Main Content


Segment point cloud data using deep learning and geometric algorithms

Semantic segmentation associates each point in a 3-D point cloud with a class label, such as car, truck, ground, or vegetation. Lidar Toolbox™ provides deep learning algorithms to perform semantic segmentation on point cloud data. Use PointSeg, SqueezeSegV2, and PointNet++ convolutional neural networks (CNN) to develop semantic segmentation models.

You can segment ground in point cloud data using the segmentGroundSMRF function. It is used in the Terrain Classification for Aerial Lidar Data workflow, which segments ground, vegetation and buildings in aerial point clouds.


expand all

segmentGroundSMRFSegment ground from lidar data using a SMRF algorithm
segmentLidarDataSegment organized 3-D range data into clusters
segmentGroundFromLidarDataSegment ground points from organized lidar data
segmentCurbPointsSegment curb points from point cloud
pcsegdistSegment point cloud into clusters based on Euclidean distance

Load Training Data

combineCombine data from multiple datastores
countEachLabelCount occurrence of pixel or box labels
groundTruthGround truth label data
imageDatastoreDatastore for image data
pixelLabelDatastoreDatastore for pixel label data

Augment and Preprocess Training Data

transformTransform datastore
sampleLidarDataSample 3-D bounding boxes and corresponding points from training data
pcBboxOversampleRandomly augment point cloud data using objects

Design Networks

pointCloudInputLayerPoint cloud input layer
squeezesegv2LayersCreate SqueezeSegV2 segmentation network for organized lidar point cloud
pointnetplusLayersCreate PointNet++ segmentation network

Segment Point Cloud

pcsemanticsegPoint cloud semantic segmentation using deep learning
semanticsegSemantic image segmentation using deep learning
segmentAerialLidarVegetationSegment vegetation points from aerial lidar data
segmentAerialLidarBuildingsSegment building points from aerial lidar data

Visualize Results

labeloverlayOverlay label matrix regions on 2-D image
pcshowPlot 3-D point cloud

Evaluate Results

evaluateSemanticSegmentationEvaluate semantic segmentation data set against ground truth
segmentationConfusionMatrixConfusion matrix of multi-class pixel-level image segmentation