Multi-prototype Relational Network for Few-Shot ALS Point Cloud Semantic Segmentation by Transferring Knowledge from Photogrammetric Point Clouds

Existing airborne laser scanning (ALS) point cloud semantic segmentation approaches are limited by their overreliances on sufficient point-wise annotations that further confine their generalization ability to new scenes. To overcome these problems, a novel three-stage multi-prototype relational netw...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on geoscience and remote sensing 2024-02, p.1-1
Hauptverfasser:	Dai, Mofan, Xing, Shuai, Xu, Qing, Li, Pengcheng, Pan, Jiechen, Zhang, Guoping, Wang, Hanyun
Format:	Artikel
Sprache:	eng
Schlagworte:	ALS point clouds Feature extraction few-shot learning knowledge transfer meta-learning photogrammetric point clouds Point cloud compression Semantic segmentation Semantics Task analysis Three-dimensional displays Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!