DAPnet: A Double Self-Attention Convolutional Network for Point Cloud Semantic Labeling

Airborne laser scanning (ALS) point clouds have complex structures, and their 3D semantic labeling has been a challenging task. It has three problems: 1) The difficulty of classifying point clouds around boundaries of objects from different classes, 2) the diversity of shapes within the same class,...

Full description

Bibliographic Details

Main Authors:	Li Chen, Weiye Chen, Zewei Xu, Haozhe Huang, Shaowen Wang, Qing Zhu, Haifeng Li
Format:	Artigo
Language:	Inglês
Published:	IEEE 2021-01-01
Series:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:	Airborne laser scanning (ALS) point clouds convolutional neural network (CNN) self-attention semantic labeling
Online Access:	https://ieeexplore.ieee.org/document/9540373/
Tags:	Add Tag No Tags, Be the first to tag this record!