% ---------------------------------------------------------------------- % 步骤1:定义所需的属性描述算法。这%包括名称、描述和用户指示。properties(Constant) % Name算法名称%指定算法名称的字符向量。Name = '激光雷达车辆探测器';% Description Algorithm Description %字符向量，指定算法的简短描述。Description = '使用PointPillars网络检测点云中的车辆';% UserDirections Algorithm Usage Directions字符向量的单元格数组，指定算法用户使用算法时要遵循的方向。UserDirections = {['ROI标签定义选择:选择一个'…“要标注的ROI定义”]，……['Run:按Run运行自动化算法。 '], ... ['Review and Modify: Review automated labels over the interval ', ... 'using playback controls. Modify/delete/add ROIs that were not ' ... 'satisfactorily automated at this stage. If the results are ' ... 'satisfactory, click Accept to accept the automated labels.'], ... ['Change Settings and Rerun: If automated results are not ' ... 'satisfactory, you can try to re-run the algorithm with ' ... 'different settings. To do so, click Undo Run to undo ' ... 'current automation run, click Settings, make changes to Settings,' ... 'and press Run again.'], ... ['Accept/Cancel: If the results of automation are satisfactory, ' ... 'click Accept to accept all automated labels and return to ' ... 'manual labeling. If the results of automation are not ' ... 'satisfactory, click Cancel to return to manual labeling ' ... 'without saving the automated labels.']}; end

% --------------------------------------------------------------------- % 第二步:定义您想要使用的属性在算法执行%。properties % SelectedLabelName %所选标签的名称。算法%检测到的车辆被赋给这个变量名。% PretrainedNetwork保存预训练的pointcolumns dlnetwork。PretrainedNetwork %沿x,y和z轴的点云范围，用于将全视图点云裁剪为前视图点云。这些参数指导计算传递给网络的输入[xn,yn]的大小。% xMin = 0.0;% x轴上最小值。% yMin = -39.68;% y轴最小值。 % zMin = -5.0; % Minimum value along Z-axis. % xMax = 69.12 % Maximum value along X-axis. % yMax = 39.68; % Maximum value along Y-axis. % zMax = 5.0; % Maximum value along Z-axis. % xStep = 0.16; % Resolution along X-axis. % yStep = 0.16; % Resolution along Y-axis. % dsFactor = 2.0; % Downsampling factor. % Dimensions for the pseudo-image calculated as % round(((xMax - xMin) / xStep));. % Xn = 432; % Yn = 496; % GridParams % Parameter used to crop full-view point cloud to front-view, % defined as {{xMin,yMin,zMin}, {xMax,yMax,zMax}, % {xStep,yStep,dsFactor}, {Xn,Yn}}; GridParams = {{0.0,-39.68,-5.0}, {69.12,39.68,5.0}, {0.16,0.16,2.0}, {432,496}} % AnchorBoxes % Predefined bounding box dimensions based on the classes to % detect, defined in the format {length, width, height, % z-center, yaw angle} AnchorBoxes = {{3.9, 1.6, 1.56, -1.78, 0}, {3.9, 1.6, 1.56, -1.78, pi/2}}; % P % Number of prominent pillars. P = 12000; % N % Number of points per pillar. N = 100; % ExecutionEnvironment % Set the execution environment. ExecutionEnvironment = "auto"; % ConfidenceThreshold % Specify the confidence threshold to use only detections with % confidence scores above this value. ConfidenceThreshold = 0.45; % OverlapThreshold % Specify the overlap threshold to remove overlapping detections. OverlapThreshold = 0.1; end

只有点云信号数据对激光雷达车辆%探测器算法有效。isValid = (signalType == vision.label .loading. signalType . pointcloud);结束

函数isValid=checkLabelDefinition（~，labelDef）%Lidar%车辆检测器算法仅长方体ROI标签定义有效。isValid=labelDef.Type==labelType.cuboid；结束

函数isReady = checkSetup(algObj) %是否有一个选择的ROI标签定义要自动化。isReady = ~ isempty (algObj.SelectedLabelDefinitions);结束

