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.