Calibrate multiple 3-D lidar sensors mounted on a vehicle to estimate a relative transformation between them. Traditional methods, such as marker-based registration, are difficult when the lidar sensors have a negligible overlap between their fields of view (FOVs). The calibration also becomes more difficult as the number of lidar sensors increases. This example demonstrates the use of the trajectories of individual lidar sensors to estimate the transformation between them. This method of calibration is also known as hand-eye calibration.

Convert unorganized point clouds to organized format using spherical projection.

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

Train a PointPillars network for object detection in point clouds.

Extract forest metrics and individual tree attributes from aerial lidar data.

Implement the simultaneous localization and mapping (SLAM) algorithm on a series of 2-D lidar scans using scan processing algorithms and pose graph optimization (PGO). The goal of this example is to estimate the trajectory of the robot and build a map of the environment.

Demonstrates how to process 3-D lidar data from a sensor mounted on a vehicle to progressively build a map. Such a map is suitable for automated driving workflows such as localization and navigation. These maps can be used to localize a vehicle within a few centimeters.