函数设置dialog (algObj) %调用对话框，带有修改%阈值和置信度阈值的选项。lidarVehicleDetectorSettings (algObj)结束

函数initialize(algObj，~) %存储选定标签定义的名称。使用这个%名称来标记检测到的车辆。algObj。挑选edLabelName = algObj.SelectedLabelDefinitions.Name; % Add the folder containing helper functions to the search path. addpath(fullfile(matlabroot,'examples','deeplearning_shared','main')) % Point to tempdir, where pretrainedNet was downloaded. preTrainedMATFile = fullfile(tempdir,'trainedPointPillarsNet.mat'); assert(exist(preTrainedMATFile,'file'), ... sprintf(['File : %s does not exists \n Download Pretrained PointPillars ' ... 'network with the link provided in the example'],preTrainedMATFile)); pretrainedNet = load(preTrainedMATFile); algObj.PretrainedNetwork = pretrainedNet.net; end

函数autoLabels=run（algObj，pointCloud）bBoxes=[]；对于i=1:2，如果i==2%，则将点云旋转180度。θ=π；rot=[cos（thetha）sin（thetha）0；..-sin（thetha）cos（thetha）0；..01]；trans=[0,0,0]；tform=rigid3d（旋转、平移）；点云=pctransform（点云，tform）；结束%裁剪点云的前视图。processedPointCloud=helperCropFrontViewFromLidarData（pointCloud，…algObj.GridParams）；%使用PointPillars网络检测车辆。[box，~，~]=generatePointPillarDetections（algObj.PretrainedNetwork，…processedPointCloud，algObj.AnchorBoxes，algObj.GridParams，{algObj.SelectedLabelName}，algObj.ConfidenceThreshold，…algObj.overlaverthreshold，algObj.P，algObj.N，algObj.ExecutionEnvironment）；if~isempty（box）if i==2 box（：，1）=-box（：，1）；框（：，2）=-框（：，2）；框（：，9）=-框（：，9）；结束bBoxes=[bBoxes；box]；如果~isempty（bBoxes）%在车辆检测器检测到的边界框位置添加自动标签，类型为长方体，名称为所选标签的%。autoLabels.Name=algObj.SelectedLabelName；autoLabels.Type=labelType.Cuboid；自动标签。位置=b框；else自动标签=[]；结束

mkdir（'+vision/+labeler'）；copyfile（完整文件（matlabroot，'examples'，'lidar'，'main'，'LidarVehicleDetector.m'），…'+vision/+labeler'）；

利达鲁尔//www.tatmou.com/supportf金宝appiles/lidar/data/WPI_LidarData.tar.gz“；lidarDataFolder=fullfile（tempdir，'WPI_LidarData'，filesep）；lidardatafile=lidarDataFolder+“WPI_LidarData.tar.gz”；if~exist（lidarDataFolder）mkdir（lidarDataFolder）end if~exist（lidardatafile，'file'）disp（'下载WPI激光雷达驱动数据（760MB）…'）；websave（lidardatafile，lidarURL）；untar（lidardatafile，lidarDataFolder）；end%检查lidar tar.gz文件是否已下载，但未解压缩。如果~存在（fullfile（lidarDataFolder，'WPI_LidarData.mat'），'file'）untar（lidardatafile，lidarDataFolder）；end

%加载下载的激光雷达数据到工作区。负载(fullfile (lidarDataFolder WPI_LidarData.mat),“lidarData”);lidarData =重塑(lidarData，大小(lidarData,2)，1);%创建新文件夹并将激光雷达数据写入PCD文件。pcdDataFolder = lidarDataFolder + "lidarData";如果存在(pcdDataFolder， 'dir') mkdir(fullfile(lidarDataFolder，'lidarData'));end disp('保存WPI激光雷达驱动数据到PCD文件…');for i = 920:940 filename = strcat(fullfile(lidarDataFolder，'lidarData'，filesep)，…num2str(我,“% 06.0 f”)、“.pcd”);我pcwrite (lidarData{},文件名); end

pointCloudDir = fullfile(lidarDataFolder， 'lidarData');lidarLabeler (pointCloudDir);