Evaluation of Plane Detection with RANSAC According to Density of 3D Point Clouds

TL;DR

This paper evaluates how the density of 3D point clouds affects the performance of plane detection using RANSAC, highlighting the impact of point density on detection results.

Contribution

It provides an experimental analysis of RANSAC-based plane detection across different point cloud densities, revealing how density influences detection outcomes.

Findings

Higher point density yields more detected planes.

Detection results vary significantly with parameter changes.

Point density impacts the reliability of plane detection.

Abstract

We have implemented a method that detects planar regions from 3D scan data using Random Sample Consensus (RANSAC) algorithm to address the issue of a trade-off between the scanning speed and the point density of 3D scanning. However, the limitation of the implemented method has not been clear yet. In this paper, we conducted an additional experiment to evaluate the implemented method by changing its parameter and environments in both high and low point density data. As a result, the number of detected planes in high point density data was different from that in low point density data with the same parameter value.