点云处理

对三维点云进行预处理、可视化、配准、拟合几何形状、构建地图、实现 SLAM 算法以及使用深度学习

点云是三维空间中的一组数据点。这些点共同构成一个三维形状或目标。数据集中的每个点由 x、y 和 z 几何坐标表示。点云可用于将大量单个空间测量值组合成一个数据集，该数据集可表示为一个可描述的目标。点云处理用于机器人导航和感知、深度估计、立体视觉、视觉配准以及高级驾驶辅助系统 (ADAS)。Computer Vision Toolbox™ 算法提供点云处理功能，用于对点云进行下采样、去噪和变换。该工具箱还提供点云配准、三维点云的几何形状拟合，以及读取、写入、存储、显示和比较点云的功能。您可以合并多个点云来重建一个三维场景，或使用配准的点云构建地图，检测闭环，优化地图以校正漂移，以及在预置的地图中执行定位。有关详细信息，请参阅Implement Point Cloud SLAM in MATLAB。

要执行点云配准，即将两个或多个点云对齐到单个坐标系的过程，通常需要先将一个点云作为参考，即固定点云，然后将其他点云（即移动点云）与之对齐。点云的绝对位姿指的是点云相对于参考系（通常称为世界坐标系）的全局位置和方向。Computer Vision Toolbox 提供了各种配准方法，用于将移动点云配准到固定点云。这些方法包括迭代最近点 (ICP)、正态分布变换 (NDT)、相位相关和相干点漂移 (CPD)。您还可以使用激光雷达配准分析器 (Lidar Toolbox)以交互方式进行配准，并比较使用不同配准方法、调节参数和预处理步骤所得的结果。

函数

全部展开

读取和写入点云

`pcread`	Read 3-D point cloud from PLY or PCD file
`pcwrite`	Write 3-D point cloud to PLY or PCD file
`pcfromdepth`	Convert depth image to point cloud (自 R2022b 起)
`pcfromkinect`	Point cloud from Kinect for Windows
`velodyneFileReader`	Read point cloud data from Velodyne PCAP file

存储点云

`pcviewset`	Manage data for point cloud based visual odometry and SLAM (自 R2020a 起)
`pointCloud`	Object for storing 3-D point cloud

可视化点云

`pcviewer`	Visualize and inspect large 3-D point cloud (自 R2023a 起)
`pcshow`	Plot 3-D point cloud
`pcshowpair`	Visualize difference between two point clouds
`pcplayer`	Visualize streaming 3-D point cloud data
`showShape`	Display shapes on image, video, or point cloud (自 R2020b 起)

处理点云

预处理

`pcbin`	Spatially bin point cloud points (自 R2020a 起)
`pcdenoise`	Remove noise from 3-D point cloud
`pcdownsample`	Downsample a 3-D point cloud
`pcnormals`	Estimate normals for point cloud

查找和删除点

`findPointsInCylinder`	Find points within a cylindrical region in a point cloud (自 R2023a 起)
`findPointsInROI`	Find points within a region of interest in the point cloud
`findNearestNeighbors`	Find nearest neighbors of a point in point cloud
`findNeighborsInRadius`	Find neighbors within a radius of a point in the point cloud
`removeInvalidPoints`	Remove invalid points from point cloud

分割点云

`pcsegdist`	Segment point cloud into clusters based on Euclidean distance
`segmentGroundFromLidarData`	Segment ground points from organized lidar data
`segmentLidarData`	Segment organized 3-D range data into clusters
`pcbin`	Spatially bin point cloud points (自 R2020a 起)

配准点云和创建地图

配准点云

`pcregistercorr`	Register two point clouds using phase correlation (自 R2020b 起)
`pcregistericp`	Register two point clouds using ICP algorithm
`pcregistercpd`	Register two point clouds using CPD algorithm
`pcregisterndt`	Register two point clouds using NDT algorithm

变换点云

`rigidtform3d`	3-D rigid geometric transformation (自 R2022b 起)
`pctransform`	Transform 3-D point cloud

