3D Roadway Scene Object Detection with LIDARs in Snowfall Conditions

TL;DR

This paper investigates how snowfall affects LiDAR-based 3D object detection by developing a physics-based model to simulate snowy conditions and assess the impact on autonomous driving perception systems.

Contribution

It introduces a physics-based model to quantify LiDAR signal degradation in snow, enabling the simulation of snowy scenarios and evaluation of detection performance under adverse weather.

Findings

LiDAR signals attenuate with increased snowfall rates.

Snow particles near the source act as effective reflectors.

Detection performance degrades significantly in snowy conditions.

Abstract

Because 3D structure of a roadway environment can be characterized directly by a Light Detection and Ranging (LiDAR) sensors, they can be used to obtain exceptional situational awareness for assitive and autonomous driving systems. Although LiDARs demonstrate good performance in clean and clear weather conditions, their performance significantly deteriorates in adverse weather conditions such as those involving atmospheric precipitation. This may render perception capabilities of autonomous systems that use LiDAR data in learning based models to perform object detection and ranging ineffective. While efforts have been made to enhance the accuracy of these models, the extent of signal degradation under various weather conditions remains largely not quantified. In this study, we focus on the performance of an automotive grade LiDAR in snowy conditions in order to develop a physics-based model that examines failure modes of a LiDAR sensor. Specifically, we investigated how the LiDAR signal attenuates with different snowfall rates and how snow particles near the source serve as small but efficient reflectors. Utilizing our model, we transform data from clear conditions to simulate snowy scenarios, enabling a comparison of our synthetic data with actual snowy conditions. Furthermore, we employ this synthetic data, representative of different snowfall rates, to explore the impact on a pre-trained object detection model, assessing its performance under varying levels of snowfall