Polylidar3D -- Fast Polygon Extraction from 3D Data

TL;DR

Polylidar3D is a fast, versatile algorithm for extracting non-convex polygons from various types of 3D point cloud data, enabling efficient flat surface modeling for applications like mapping and localization.

Contribution

The paper introduces Polylidar3D, a novel non-convex polygon extraction method that is fast, adaptable to different data formats, and leverages multi-threading and GPU acceleration.

Findings

Demonstrates high speed and accuracy across diverse real-world datasets.

Outperforms existing methods in planar segmentation benchmarks.

Effective in indoor, outdoor, and aerial mapping scenarios.

Abstract

Flat surfaces captured by 3D point clouds are often used for localization, mapping, and modeling. Dense point cloud processing has high computation and memory costs making low-dimensional representations of flat surfaces such as polygons desirable. We present Polylidar3D, a non-convex polygon extraction algorithm which takes as input unorganized 3D point clouds (e.g., LiDAR data), organized point clouds (e.g., range images), or user-provided meshes. Non-convex polygons represent flat surfaces in an environment with interior cutouts representing obstacles or holes. The Polylidar3D front-end transforms input data into a half-edge triangular mesh. This representation provides a common level of input data abstraction for subsequent back-end processing. The Polylidar3D back-end is composed of four core algorithms: mesh smoothing, dominant plane normal estimation, planar segment extraction, and finally polygon extraction. Polylidar3D is shown to be quite fast, making use of CPU multi-threading and GPU acceleration when available. We demonstrate Polylidar3D's versatility and speed with real-world datasets including aerial LiDAR point clouds for rooftop mapping, autonomous driving LiDAR point clouds for road surface detection, and RGBD cameras for indoor floor/wall detection. We also evaluate Polylidar3D on a challenging planar segmentation benchmark dataset. Results consistently show excellent speed and accuracy.