Detecting the Anomalies in LiDAR Pointcloud

TL;DR

The paper tackles the problem of detecting anomalies in LiDAR pointclouds caused by adverse weather and hardware faults without relying on labeled data. It introduces a training-free quality metric that combines spatial dispersion, via Moran's I, with an intensity-based multiplier, computed over a LiDAR image grid and accelerated by GPUs. The approach is validated on extensive real-road data from multiple LiDAR models, demonstrating effectiveness in identifying EMI-induced noise and rain/fog effects, while offering practical thresholds for safety monitoring and data selection. The proposed method enables online anomaly monitoring and offline analysis, contributing a scalable, model-free tool for ADS safety and development pipelines.

Abstract

LiDAR sensors play an important role in the perception stack of modern autonomous driving systems. Adverse weather conditions such as rain, fog and dust, as well as some (occasional) LiDAR hardware fault may cause the LiDAR to produce pointcloud with abnormal patterns such as scattered noise points and uncommon intensity values. In this paper, we propose a novel approach to detect whether a LiDAR is generating anomalous pointcloud by analyzing the pointcloud characteristics. Specifically, we develop a pointcloud quality metric based on the LiDAR points' spatial and intensity distribution to characterize the noise level of the pointcloud, which relies on pure mathematical analysis and does not require any labeling or training as learning-based methods do. Therefore, the method is scalable and can be quickly deployed either online to improve the autonomy safety by monitoring anomalies in the LiDAR data or offline to perform in-depth study of the LiDAR behavior over large amount of data. The proposed approach is studied with extensive real public road data collected by LiDARs with different scanning mechanisms and laser spectrums, and is proven to be able to effectively handle various known and unknown sources of pointcloud anomaly.

Figures (17)

• Figure 1: Examples of Anomalous LiDAR Pointcloud
• Figure 2: Illustration of Clustered and Dispersed LiDAR Pointcloud
• Figure 3: Examples of Pointcloud Distribution
• Figure 4: Exemplary LiDAR Noise in Heavy Rain
• Figure 5: Average Intensity of LiDAR Passing Road Sign