Mapping LiDAR and Camera Measurements in a Dual Top-View Grid Representation Tailored for Automated Vehicles
This work addresses the need for reliable sensor fusion in automated driving, though it appears incremental as it builds on existing grid mapping techniques with specific adaptations for LiDAR and camera inputs.
The authors tackled the problem of robustly mapping LiDAR and camera data for automated vehicles by introducing a dual top-view grid representation that separately estimates occupancy and ground semantics, achieving high detail and efficiency in real traffic scenarios.
We present a generic evidential grid mapping pipeline designed for imaging sensors such as LiDARs and cameras. Our grid-based evidential model contains semantic estimates for cell occupancy and ground separately. We specify the estimation steps for input data represented by point sets, but mainly focus on input data represented by images such as disparity maps or LiDAR range images. Instead of relying on an external ground segmentation only, we deduce occupancy evidence by analyzing the surface orientation around measurements. We conduct experiments and evaluate the presented method using LiDAR and stereo camera data recorded in real traffic scenarios. Our method estimates cell occupancy robustly and with a high level of detail while maximizing efficiency and minimizing the dependency to external processing modules.