对齐或合并点云

`pcalign`	Align array of point clouds (自 R2020b 起)
`pccat`	Concatenate 3-D point cloud array (自 R2020b 起)
`pcmerge`	Merge two 3-D point clouds

确定闭环候选项

`findPose`	Localize point cloud within map using normal distributions transform (NDT) algorithm (自 R2021a 起)
`scanContextDistance`	Distance between scan context descriptors (自 R2020b 起)
`scanContextDescriptor`	Extract scan context descriptor from point cloud (自 R2020b 起)
`scanContextLoopDetector`	Detect loop closures using scan context descriptors (自 R2021b 起)

优化位姿

`createPoseGraph`	Create pose graph (自 R2020a 起)
`optimizePoses`	Optimize absolute poses using relative pose constraints (自 R2020a 起)

创建定位地图

pcmapndt Localization map based on normal distributions transform (NDT) (自 R2021a 起)

对点云进行几何模型拟合

`pcfitcylinder`	Fit cylinder to 3-D point cloud
`pcfitplane`	Fit plane to 3-D point cloud
`pcfitsphere`	Fit sphere to 3-D point cloud
`pcnormals`	Estimate normals for point cloud
`fitPolynomialRANSAC`	Fit polynomial to points using RANSAC
`ransac`	Fit model to noisy data
`cylinderModel`	Parametric cylinder model
`planeModel`	Object for storing parametric plane model
`sphereModel`	Object for storing a parametric sphere model

模块

全部展开

可视化点云

Point Cloud Viewer

Visualize streaming point cloud data sequence (自 R2023a 起)

主题

Choose a Point Cloud Viewer
Compare visualization functions.
Choose SLAM Workflow Based on Sensor Data
Choose the right simultaneous localization and mapping (SLAM) workflow and find topics, examples, and supported features.
Implement Point Cloud SLAM in MATLAB
Understand point cloud registration and mapping workflow.
Getting Started with Point Clouds Using Deep Learning
Understand how to use point clouds for deep learning.
The PLY Format
The Stanford Triangle Format.
Getting Started with Point Clouds Using Deep Learning
Understand how to use point clouds for deep learning.
Choose Function to Visualize Detected Objects
Compare visualization functions.
Labeling, Segmentation, and Detection (Lidar Toolbox)
Label, segment, detect, and track objects in point cloud data using deep learning and geometric algorithms

精选示例

Build a Map from Lidar Data Using SLAM

Process lidar data to build a map and estimate a vehicle trajectory using simultaneous localization and mapping.

打开实时脚本

Build a Map from Lidar Data Using SLAM on GPU

Perform 3-D simultaneous localization and mapping (SLAM) on an NVIDIA^® GPU.

打开实时脚本

Point Cloud Classification Using PointNet Deep Learning

Train PointNet for point cloud classification.

打开实时脚本

Build a Map from Lidar Data

Process 3-D lidar sensor data to progressively build a map, with assistance from inertial measurement unit (IMU) readings.

打开脚本

Detect and Track Vehicles Using Lidar Data

Track vehicles using measurements from a lidar sensor mounted on top of an ego vehicle.

打开脚本

Train Classification Network to Classify Object in 3-D Point Cloud

Train a classification network to classify objects in a 3-D point cloud.

打开实时脚本

3-D Point Cloud Registration and Stitching

Combine multiple point clouds to reconstruct a 3-D scene using Iterative Closest Point (ICP) algorithm. It then shows how to leverage color information available in the point clouds to improve the accuracy of the scene.

打开实时脚本

Design Lidar SLAM Algorithm Using Unreal Engine Simulation Environment

Record synthetic sensor data from a 3-D simulation environment, and develop a simultaneous localization and mapping (SLAM) algorithm using the recorded data.

打开实时脚本

Ground Plane and Obstacle Detection Using Lidar

Process 3-D lidar data from a sensor mounted on a vehicle by segmenting the ground plane and finding nearby obstacles.

打开脚本

本页内容对您有帮助吗？

Unrated 1 star 2 stars 3 stars 4 stars 5 stars