Real-time Track Obstacle Detection from 3D LIDAR Point Cloud

Abstract

Abstract Obstacle detection is one of the important works in the field of driverless vehicle. Camera, millimeter wave radar, LIDAR and other sensors are widely used in the obstacle detection of driverless vehicle. However, cameras and millimeter wave radar are highly dependent on the environment and greatly affected by external factors, especially in the process of high-speed driving, which is easy to produce serious system errors, and even unable to detect obstacles, which has a great potential for the safety of driverless vehicle. LIDAR is used to detect obstacles by launching laser, which is not easy to be interfered by the environment. It has high precision and is suitable for outdoor environment. The main contributions of this paper are as follows: 1) a 16 line LIDAR track recognition method based on driverless equation is proposed. 2) it is easy to get the obstacle coordinates through plane segmentation and clustering for the use of subsequent camera and LIDAR fusion.