字段的harris關鍵點檢測子，其中包括多種不同的harris關鍵點檢測算法的變種，其關鍵函數的說明如下：
Public Member Functions |
|
| HarrisKeypoint2D (ResponseMethod method=HARRIS, int window_width=3, int window_height=3, int min_distance=5, float threshold=0.0) | |
| 重構函數，method需要設置采樣哪種關鍵點檢測方法，有HARRIS，NOBLE，LOWE，WOMASI四種方法，默認為HARRIS，window_width window_height為檢測窗口的寬度和高度min_distance 為兩個關鍵點之間 容許的最小距離，threshold為判斷是否為關鍵點的感興趣程度的閥值，小於該閥值的點忽略，大於則認為是關鍵點 | |
| void | setMethod (ResponseMethod type)設置檢測方式 |
| void | setWindowWidth (int window_width) 設置檢測窗口的寬度 |
| void | setWindowHeight (int window_height) 設置檢測窗口的高度 |
| void | setSkippedPixels (int skipped_pixels) 設置在檢測時每次跳過的像素的數目 |
| void | setMinimalDistance (int min_distance) 設置候選關鍵點之間的最小距離 |
| void | setThreshold (float threshold) 設置感興趣的閥值 |
| void | setNonMaxSupression (bool=false) 設置是否對小於感興趣閥值的點進行剔除，如果是true則剔除,否則返回這個點 |
| void | setRefine (bool do_refine)設置是否對所得的關鍵點結果進行優化， |
| void | setNumberOfThreads (unsigned int nr_threads=0) 設置該算法如果采用openMP並行機制，能夠創建線程數目 |
（3）pcl::HarrisKeypoint3D< PointInT, PointOutT, NormalT >
類HarrisKeypoint3D和HarrisKeypoint2D類似，但是沒有在點雲的強度空間檢測關鍵點，而是利用點雲的3D空間的信息表面法線向量來進行關鍵點檢測，關於HarrisKeypoint3D的類與HarrisKeypoint2D相似，除了
HarrisKeypoint3D (ResponseMethod method=HARRIS, float radius=0.01f, float threshold=0.0f)
重構函數，method需要設置采樣哪種關鍵點檢測方法，有HARRIS，NOBLE，LOWE，WOMASI四種方法，默認為HARRIS，radius為法線估計的搜索半徑，threshold為判斷是否為關鍵點的感興趣程度的閥值，小於該閥值的點忽略，大於則認為是關鍵點。
（4）pcl::HarrisKeypoint6D< PointInT, PointOutT, NormalT >
類HarrisKeypoint6D和HarrisKeypoint2D類似，只是利用了歐式空間域XYZ或者強度域來候選關鍵點，或者前兩者的交集，即同時滿足XYZ域和強度域的關鍵點為候選關鍵點，
HarrisKeypoint6D (float radius=0.01, float threshold=0.0) 重構函數，此處並沒有方法選擇的參數，而是默認采用了Tomsai提出的方法實現關鍵點的檢測，radius為法線估計的搜索半徑，threshold為判斷是否為關鍵點的感興趣程度的閥值，小於該閥值的點忽略，大於則認為是關鍵點。
（5）pcl::SIFTKeypoint< PointInT, PointOutT >
類SIFTKeypoint是將二維圖像中的SIFT算子調整后移植到3D空間的SIFT算子的實現，輸入帶有XYZ坐標值和強度的點雲，輸出為點雲中的SIFT關鍵點，其關鍵函數的說明如下：
| void | setScales (float min_scale, int nr_octaves, int nr_scales_per_octave) |
| 設置搜索時與尺度相關的參數，min_scale在點雲體素尺度空間中標准偏差，點雲對應的體素柵格中的最小尺寸 | |
| int nr_octaves是檢測關鍵點時體素空間尺度的數目，nr_scales_per_octave為在每一個體素空間尺度下計算高斯空間的尺度所需要的參數 | |
| void | setMinimumContrast (float min_contrast) 設置候選關鍵點對應的對比度下限 |
（6）還有很多不再一一介紹
實例分析
實驗實現提取NARF關鍵點，並且用圖像和3D顯示的方式進行可視化，可以直觀的觀察關鍵點的位置和數量 narf_feature_extraction.cpp：
#include <iostream> #include <boost/thread/thread.hpp> #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/features/narf_descriptor.h> #include <pcl/console/parse.h> typedef pcl::PointXYZ PointType; // -------------------- // -----Parameters----- // -------------------- float angular_resolution = 0.5f; ////angular_resolution為模擬的深度傳感器的角度分辨率，即深度圖像中一個像素對應的角度大小 float support_size = 0.2f; //點雲大小的設置 pcl::RangeImage::CoordinateFrame coordinate_frame = pcl::RangeImage::CAMERA_FRAME; //設置坐標系 bool setUnseenToMaxRange = false; bool rotation_invariant = true; // -------------- // -----Help----- // -------------- 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 to max range\n" << "-s <float> support size for the interest points (diameter of the used sphere - " "default "<<support_size<<")\n" << "-o <0/1> switch rotational invariant version of the feature on/off" << " (default "<< (int)rotation_invariant<<")\n" << "-h this help\n" << "\n\n"; } void