A Method for Synthetic LiDAR Generation to Create Annotated Datasets for Autonomous Vehicles Perception

Abstract

LiDAR devices have become a key sensor for autonomous vehicles perception due to their ability to capture reliable geometry information. Indeed, approaches processing LiDAR data have shown an impressive accuracy for 3D object detection tasks, outperforming methods solely based on image inputs. However, the wide diversity of on-board sensor configurations makes the deployment of published algorithms into real platforms a hard task, due to the scarcity of annotated datasets containing laser scans. We present a method to generate new point clouds datasets as captured by a real LiDAR device. The proposed pipeline makes use of multiple frames to perform an accurate 3D reconstruction of the scene in the spherical coordinates system that enables the simulation of the sweeps of a virtual LiDAR sensor, configurable both in location and inner specifications. The similarity between real data and the generated synthetic clouds is assessed through a set of experiments performed using KITTI Depth and Object Benchmarks.