.png){kind=icon}
返回
Point cloud semantic segmentation with adaptive spatial structure graph transformer
.png){kind=icon}
OA
AI
DOI：10.1016/j.jag.2024.104105.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With the rapid development of LiDAR and artificial intelligence technologies, 3D point cloud semantic segmentation has become a highlight research topic. This technology is able to significantly enhance the capabilities of building information modeling, navigation and environmental perception. However, current deep learning-based methods primarily rely on voxelization or multi-layer convolution for feature extraction. These methods often face challenges in effectively differentiating between homogeneous objects or structurally adherent targets in complex real-world scenes. To this end, we propose a Graph Transformer point cloud semantic segmentation network (ASGFormer) tailored for structurally adherent objects. Firstly, ASGFormer combines Graph and Transformer to promote global correlation understanding in the graph. Secondly, spatial index and position embedding are constructed based on distance relationships and feature differences. Through a learnable mechanism, the structural weights between points are dynamically adjusted, achieving adaptive spatial structure within the graph. Finally, dummy nodes are introduced to facilitate global information storage and transmission between layers, effectively addressing the issue of information loss at the terminal nodes of the graph. Comprehensive experiments are conducted on the various real-world 3D point cloud datasets, analyzing the effectiveness of proposed ASGFormer through qualitative and quantitative evaluations. ASGFormer outperforms existing approaches with of 91.3% for OA, 78.0% for mAcc, and 72.3% for mIoU on S3DIS dataset. Moreover, ASGFormer achieves 72.8%, 45.5%, 81.6%, 70.1% mIoU on ScanNet, City-Facade, Toronto 3D and Semantic KITTI dataset, respectively. Notably, the proposed method demonstrates effective differentiation of homogeneous structurally adherent objects, further contributing to the intelligent perception and modeling of complex scenes.
Keyword:
Graph transformer
Point cloud
LiDAR
Semantic segmentation
Deep learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.6
论文数:
5.3K
被引数:
2.4W
机构
引用论文
Air Quality and Thermal Comfort in an Office with Underfloor, Mixing and Displacement Ventilation
PREAI
分享收藏
分享收藏Geometric attentional dynamic graph convolutional neural networks for point cloud analysis用于点云分析的几何注意动态图卷积神经网络.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容