setViewerPose (pcl::visualization::PCLVisualizer& viewer, const Eigen::Affine3f& viewer_pose) //設置視口的位姿 { Eigen::Vector3f pos_vector = viewer_pose * Eigen::Vector3f (0, 0, 0); //視口的原點pos_vector Eigen::Vector3f look_at_vector = viewer_pose.rotation () * Eigen::Vector3f (0, 0, 1) + pos_vector; //旋轉+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], //設置照相機的位姿 look_at_vector[0], look_at_vector[1], look_at_vector[2], up_vector[0], up_vector[1], up_vector[2]); } // -------------- // -----Main----- // -------------- int main (int argc, char** argv) { // -------------------------------------- // -----Parse Command Line Arguments----- // -------------------------------------- if (pcl::console::find_argument (argc, argv, "-h") >= 0) { printUsage (argv[0]); return 0; } if (pcl::console::find_argument (argc, argv, "-m") >= 0) { setUnseenToMaxRange = true; cout << "Setting unseen values in range image to maximum range readings.\n"; } if (pcl::console::parse (argc, argv, "-o", rotation_invariant) >= 0) cout << "Switching rotation invariant feature version "<< (rotation_invariant ? "on" : "off")<<".\n"; int tmp_coordinate_frame; if (pcl::console::parse (argc, argv, "-c", tmp_coordinate_frame) >= 0) { coordinate_frame = pcl::RangeImage::CoordinateFrame (tmp_coordinate_frame); cout << "Using coordinate frame "<< (int)coordinate_frame<<".\n"; } if (pcl::console::parse (argc, argv, "-s", support_size) >= 0) cout << "Setting support size to "<<support_size<<".\n"; if (pcl::console::parse (argc, argv, "-r", angular_resolution) >= 0) cout << "Setting angular resolution to "<<angular_resolution<<"deg.\n"; angular_resolution = pcl::deg2rad (angular_resolution); // ------------------------------------------------------------------ // -----Read pcd file or create example point cloud if not given----- // ------------------------------------------------------------------ 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; Eigen::Affine3f scene_sensor_pose (Eigen::Affine3f::Identity ()); std::vector<int> pcd_filename_indices = pcl::console::parse_file_extension_argument (argc, argv, "pcd"); if (!pcd_filename_indices.empty ()) { std::string filename = argv[pcd_filename_indices[0]]; if (pcl::io::loadPCDFile (filename, point_cloud) == -1) { cerr << "Was not able to open file \""<<filename<<"\".\n"; printUsage (argv[0]); return 0; } scene_sensor_pose = Eigen::Affine3f (Eigen::Translation3f (point_cloud.sensor_origin_[0], //場景傳感器的位置 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; cout << "\nNo *.pcd file given => Genarating 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 = (int) point_cloud.points.size (); point_cloud.height = 1; } // ----------------------------------------------- // -----Create RangeImage from the PointCloud----- // ----------------------------------------------- float noise_level = 0.0; float min_range = 0.0f; int border_size = 1; boost::shared_ptr<pcl::RangeImage> range_image_ptr (new pcl::RangeImage); pcl::RangeImage& range_image = *range_image_ptr; 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 (); // -------------------------------------------- // -----Open 3D viewer and add point