On Enhancing Ground Surface Detection from Sparse Lidar Point Cloud

TL;DR

This paper introduces a novel ground surface detection method for sparse lidar point clouds in autonomous driving, utilizing enhanced RANSAC plane fitting with tangent features for real-time performance.

Contribution

It proposes a new approach for ground detection in low-resolution lidar data using tangent features and multiple plane regions, improving accuracy and efficiency.

Findings

Effective in sparse lidar scenarios

Real-time computational performance

Improved accuracy over existing methods

Abstract

Ground surface detection in point cloud is widely used as a key module in autonomous driving systems. Different from previous approaches which are mostly developed for lidars with high beam resolution, e.g. Velodyne HDL-64, this paper proposes ground detection techniques applicable to much sparser point cloud captured by lidars with low beam resolution, e.g. Velodyne VLP-16. The approach is based on the RANSAC scheme of plane fitting. Inlier verification for plane hypotheses is enhanced by exploiting the point-wise tangent, which is a local feature available to compute regardless of the density of lidar beams. Ground surface which is not perfectly planar is fitted by multiple (specifically 4 in our implementation) disjoint plane regions. By assuming these plane regions to be rectanglar and exploiting the integral image technique, our approach approximately finds the optimal region partition and plane hypotheses under the RANSAC scheme with real-time computational complexity.