Semantic segmentation associates each point in a 3-D point cloud with a class
label, such as
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.
Load Training Data
|Combine data from multiple datastores|
|Count occurrence of pixel or box labels|
|Ground truth label data|
|Datastore for image data|
|Datastore for pixel label data|
Augment and Preprocess Training Data
|Sample 3-D bounding boxes and corresponding points from training data|
|Randomly augment point cloud data using objects|
|Create SqueezeSegV2 segmentation network for organized lidar point cloud|
|Semantic image segmentation using deep learning|
|Create PointNet++ segmentation network|
- Getting Started with Point Clouds Using Deep Learning
Understand how to use point clouds for deep learning.
- Getting Started with PointNet++
Define PointNet++ network and learn how to perform semantic segmentation using the same.
- Datastores for Deep Learning (Deep Learning Toolbox)
Learn how to use datastores in deep learning applications.
- List of Deep Learning Layers (Deep Learning Toolbox)
Discover all the deep learning layers in MATLAB®.