Main Content

Object Detection and Tracking

Object detection, classification, shape fitting, and tracking in lidar point cloud data

Object detection is a major lidar application. The objects detected in lidar point cloud data are crucial for downstream workflows like tracking and labeling. Objects are detected and stored in bounding boxes. Lidar Toolbox™ introduces a new feature that fits cuboid bounding boxes around detected objects. The fitting function uses an L-shape fitting approach to fit the bounding boxes. The toolbox also includes an object to store bounding box data.

Lidar Toolbox provides example workflows to showcase vehicle detection and tracking using a joint probabilistic data association (JPDA) tracker.

Functions

expand all

segmentLidarDataSegment organized 3-D range data into clusters
segmentGroundFromLidarDataSegment ground points from organized lidar data
pcsegdistSegment point cloud into clusters based on Euclidean distance
pcfitcuboidFit cuboid over point cloud
pcfitplaneFit plane to 3-D point cloud
pcnormalsEstimate normals for point cloud
planeModelObject for storing a parametric plane model
cuboidModelParametric cuboid model

Featured Examples