• documentation
main content

point cloud processing -凯发k8网页登录

preprocess, visualize, register, fit geometrical shapes, build maps, implement slam algorithms, and use deep learning with 3-d point clouds

a point cloud is a set of data points in 3-d space. the points together represent a 3-d shape or object. each point in the data set is represented by an x, y, and z geometric coordinate. point clouds provide a means of assembling a large number of single spatial measurements into a dataset that can be represented as a describable object. point cloud processing is used in robot navigation and perception, depth estimation, stereo vision, visual registration, and in advanced driver assistance systems (adas). computer vision toolbox™ algorithms provide point cloud processing functionality for downsampling, denoising, and transforming point clouds. the toolbox also provides point cloud registration, geometrical shape fitting to 3-d point clouds, and the ability to read, write, store, display, and compare point clouds. you can also combine multiple point clouds to reconstruct a 3-d scene.

you can use , , , and to register a moving point cloud to a fixed point cloud. these registration algorithms are based on the iterative closest point (icp) algorithm, the normal-distributions transform (ndt) algorithm, the phase correlation algorithm, and the coherent point drift (cpd) algorithm, respectively. you can build a map with the registered point clouds, detect loop closures, optimize the map to correct for drift, and perform localization in the prebuilt map. for more details, see .

figure showing a point cloud of two concentric point clouds combined, a sensor angle computation, and a point cloud representing a teapot

functions

read 3-d point cloud from ply or pcd file
write 3-d point cloud to ply or pcd file
convert depth image to point cloud
point cloud from kinect for windows
read point cloud data from velodyne pcap file
manage data for point cloud based visual odometry and slam
object for storing 3-d point cloud
visualize and inspect large 3-d point cloud
plot 3-d point cloud
visualize difference between two point clouds
visualize streaming 3-d point cloud data
display shapes on image, video, or point cloud

preprocess

spatially bin point cloud points
remove noise from 3-d point cloud
downsample a 3-d point cloud
estimate normals for point cloud

find and remove points

find points within a cylindrical region in a point cloud
find points within a region of interest in the point cloud
find nearest neighbors of a point in point cloud
find neighbors within a radius of a point in the point cloud
remove invalid points from point cloud
segment point cloud into clusters based on euclidean distance
segment ground points from organized lidar data
segment organized 3-d range data into clusters
spatially bin point cloud points

register point clouds

register two point clouds using phase correlation
register two point clouds using icp algorithm
register two point clouds using cpd algorithm
register two point clouds using ndt algorithm

transform point clouds

3-d rigid geometric transformation
transform 3-d point cloud

align or combine point clouds

align array of point clouds
concatenate 3-d point cloud array
merge two 3-d point clouds

determine loop closure candidates

localize point cloud within map using normal distributions transform (ndt) algorithm
distance between scan context descriptors
extract scan context descriptor from point cloud
detect loop closures using scan context descriptors

optimize poses

create pose graph
optimize absolute poses using relative pose constraints

create localization map

localization map based on normal distributions transform (ndt)
fit cylinder to 3-d point cloud
fit plane to 3-d point cloud
fit sphere to 3-d point cloud
estimate normals for point cloud
fit polynomial to points using ransac
fit model to noisy data
parametric cylinder model
object for storing parametric plane model
object for storing a parametric sphere model

blocks

visualize streaming point cloud data sequence

topics

网站地图