FEC: Fast Euclidean Clustering for Point Cloud Segmentation
This addresses the need for fast and computationally efficient point cloud segmentation in applications like autonomous cars and mobile robots, though it appears incremental as it builds on existing Euclidean clustering approaches.
The paper tackles the problem of efficient instance segmentation in sparse, unstructured point clouds by proposing a fast Euclidean clustering (FEC) algorithm that uses a pointwise scheme instead of clusterwise schemes. The result is a method that is two orders of magnitude faster than classical methods while maintaining high-quality segmentation.
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.