计算机工程与应用 ›› 2023, Vol. 59 ›› Issue (24): 259-267.DOI: 10.3778/j.issn.1002-8331.2305-0381

• 图形图像处理 • 上一篇    下一篇

分组自注意力机制的多层级三维点云分类方法

何春秀,荆现文,何永宁   

  1. 1.湖北师范大学 城市与环境学院,湖北 黄石 435002
    2.广西壮族自治区自然资源信息中心,南宁 530021
  • 出版日期:2023-12-15 发布日期:2023-12-15

Multilayer 3D Point Cloud Classification Method Based on Group Self-Attention Mechanism

HE Chunxiu, JING Xianwen, HE Yongning   

  1. 1.College of Urban and Environmental Sciences, Hubei Normal University, Huangshi, Hubei 435002, China
    2.Guangxi Zhuang Autonomous Region Natural Resources Information Center, Nanning 530021, China
  • Online:2023-12-15 Published:2023-12-15

摘要: 针对大规模城市场景点云数据体量大、噪声多等导致的点云分类模型难以训练、模型分类准确率低等问题,设计了一种多层级分组自注意力机制的点云分类模型。该模型在数据采样阶段,设计了一种自适应随机采样算法,可以有效解决模型因点云数据量庞大而加载困难的问题;将采样输入的点云数据划分为三个层级,分层级可以扩大点云特征数据的覆盖范围,三个层级分别将点云数据分为16、9、4组,分组可以减少自注意力机制的计算复杂度;进入一个跳跃连接模块,将丢失的低维度特征信息重新利用,从而更好地提高模型分类精度。在SensatUrban数据集上进行实验,结果表明,采样算法相较于最远点采样算法在mIoU指标上提升了0.43个百分点,该模型比同样采用自注意力机制的PCT模型以及经典的PointNet++模型在mIoU指标上分别提升了3.12、8.17个百分点。

关键词: 计算机视觉, 三维图像处理, 点云分割, 随机采样, 自注意力机制

Abstract: In response to the problems of difficulty in training point cloud classification models and low classification accuracy caused by the large volume and high noise of point cloud data in large-scale urban scenes, this paper proposes a multi-level point cloud classification method with a group self attention mechanism. In the data sampling stage, an adaptive random sampling algorithm is designed to effectively solve the problem of model loading difficulties due to the large amount of point cloud data. Then, the sampled input point cloud data is divided into three levels, which can expand the coverage of point cloud feature data. The three levels divide the point cloud data into 16, 9, and 4 groups, which can reduce the computational complexity of the self attention mechanism. Finally, entering a skip connection module to reuse the lost low dimensional feature information, thereby better improving the accuracy of model classification. Experiments are conducted on the SensatUrban dataset, and the results show that the sampling algorithm proposed in this paper improves the mIoU metric by 0.43 percentage points compared to the farthest point sampling algorithm. The model proposed in this paper improves the mIoU metric by 3.12 and 8.17 percentage points, respectively, compared to the PCT model that also uses self attention mechanism and the classic PointNet++ model.

Key words: computer vision, three-dimensional image processing, point cloud segmentation, random sampling, self attention mechanism