Robust Ground Plane Detection from 3D Point Clouds

Ground provides useful and basic information such as traversal regions and location of 3D objects. The given point cloud may contain a point not only from ground, but also from other objects such as walls and people. Those points from other objects can disturb to find and identify a ground plane. In this paper, we propose robust and fast ground plane detection with an asymmetric kernel and RANSAC. We derive a probabilistic model of a 3D point based on an observation that a point from other objects is always above the ground. The asymmetric kernel is its approximation for fast computation, which is incorporated with RANSAC as a score function. We demonstrate effectiveness of our proposed method as quantitative experiments with our on-road 3D LiDAR dataset. The experimental result presents that our method was sufficiently accurate with slightly more computation. Finally, we also show our ground detection's application to augmented perception and visualization for drivers and remote operators.