FEC: Fast Euclidean Clustering for Point Cloud Segmentation

TL;DR

This paper introduces FEC, a fast Euclidean clustering algorithm for point cloud segmentation that is simple, efficient, and significantly faster than traditional methods, suitable for real-time applications.

Contribution

The paper proposes a novel pointwise Euclidean clustering algorithm that is easy to implement and vastly improves segmentation speed over classical methods.

Findings

Achieves two orders of magnitude faster segmentation.

Produces high-quality segmentation results.

Simple implementation with only 40 lines of C++ code.

Abstract

Segmentation from point cloud data is essential in many applications such as remote sensing, mobile robots, or autonomous cars. However, the point clouds captured by the 3D range sensor are commonly sparse and unstructured, challenging efficient segmentation. In this paper, we present a fast solution to point cloud instance segmentation with small computational demands. To this end, we propose a novel fast Euclidean clustering (FEC) algorithm which applies a pointwise scheme over the clusterwise scheme used in existing works. Our approach is conceptually simple, easy to implement (40 lines in C++), and achieves two orders of magnitudes faster against the classical segmentation methods while producing high-quality results.