基于Spider卷积的三维点云分类与分割网络

doi:10.11772/j.issn.1001-9081.2019101879

摘要
图/表
参考文献(18)
相关文章 (15)

全文: PDF (689 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要

针对传统的卷积神经网络（CNN）不能直接处理点云数据，需先将点云数据转换为多视图或者体素化网格，导致过程复杂且点云识别精度低的问题，提出一种新型的点云分类与分割网络Linked-Spider CNN。首先，在Spider CNN基础上通过增加Spider卷积层数以获取点云深层次特征；其次，引入残差网络的思想在每层Spider卷积增加短连接构成残差块；然后，将每层残差块的输出特征进行拼接融合形成点云特征；最后，使用三层全连接层对点云特征进行分类或者利用多层卷积层对点云特征进行分割。在ModelNet40和ShapeNet Parts数据集上将所提网络与PointNet、PointNet++和Spider CNN等网络进行对比实验，实验结果表明，所提网络可以提高点云的分类精度和分割效果，说明该网络具有更快的收敛速度和更强的鲁棒性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王本杰
	农丽萍
	张文辉
	林基明
	王俊义

关键词 ：卷积神经网络, Spider卷积, 点云分类与分割, 残差块, 鲁棒性

Abstract：

The traditional Convolutional Neural Network (CNN) cannot directly process point cloud data, and the point cloud data must be converted into a multi-view or voxelized grid, which leads to a complicated process and low point cloud recognition accuracy. Aiming at the problem, a new point cloud classification and segmentation network called Linked-Spider CNN was proposed. Firstly, the deep features of point cloud were extracted by adding more Spider convolution layers based on Spider CNN. Secondly, by introducing the idea of residual network, short links were added to every Spider convolution layer to form residual blocks. Thirdly, the output features of each layer of residual blocks were spliced and fused to form the point cloud features. Finally, the point cloud features were classified by three-layer fully connected layers or segmented by multiple convolution layers. The proposed network was compared with other networks such as PointNet, PointNet++ and Spider CNN on ModelNet40 and ShapeNet Parts datasets. The experimental results show that the proposed network can improve the classification accuracy and segmentation effect of point clouds, and it has faster convergence speed and stronger robustness.

Key words： Convolutional Neural Network (CNN) Spider convolution point cloud classification and segmentation residual block robustness

收稿日期: 2019-11-04

中图分类号:

TP 391.4

基金资助:

国家自然科学基金资助项目（61966007）；认知无线电与信息处理教育部重点实验室开发基金资助项目（CRKL180201）；广西云计算与大数据协同创新中心项目（1716）；广西无线宽带通信与信号处理重点实验室主任基金资助项目（GXKL06180107,CRKL180106)。

通讯作者: 张文辉(1970—) E-mail: zhangwh@guet.edu.cn

作者简介: 王本杰(1993—)，男，河南南阳人，硕士研究生，主要研究方向：点云识别、深度学习。农丽萍(1985—)，女，广西天等人，讲师，博士研究生，主要研究方向：图信号处理、几何深度学习。张文辉(1970—),女,湖南益阳人，副教授，硕士，主要研究方向：计算机图形学、计算机动画。林基明（1970—），男，四川三台人，教授，博士，主要研究方向：无线通信、移动通信。王俊义（1977—），男，河北邢台人，研究员，博士，主要研究方向：图信号处理、深度学习、无线网络资源管控。

引用本文:

王本杰, 农丽萍, 张文辉, 林基明, 王俊义. 基于Spider卷积的三维点云分类与分割网络[J]. 计算机应用, 2020, 40(6): 1607-1612. WANG Benjie, NONG Liping, ZHANG Wenhui, LIN Jiming, WANG Junyi. 3D point cloud classification and segmentation network based on Spider convolution. Journal of Computer Applications, 2020, 40(6): 1607-1612.

链接本文:

http://www.joca.cn/CN/10.11772/j.issn.1001-9081.2019101879 或 http://www.joca.cn/CN/Y2020/V40/I6/1607

1 JIANGC, LIM B, ZHANGS. Three-dimensional shape measurement using a structured light system with dual projectors [J]. Applied Optics, 2018, 57(14): 3983-3990.
2 HIRONAGAN, KIMURAT, MITSUDOT, et al. Proposal for an accurate TMS-MRI co-registration process via 3D laser scanning [J]. Neuroscience Research, 2019, 144: 30-39.
3 QIC R, LIUW, WUC, et al. Frustum PointNets for 3D object detection from RGB-D data [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 918-927.
4 ZHUY, MOTTAGHIR, KOLVEE, et al. Target-driven visual navigation in indoor scenes using deep reinforcement learning [C]// Proceedings of the 2017 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2017: 3357-3364.
5 ZHANGK, XIONGC, ZHANGW, et al. Environmental features recognition for lower limb prostheses toward predictive walking [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019, 27(3):465-476.
6 XUY, FANT, XUM, et al. SpiderCNN: deep learning on point sets with parameterized convolutional filters [C]// Proceedings of the 2018 European Conference on Computer Vision, LNCS 11212. Cham: Springer, 2018: 90-105.
7 HEK, ZHANGX, RENS, et al. Deep residual learning for image recognition [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778.
8 牛辰庚,刘玉杰,李宗民,等.基于点云数据的三维目标识别和模型分割方法[J].图学学报,2019,40(2):274-281. NIUC G, LIUY J, LIZ M, et al. 3D object recognition and model segmentation based on point cloud data [J]. Journal of Graphics, 2019, 40(2): 274-281.
9 CHENX, MAH, WANJ, et al. Multi-view 3D object detection network for autonomous driving [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6526-6534.
10 KU J, MOZIFIANM, LEE J, et al. Joint 3D proposal generation and object detection from view aggregation [C]// Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway: IEEE, 2018: 1-8.
11 QIC R, SUH, NIEßNERM, et al. Volumetric and multi-view CNNs for object classification on 3D data [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 5648-5656.
12 WUZ, SONGS, KHOSLAA, et al. 3D ShapeNets: a deep representation for volumetric shapes [C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 1912-1920.
13 WANGP, LIUY, GUOY, et al. O-CNN: octree-based convolutional neural networks for 3D shape analysis [J]. ACM Transactions on Graphics, 2017, 36(4): Article No.72.
14 QIC R, SUH, MOK, et al. PointNet: deep learning on point sets for 3D classification and segmentation [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 77-85.
15 QIC R, YIL, SUH, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space [C]// Proceedings of the 31st Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 5099-5108.
16 WANGY, SUNY, LIUZ, et al. Dynamic graph CNN for learning on point clouds [EB/OL]. [2019-03-24]. https://arxiv.org/pdf/1801.07829v1.pdf.
17 LIY, BUR, SUNM, et al. PointCNN: convolution on X-transformed points [C]// Proceedings of the 32nd Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2018: 820-830.
18 XIEZ, CHENJ, PENGB. Point clouds learning with attention-based graph convolution networks [EB/OL]. [2019-05-31].https://arxiv.org/pdf/1905.13445.pdf.