Preprocessing

Downsample, median filter, transform, extract features from, and align 3-D point clouds

Point cloud data from a lidar sensor has applications in robot navigation and perception, depth estimation, stereo vision, visual registration, and in advanced driver assistance systems (ADAS). Raw point cloud data from lidar sensors requires basic processing before utilizing it in these advanced workflows. Lidar Toolbox™ provides functionality for downsampling, median filtering, aligning, transforming, and extracting features from point clouds. These preliminary processing algorithms can improve the quality and accuracy of data, and obtain valuable information about the point clouds. This can be helpful in accelerating advanced workflows and provide better results.

Several advanced workflows require organized point clouds for processing. You can convert unorganized point clouds to organized point clouds with the Unorganized to Organized Conversion of Point Clouds Using Spherical Projection workflow.

Functions

`pcdownsample`	Downsample a 3-D point cloud
`pcmedian`	Median filtering 3-D point cloud data
`pcdenoise`	Remove noise from 3-D point cloud
`pcalign`	Align an array point clouds
`pccat`	Concatenate 3-D point cloud array
`pcnormals`	Estimate normals for point cloud
`pctransform`	Transform 3-D 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
`findPointsInROI`	Find points within a region of interest in the point cloud
`removeInvalidPoints`	Remove invalid points from point cloud

`extractEigenFeatures`	Extract eigenvalue-based features from point cloud segments
`extractFPFHFeatures`	Extract fast point feature histogram (FPFH) descriptors from point cloud
`detectRectangularPlanePoints`	Detect rectangular plane of specified dimensions in point cloud