DETECTION AND TRACKING OF ROAD-SIDE POLE-SHAPED STATIC OBJECTS FROM LIDAR POINT CLOUD DATA

摘要

Systems and methods of detecting and tracking a pole-shaped object proximate to a vehicle comprise down-sampling three-dimensional (3D) light detection and ranging (LIDAR) point cloud data for each of a plurality of frames according to a user-configurable voxel size, filtering the down-sampled 3D LIDAR point cloud data to remove data points corresponding to ground surface reflections, dividing the 3D LIDAR point cloud data into a plurality of clusters that are parallel to the vehicle's moving direction, projecting the plurality of clusters to a plane that is parallel to sides of the vehicle to generate an image, detecting a pole-shaped object in the image, and tracking the pole-shaped object by deep sorting across multiple frames of the plurality of frames.