Ground Segmentation for LiDAR Point Clouds in Structured and Unstructured Environments Using a Hybrid Neural–Geometric Approach
Antonio Santo, Enrique Heredia, Carlos Viegas, David Valiente and Arturo Gil
Technologies  (2025)
Ed. MDPI  ISSN:2227-7080  DOI:10.3390/technologies13040162  BIBTEX:@Article{technologies13040162, AUTHOR = {Santo, Antonio and Heredia, Enrique and Viegas, Carlos and Valiente, David and Gil, Arturo}, TITLE = {Ground Segmentation for LiDAR Point Clouds in Structured and Unstructured Environments Using a Hybrid Neural–Geometric Approach}, JOURNAL = {Technologies}, VOLUME = {13}, YEAR = {2025}, NUMBER = {4}, ARTICLE-NUMBER = {162}, URL = {https://www.mdpi.com/2227-7080/13/4/162}, ISSN = {2227-7080}, ABSTRACT = {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.}, DOI = {10.3390/technologies13040162} }  - Vol. 13 (4)

Resumen:

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.