cloud----- // -------------------------------------------- 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 ()); // -------------------------- // -----Show range image----- // -------------------------- pcl::visualization::RangeImageVisualizer range_image_widget ("Range image"); range_image_widget.showRangeImage (range_image); /********************************************************************************************************* 創建RangeImageBorderExtractor對象，它是用來進行邊緣提取的，因為NARF的第一步就是需要探測出深度圖像的邊緣， *********************************************************************************************************/ // -------------------------------- // -----Extract NARF keypoints----- // -------------------------------- pcl::RangeImageBorderExtractor range_image_border_extractor; //用來提取邊緣 pcl::NarfKeypoint narf_keypoint_detector; //用來檢測關鍵點 narf_keypoint_detector.setRangeImageBorderExtractor (&range_image_border_extractor); // narf_keypoint_detector.setRangeImage (&range_image); narf_keypoint_detector.getParameters ().support_size = support_size; //設置NARF的參數 pcl::PointCloud<int> keypoint_indices; narf_keypoint_detector.compute (keypoint_indices); std::cout << "Found "<<keypoint_indices.points.size ()<<" key points.\n"; // ---------------------------------------------- // -----Show keypoints in range image widget----- // ---------------------------------------------- //for (size_t i=0; i<keypoint_indices.points.size (); ++i) //range_image_widget.markPoint (keypoint_indices.points[i]%range_image.width, //keypoint_indices.points[i]/range_image.width); // ------------------------------------- // -----Show keypoints in 3D viewer----- // ------------------------------------- pcl::PointCloud<pcl::PointXYZ>::Ptr keypoints_ptr (new pcl::PointCloud<pcl::PointXYZ>); pcl::PointCloud<pcl::PointXYZ>& keypoints = *keypoints_ptr; keypoints.points.resize (keypoint_indices.points.size ()); for (size_t i=0; i<keypoint_indices.points.size (); ++i) keypoints.points[i].getVector3fMap () = range_image.points[keypoint_indices.points[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"); // ------------------------------------------------------ // -----Extract NARF descriptors for interest points----- // ------------------------------------------------------ std::vector<int> keypoint_indices2; keypoint_indices2.resize (keypoint_indices.points.size ()); for (unsigned int i=0; i<keypoint_indices.size (); ++i) // This step is necessary to get the right vector type keypoint_indices2[i]=keypoint_indices.points[i]; pcl::NarfDescriptor narf_descriptor (&range_image, &keypoint_indices2); narf_descriptor.getParameters ().support_size = support_size; narf_descriptor.getParameters ().rotation_invariant = rotation_invariant; pcl::PointCloud<pcl::Narf36> narf_descriptors; narf_descriptor.compute (narf_descriptors); cout << "Extracted "<<narf_descriptors.size ()<<" descriptors for " <<keypoint_indices.points.size ()<< " keypoints.\n"; //-------------------- // -----Main loop----- //-------------------- while (!viewer.wasStopped ()) { range_image_widget.spinOnce (); // process GUI events viewer.spinOnce (); pcl_sleep(0.01); } }
運行結果：
未完待續**********************88888
有興趣這可以掃描下面的二維碼關注公眾號與我交流，
