曲线和多头移动通道自注意力机制融合的点云语义分割

打开文本图片集

中图分类号： TP391.4 （20 文献标志码：A

DOI：10. 13338/j. issn.1674-649x.2025.02.004

Curve and multi-head shifted channel self-attention mechanism fusion for point cloud semantic segmentation

LU Jian ，ZHENG Yufei，LIANG Youcheng，LUO Liguo ，SU Shengbin （School of Electronics and Information，Xi'an Polytechnic University，Xi'an 710o48，China）

Abstract In order to solve the problem of inadequate extraction of local spatial structure and deep-level point cloud features in point cloud semantic segmentation. We proposed a 3D point cloud semantic segmentation network based on the fusion of curve and multi-head shifted channel self-attention mechanism.First，the curve module performed grouping and walking operations on the point cloud through a dynamic walking strategy to obtain the correlation and geometric correlation between remote points. Secondly，the multi-head shifted channel self-attention mechanism module was introduced to segment the channels by sliding windows and construct multi-head selfatention aggregated channel features to capture the deep semantic information of the point cloud. Finally，the reverse botleneck module was proposed to deepen the hierarchy of the network by embedding low-dimensional MLP into the interpolation structure to enhance the expression of the features，and at the same time to effectively improve to the gradient vanishing and overfitting problems.The experimental results show that the accuracy of this paper's model is 90.1% and the mean intersection over union is 68.6% on the S3DIS Area 5 dataset;the mean intersection O- ver union used for testing in ScanNet is 70.9% ：

Keywords curve module;multi-head shifted channel self-attention mechanism； point cloud; semantic segmentation;deep learning

0引言

近年来，随着传感器技术的发展，点云数据能够高效表征原始物体的几何信息[]，被广泛运用于机器人[2]、自动驾驶[3]、增强现实[4]等技术领域。（剩余16569字）