A Fully Interpretable Statistical Approach for Roadside LiDAR Background Subtraction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Iglesias, Aitor, Aranjuelo, Nerea, Javierre, Patricia, Menendez, Ainhoa, Arganda-Carreras, Ignacio, Nieto, Marcos
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908837970182144
author Iglesias, Aitor
Aranjuelo, Nerea
Javierre, Patricia
Menendez, Ainhoa
Arganda-Carreras, Ignacio
Nieto, Marcos
author_facet Iglesias, Aitor
Aranjuelo, Nerea
Javierre, Patricia
Menendez, Ainhoa
Arganda-Carreras, Ignacio
Nieto, Marcos
contents We present a fully interpretable and flexible statistical method for background subtraction in roadside LiDAR data, aimed at enhancing infrastructure-based perception in automated driving. Our approach introduces both a Gaussian distribution grid (GDG), which models the spatial statistics of the background using background-only scans, and a filtering algorithm that uses this representation to classify LiDAR points as foreground or background. The method supports diverse LiDAR types, including multiline 360 degree and micro-electro-mechanical systems (MEMS) sensors, and adapts to various configurations. Evaluated on the publicly available RCooper dataset, it outperforms state-of-the-art techniques in accuracy and flexibility, even with minimal background data. Its efficient implementation ensures reliable performance on low-resource hardware, enabling scalable real-world deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22390
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Fully Interpretable Statistical Approach for Roadside LiDAR Background Subtraction
Iglesias, Aitor
Aranjuelo, Nerea
Javierre, Patricia
Menendez, Ainhoa
Arganda-Carreras, Ignacio
Nieto, Marcos
Computer Vision and Pattern Recognition
We present a fully interpretable and flexible statistical method for background subtraction in roadside LiDAR data, aimed at enhancing infrastructure-based perception in automated driving. Our approach introduces both a Gaussian distribution grid (GDG), which models the spatial statistics of the background using background-only scans, and a filtering algorithm that uses this representation to classify LiDAR points as foreground or background. The method supports diverse LiDAR types, including multiline 360 degree and micro-electro-mechanical systems (MEMS) sensors, and adapts to various configurations. Evaluated on the publicly available RCooper dataset, it outperforms state-of-the-art techniques in accuracy and flexibility, even with minimal background data. Its efficient implementation ensures reliable performance on low-resource hardware, enabling scalable real-world deployment.
title A Fully Interpretable Statistical Approach for Roadside LiDAR Background Subtraction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.22390