A novel GCN-based point cloud classification model robust to pose variances
A novel GCN-based point cloud classification model robust to pose variances
复制标题
DOI：
10.1016/j.patcog.2021.108251
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Huafeng Wang;Yaming Zhang;Wanquan Liu;X. Gu;Xin Jing;Zicheng Liu
中科院分区：
文献类型：
--
作者：
Huafeng Wang;Yaming Zhang;Wanquan Liu;X. Gu;Xin Jing;Zicheng Liu
点云数据可以由许多深度传感器产生，例如光探测和测距（LIDAR）和RGB-D相机，并且它们被广泛用于机器人导航和遥感的广泛应用中，以了解环境。因此，对基于三维点云的物体表示和分类的新技术的需求越来越高。由于物体形状的不规则性，基于点云的物体识别是一个非常具有挑战性的任务，特别是点云的姿态变化会给识别带来很多困难。在本文中，我们通过开发一种新的端到端姿态鲁棒图卷积网络来解决基于点云的对象分类中姿态变化的挑战。从技术上讲，我们首先使用球面系统来表示点云，而不是传统的笛卡尔系统，以简化计算和表示。然后构造了一个位姿辅助网络，以估计旋转角度的位姿变化。最后，针对点云的姿态变化构造了一个图卷积网络用于目标分类。实验结果表明，新模型优于现有的方法（如PointNet和PointNet++）的分类任务时进行实验的ModelNet 40和ShapeNetCore数据集与一系列随机旋转的3D点云。具体来说，我们使用Delaunay三角剖分算法在ModelNet 40上获得了73.02%的分类准确率，这远远优于PointNet和PointCNN等最先进的算法。
Point cloud data can be produced by many depth sensors, such as Light Detection and Ranging (LIDAR) and RGB-D cameras, and they are widely used in broad applications of robotic navigation and remote-sensing for the understanding of environment. Hence, new techniques for object representation and classification based on 3D point cloud are becoming increasingly in high demand. Due to the irregularity of the object shape, the point cloud-based object recognition is a very challenging task, especially the pose variances of a point cloud will impose many difficulties. In this paper, we tackle the challenge of pose variances in object classification based on point cloud by developing a novel end-to-end pose robust graph convolutional network. Technically, we first represent the point cloud using the spherical system instead of the traditional Cartesian system for simplicity of computation and representation. Then a pose auxiliary network is constructed with an aim to estimate the pose changes in terms of rotation angles. Finally, a graph convolutional network is constructed for object classification against the pose variations of point cloud. The experimental results show the new model outperforms the existing approaches (such as PointNet and PointNet++) on the classification task when conducting experiments on both the ModelNet40 and the ShapeNetCore dataset with a series of random rotations of a 3D point cloud. Specifically, we obtain 73.02% accuracy for classification task on the ModelNet40 with delaunay triangulation algorithm, which is much better than the state of the art algorithms, such as PointNet and PointCNN.