Labeling, Segmentation, and Detection

Label, segment, detect, and track objects in point cloud data using deep learning and geometric algorithms

Lidar Toolbox™ includes geometric and pre-trained deep learning algorithms to segment point cloud data as well as detect and track objects of interest. You can apply the deep learning algorithms in advanced driver assistance systems (ADAS) applications to segment and detect vehicles. You can use the Lidar Labeler app to prepare labeled training data for the deep learning algorithms.

Highlighted Topics

Featured Examples

Lidar Object Detection Using Complex-YOLO v4 Network

Train a Complex-YOLO v4 network to perform object detection on point clouds.

Open Live Script

Lidar 3-D Object Detection Using PointPillars Deep Learning

Train a PointPillars network for object detection in point clouds.

Open Live Script

Aerial Lidar Semantic Segmentation Using PointNet++ Deep Learning

Train a PointNet++ deep learning network to perform semantic segmentation on aerial lidar data.

Open Live Script

Automate Ground Truth Labeling for Lidar Point Cloud Semantic Segmentation Using Lidar Labeler

Automate semantic labeling in a point cloud using a pretrained semantic segmentation network in the Lidar Labeler app. In this example, you can use the AutomationAlgorithm class to automate labeling in the Lidar Labeler app.

Open Live Script

Curb Detection in 3-D Lidar Point Cloud

Detect curbs in lidar point clouds. A curb is a line of stone or concrete, that connects the roadway to the sidewalk. Curbs act as delimiters for the drivable area of the road. In the absence of GPS signals, detecting the curb position is important for path planning and safe navigation in autonomous driving applications.

Open Live Script

Terrain Classification for Aerial Lidar Data

Segment and classify terrain in aerial lidar data as ground, building, and vegetation. The example uses a LAZ file captured by an airborne lidar system as input. First, classify the point cloud data in the LAZ file into ground and non-ground points. Then, further classify non-ground points into building and vegetation points based on normals and curvature features. This figure provides an overview of the process.

Open Live Script