Oriented Point Sampling for Plane Detection in Unorganized Point Clouds

TL;DR

This paper introduces Oriented Point Sampling (OPS), a novel method for detecting planes in unorganized 3D point clouds, outperforming traditional techniques in efficiency and applicability for tasks like segmentation and SLAM.

Contribution

The paper presents OPS, a new plane detection approach that samples points with estimated normals, suitable for unorganized point clouds, and compares it with existing methods on a large dataset.

Findings

OPS outperforms traditional methods in efficiency.

OPS is effective on unorganized point clouds without 2D parametrization.

The method is validated on 10,000 point clouds from SUN RGB-D.

Abstract

Plane detection in 3D point clouds is a crucial pre-processing step for applications such as point cloud segmentation, semantic mapping and SLAM. In contrast to many recent plane detection methods that are only applicable on organized point clouds, our work is targeted to unorganized point clouds that do not permit a 2D parametrization. We compare three methods for detecting planes in point clouds efficiently. One is a novel method proposed in this paper that generates plane hypotheses by sampling from a set of points with estimated normals. We named this method Oriented Point Sampling (OPS) to contrast with more conventional techniques that require the sampling of three unoriented points to generate plane hypotheses. We also implemented an efficient plane detection method based on local sampling of three unoriented points and compared it with OPS and the 3D-KHT algorithm, which is based on octrees, on the detection of planes on 10,000 point clouds from the SUN RGB-D dataset.