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

Segmentation

`segmentLidarData`	Segment organized 3-D range data into clusters
`segmentGroundFromLidarData`	Segment ground points from organized lidar data
`pcsegdist`	Segment point cloud into clusters based on Euclidean distance

Geometric Shape Fitting

`pcfitcuboid`	Fit cuboid over point cloud
`pcfitplane`	Fit plane to 3-D point cloud
`pcnormals`	Estimate normals for point cloud
`planeModel`	Object for storing a parametric plane model
`cuboidModel`	Parametric cuboid model

Featured Examples

Detect, Classify, and Track Vehicles Using Lidar

Detect, classify, and track vehicles by using lidar point cloud data captured by a lidar sensor mounted on an ego vehicle. The lidar data used in this example is recorded from a highway-driving scenario. In this example, the point cloud data is segmented to determine the class of objects using the PointSeg network. A joint probabilistic data association (JPDA) tracker with an interactive multiple model filter is used to track the detected vehicles.

Open Live Script

Track Vehicles Using Lidar: From Point Cloud to Track List

Track vehicles using measurements from a lidar sensor mounted on top of an ego vehicle. Lidar sensors report measurements as a point cloud. The example illustrates the workflow in MATLAB® for processing the point cloud and tracking the objects. For a Simulink® version of the example, refer to Track Vehicles Using Lidar Data in Simulink (Sensor Fusion and Tracking Toolbox).The lidar data used in this example is recorded from a highway driving scenario. In this example, you use the recorded data to track vehicles with a joint probabilistic data association (JPDA) tracker and an interacting multiple model (IMM) approach.

Open Script

Documentation