计算机工程

• •    

一种鲁棒的多特征点云分类分割深度神经网络

  

  • 出版日期:2020-12-23 发布日期:2020-12-23

A robust deep neural network for multi-feature point cloud classification and segmentation

  • Online:2020-12-23 Published:2020-12-23

摘要: 点云是一种常用的三维图形表示方式,目前点云的分类和分割是深度学习领域的研究热点。 现有的深度学习方法不能有效地学习点云的局部特征,从而导致较低的分类分割精度和较差的鲁棒 性。为了解决这一问题,提出一种鲁棒的多特征点云分类分割深度神经网络 RMFP-DNN。首先通过自 注意力模块提取点云的局部特征,然后使用 MLP(Multilayer Perceptron, 多层感知机)提取点云的全局 特征,最后通过特征融合将点云的局部特征和全局特征结合来提高分类分割的准确率和鲁棒性。采用 ModelNet40 物体分类数据集和 ShapeNet 部件分割数据集对 RMFP-DNN 进行了训练和测试。结果表明, 和 PointNet、PointNet++和 DGCNN 等方法相比,RMFP-DNN 具有较好的鲁棒性和准确率。

Abstract: A point cloud is one of the common representations of 3D shapes. The classification and segmentation of point clouds is a popular research topic in the field of deep learning. While the existing methods cannot effectively learn the local features of point clouds, resulting in lower classification and segmentation accuracy and poor robustness. we propose a robust deep neural network, RMFP-DNN, for multi-feature point cloud classification and segmentation. RMFP-DNN extracts the local features between points through the self-attention module, uses the multilayer perceptron (MLP) to learn the global feature of points, and finally improves the accuracy and robustness by combining the local features and the point features through feature fusion. We train and test RMFP-DNN using the ModelNet40 dataset for object classification dataset and the ShapeNet dataset for part segmentation. Results show that RMFP-DNN has better accuracy and robustness than PointNet, PointNet++ and DGCNN.