DONEX: Real-time occupancy grid based dynamic echo classification for 3D point cloud

TL;DR

DONEX is a real-time algorithm that classifies the motion state of 3D LiDAR echoes using an occupancy grid, improving speed and applicability in moving vehicle scenarios for autonomous driving.

Contribution

It introduces a novel occupancy grid-based method for dynamic echo classification in 3D LiDAR data, optimized for real-time performance in moving vehicle environments.

Findings

Reduced runtime through 2D grid approach

Effective classification of dynamic and static echoes in real-time

Applicable in scenarios with moving sensors

Abstract

For driving assistance and autonomous driving systems, it is important to differentiate between dynamic objects such as moving vehicles and static objects such as guard rails. Among all the sensor modalities, RADAR and FMCW LiDAR can provide information regarding the motion state of the raw measurement data. On the other hand, perception pipelines using measurement data from ToF LiDAR typically can only differentiate between dynamic and static states on the object level. In this work, a new algorithm called DONEX was developed to classify the motion state of 3D LiDAR point cloud echoes using an occupancy grid approach. Through algorithmic improvements, e.g. 2D grid approach, it was possible to reduce the runtime. Scenarios, in which the measuring sensor is located in a moving vehicle, were also considered.