Optimizing plane detection in point clouds through line sampling

Abstract Plane detection in point clouds is a common step in interpreting environments within robotics. Mobile robotic platforms must interact efficiently and safely with their surroundings, which requires capabilities such as detecting walls to avoid collisions and recognizing workbenches for objec...

Full description

Saved in:
Bibliographic Details
Main Authors: José María Martínez-Otzeta, Jon Azpiazu, Iñigo Mendialdua, Basilio Sierra
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-12660-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226474156982272
author José María Martínez-Otzeta
Jon Azpiazu
Iñigo Mendialdua
Basilio Sierra
author_facet José María Martínez-Otzeta
Jon Azpiazu
Iñigo Mendialdua
Basilio Sierra
author_sort José María Martínez-Otzeta
collection DOAJ
description Abstract Plane detection in point clouds is a common step in interpreting environments within robotics. Mobile robotic platforms must interact efficiently and safely with their surroundings, which requires capabilities such as detecting walls to avoid collisions and recognizing workbenches for object manipulation. Since these environmental elements typically appear as plane-shaped surfaces, a fast and accurate plane detector is an essential tool for robotics practitioners. RANSAC (Random Sample Consensus) is a widely used technique for plane detection that iteratively evaluates the fitness of planes by sampling three points at a time from a point cloud. In this work, we present an approach that, rather than seeking planes directly, focuses on finding lines by sampling only two points at a time. This leverages the observation that it is more likely to detect lines within the plane than to find the plane itself. To estimate planes from these lines, we perform an additional step that fits a plane for each pair of lines. Experiments conducted on three datasets, two of which are public, demonstrate that our approach outperforms the traditional RANSAC method, achieving better results while requiring fewer iterations. A public repository containing the developed code is also provided.
format Article
id doaj-art-0caf106d7f9c4c50ae7bebea598b2b6e
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-0caf106d7f9c4c50ae7bebea598b2b6e2025-08-24T11:17:20ZengNature PortfolioScientific Reports2045-23222025-08-0115111410.1038/s41598-025-12660-wOptimizing plane detection in point clouds through line samplingJosé María Martínez-Otzeta0Jon Azpiazu1Iñigo Mendialdua2Basilio Sierra3Department of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU)Department of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU)Department of Languages and Information Systems, University of the Basque Country (UPV/EHU)Department of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU)Abstract Plane detection in point clouds is a common step in interpreting environments within robotics. Mobile robotic platforms must interact efficiently and safely with their surroundings, which requires capabilities such as detecting walls to avoid collisions and recognizing workbenches for object manipulation. Since these environmental elements typically appear as plane-shaped surfaces, a fast and accurate plane detector is an essential tool for robotics practitioners. RANSAC (Random Sample Consensus) is a widely used technique for plane detection that iteratively evaluates the fitness of planes by sampling three points at a time from a point cloud. In this work, we present an approach that, rather than seeking planes directly, focuses on finding lines by sampling only two points at a time. This leverages the observation that it is more likely to detect lines within the plane than to find the plane itself. To estimate planes from these lines, we perform an additional step that fits a plane for each pair of lines. Experiments conducted on three datasets, two of which are public, demonstrate that our approach outperforms the traditional RANSAC method, achieving better results while requiring fewer iterations. A public repository containing the developed code is also provided.https://doi.org/10.1038/s41598-025-12660-wRandom sample consensusPlane detectionPoint cloud segmentationRobotics
spellingShingle José María Martínez-Otzeta
Jon Azpiazu
Iñigo Mendialdua
Basilio Sierra
Optimizing plane detection in point clouds through line sampling
Scientific Reports
Random sample consensus
Plane detection
Point cloud segmentation
Robotics
title Optimizing plane detection in point clouds through line sampling
title_full Optimizing plane detection in point clouds through line sampling
title_fullStr Optimizing plane detection in point clouds through line sampling
title_full_unstemmed Optimizing plane detection in point clouds through line sampling
title_short Optimizing plane detection in point clouds through line sampling
title_sort optimizing plane detection in point clouds through line sampling
topic Random sample consensus
Plane detection
Point cloud segmentation
Robotics
url https://doi.org/10.1038/s41598-025-12660-w
work_keys_str_mv AT josemariamartinezotzeta optimizingplanedetectioninpointcloudsthroughlinesampling
AT jonazpiazu optimizingplanedetectioninpointcloudsthroughlinesampling
AT inigomendialdua optimizingplanedetectioninpointcloudsthroughlinesampling
AT basiliosierra optimizingplanedetectioninpointcloudsthroughlinesampling