Object-wise comparison of LiDAR occupancy grid scan rendering methods

Abstract

Computing Occupancy grids with LiDAR data, is a popular strategy for environment representation. In the last two decades, several authors have proposed different methods to render the sensed information into the grids, seeking to obtain computational efficiency or accurate environment modeling. However, no comparison regarding their performance under object detection in autonomous driving applications has been found in the literature. As a result, this work compares six representative LiDAR scan rendering strategies in a quantitative manner. To that end, a novel quantitative evaluation framework for occupancy grids is proposed. It addresses the two main steps of object detection: object segmentation and features estimation, proposing a meaningful procedure, repeatable with other OG approaches.