3D Roadway Scene Object Detection with LIDARs in Snowfall Conditions

2025-10-25

AI Summary

Snowfall induces LiDAR signal attenuation and scattering, severely degrading 3D object detection performance; however, existing work lacks quantitative, physics-based modeling of degradation mechanisms across varying snow intensities. Method: We propose the first physics-informed vehicular LiDAR snow degradation model, explicitly characterizing how snowflake size, density, and fall velocity affect laser attenuation and backscattering, and enabling high-fidelity synthetic point cloud generation conditioned on snowfall rate (0.5–10 mm/h). Contribution/Results: Through systematic real-synthetic data comparison, we quantitatively benchmark performance degradation of mainstream 3D detectors—including PointPillars and CenterPoint—under snow conditions. The model establishes an interpretable, reproducible quantitative benchmark and data synthesis tool for robustness analysis of perception systems in adverse weather.

Technology Category

• Computer Vision: 3D Computer Vision
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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

Problem

• Quantifying LiDAR signal degradation in snowfall conditions
• Developing physics-based model for LiDAR failure modes
• Assessing object detection performance under varying snowfall rates

Innovation

• Developed physics-based LiDAR model for snowfall
• Simulated snowy scenarios from clear weather data
• Assessed object detection model under varying snowfall