Semantic Segmentation of Sparse Array-SAR 3D Point Clouds Using an Enhanced PointNet++ Framework
Applied Sciences · 23.04.2026 · 16 (9) · 4149
DOI: 10.3390/app16094149 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 23.04.2026. Verfasst von Ya Shu und 2 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China.
Abstract (Originalsprache)
The semantic segmentation of sparse array synthetic aperture radar (SAR) 3D point clouds remains a significant challenge. These datasets are characterized by extreme sparsity, irregular distribution, and structural discontinuity, factors that diminish the reliability of local neighborhoods and impede the performance of traditional segmentation algorithms. This study introduces an enhanced PointNet++ framework specifically tailored for the semantic segmentation of sparse array-SAR 3D point clouds. Utilizing PointNet++ as a hierarchical backbone, the proposed architecture incorporates three geometry-oriented modifications: a feature enhancement strategy integrating normalized height, surface normals, and local density; an EdgeConv module positioned at an intermediate abstraction stage to reinforce local geometric modeling; and an FP-Refine module designed to optimize cross-scale feature propagation and recovery within sparse regions. Rather than proposing a fundamentally distinct universal architecture, this research focuses on a task-oriented adaptation of PointNet++ to address the neighborhood instability and structural gaps inherent in sparse array-SAR data. Experimental evaluations using the SARMV3D-1.0 dataset indicate that the proposed method consistently outperforms the PointNet++ baseline, maintaining stable performance across various random seeds with an mIoU between 55% and 58%. Further validation through ablation studies, parameter sensitivity analyses, and perturbation-based robustness assessments confirms the utility of the integrated components. Additionally, cross-dataset experiments on S3DIS and Toronto3D suggest that the framework generalizes effectively to point clouds with varying densities and spatial configurations. The findings demonstrate that the method is particularly successful for categories defined by distinct vertical geometry and structural continuity, such as trees, roofs, and facades, though performance remains limited for weakly structured classes like roads.
Förderung
- the National Natural Science Foundation of China
Zitieren
APA
Shu, Y., Pang, L., & Li, M. (2026). Semantic Segmentation of Sparse Array-SAR 3D Point Clouds Using an Enhanced PointNet++ Framework. Applied Sciences, 16(9), 4149. https://doi.org/10.3390/app16094149
Vancouver
Shu Y, Pang L, Li M. Semantic Segmentation of Sparse Array-SAR 3D Point Clouds Using an Enhanced PointNet++ Framework. Applied Sciences. 2026;16(9):4149. doi:10.3390/app16094149
BibTeX
@article{Shu2026,
author = {Shu, Ya and Pang, Lei and Li, Miao},
title = {Semantic Segmentation of Sparse Array-SAR 3D Point Clouds Using an Enhanced PointNet++ Framework},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {9},
pages = {4149},
doi = {10.3390/app16094149}
}
EUVIMED