Ground Segmentation for LiDAR Point Clouds in Structured and Unstructured Environments Using a Hybrid Neural–Geometric Approach

• Published in: Technologies (Basel) Vol. 13; no. 4; p. 162
• Main Authors: Santo, Antonio, Heredia, Enrique, Viegas, Carlos, Valiente, David, Gil, Arturo
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.04.2025
• Subjects: Adaptation; Algorithms; annotation procedure; Artificial intelligence; Artificial neural networks; Autonomous cars; autonomous navigation; Datasets; Deep learning; Geospatial data; ground segmentation; Image segmentation; Lidar; LiDAR point clouds; Methods; Morphology; Neural networks; Optical radar; Principal components analysis; Remote sensing; Roving vehicles; Sensors; Space exploration; Sparsity; Spatial data; Terrain models; traversability estimation; Urban environments; Portugal
• ISSN: 2227-7080; 2227-7080
• DOI: 10.3390/technologies13040162

Ground segmentation in LiDAR point clouds is a foundational capability for autonomous systems, enabling safe navigation in applications ranging from urban self-driving vehicles to planetary exploration rovers. Reliably distinguishing traversable surfaces in geometrically irregular or sensor-sparse environments remains a critical challenge. This paper introduces a hybrid framework that synergizes multi-resolution polar discretization with sparse convolutional neural networks (SCNNs) to address these challenges. The method hierarchically partitions point clouds into adaptive sectors, leveraging PCA-derived geometric features and dynamic variance thresholds for robust terrain modeling, while a SCNN resolves ambiguities in data-sparse regions. Evaluated in structured (SemanticKITTI) and unstructured (Rellis-3D) environments, two different versions of the proposed method are studied, including a purely geometric method and a hybrid approach that exploits deep learning techniques. A comparison of the proposed method with its purely geometric version is made for the purpose of highlighting the strengths of each approach. The hybrid approach achieves state-of-the-art performance, attaining an F1-score of 95.4% in urban environments, surpassing the purely geometric (91.4%) and learning-based baselines. Conversely, in unstructured terrains, the geometric variant demonstrates superior metric balance (80.8% F1) compared to the hybrid method (75.8% F1), highlighting context-dependent trade-offs between precision and recall. The framework’s generalization is further validated on custom datasets (UMH-Gardens, Coimbra-Liv), showcasing robustness to sensor variations and environmental complexity. The code and datasets are openly available to facilitate reproducibility.