PDC-Net: Robust point cloud registration using deep cyclic neural network combined with PCA

Liu Dengzhi; Zhang Yu; Luo Lin; Li Jinlong; Gao Xiaorong

首页> 外文期刊>Applied optics >PDC-Net: Robust point cloud registration using deep cyclic neural network combined with PCA

【24h】

PDC-Net: Robust point cloud registration using deep cyclic neural network combined with PCA

机译：PDC-net：使用深循环神经网络与PCA相结合的强大点云注册

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

It is important to improve the registration precision and speed in the process of registration. In order to solve this problem, we proposed a robust point cloud registration method based on deep learning, called PDC-Net, using a principal component analysis based adjustment network that quickly adjusts the initial position between two slices of the point cloud, then using an iterative neural network based on the inverse compositional algorithm to complete the final registration transformation. We compare it on the ModelNet40 dataset with iterative closest point, which is the traditional point cloud registration method, and the learning-based methods including PointNet-LK and deep closest point. The experimental results show that the registration error is not worse with the increase of the initial phase between point clouds, avoiding the algorithm falling into the local optimal solution and enhancing the robustness of registration. (C) 2021 Optical Society of America

机译：在配准过程中，提高配准精度和配准速度至关重要。为了解决这个问题，我们提出了一种基于深度学习的鲁棒点云配准方法，称为PDC网络，使用基于主成分分析的调整网络快速调整点云两片之间的初始位置，然后使用基于逆合成算法的迭代神经网络完成最终的配准变换。我们在ModelNet40数据集上比较了迭代最近点法（传统的点云配准方法）和基于学习的点网LK和深度最近点法。实验结果表明，随着点云间初始相位的增大，配准误差不会变差，避免了算法陷入局部最优解，增强了配准的鲁棒性。（2021）美国光学学会

著录项

来源
《Applied optics》 |2021年第11期|共8页
作者
Liu Dengzhi; Zhang Yu; Luo Lin; Li Jinlong; Gao Xiaorong;
展开▼
作者单位

Southwest Jiaotong Univ Sch Phys Sci &

Technol Chengdu 610031 Peoples R China;

Southwest Jiaotong Univ Sch Phys Sci &

Technol Chengdu 610031 Peoples R China;

Southwest Jiaotong Univ Sch Phys Sci &

Technol Chengdu 610031 Peoples R China;

Southwest Jiaotong Univ Sch Phys Sci &

Technol Chengdu 610031 Peoples R China;

Southwest Jiaotong Univ Sch Phys Sci &

Technol Chengdu 610031 Peoples R China;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类应用;
关键词

相似文献

外文文献
中文文献
专利

1. Predicted Robustness as QoS for Deep Neural Network Models [J] . Yue-Huan Wang, Ze-Nan Li, Jing-Wei Xu, 计算机科学技术学报（英文版） . 2020,第005期
2. Assessing the Forecasting of Comprehensive Loss Incurred by Typhoons:A Combined PCA and BP Neural Network Model [J] . Shuai Yuan, Guizhi Wang, Jibo Chen, 人工智能杂志(英文) . 2019,第002期
3. CorsNet: 3D Point Cloud Registration by Deep Neural Network [J] . Kurobe Akiyoshi, Sekikawa Yusuke, Ishikawa Kohta, IEEE Robotics and Automation Letters . 2020,第3期

机译：Corsnet：深度神经网络的3D点云注册
4. Robust Binaural Localization of a Target Sound Source by Combining Spectral Source Models and Deep Neural Networks [J] . Ning Ma, Jose A. Gonzalez, Guy J. Brown Audio, Speech, and Language Processing, IEEE/ACM Transactions on . 2018,第11期

机译：结合频谱源模型和深层神经网络对目标声源进行稳健的双耳本地化
5. Rigid medical image registration using PCA neural network [J] . Lifeng Shang, Jian Cheng Lv, Zhang Yi Neurocomputing . 2006,第13a15期

机译：使用PCA神经网络进行刚性医学图像配准
6. Two-Dimensional PCA Combined with PCA for Neural Network Based Image Registration [C] . Anbang Xu, Xin Jin, Ping Guo Advances in Natural Computation pt.2; Lecture Notes in Computer Science; 4222 . 2006

机译：二维PCA与PCA结合用于基于神经网络的图像配准
7. Privacy and Robustness of Deep Neural Networks [D] . Li, Bai. 2021

机译：深度神经网络的隐私和鲁棒性
8. Accurate and robust segmentation of neuroanatomy in T1‐weighted MRI by combining spatial priors with deep convolutional neural networks [O] . Philip Novosad, Vladimir Fonov, D. Louis Collins, 2020

机译：通过将空间先验与深度卷积神经网络相结合对T1加权MRI中的神经解剖结构进行准确而鲁棒的分割
9. A New Cost Function Combining Deep Neural Networks (DNNs) and l2,1-Norm with Extraction of Robust Facial and Superpixels Features in Age Estimation [O] . Arafat Abu Mallouh, Zakariya Qawaqneh, Buket Barkana 2018

机译：一种新的成本函数，将深度神经网络（DNN）和L2,1-NUM与鲁棒面部和超像素提取相结合的年龄估计
10. Robust Global Image Registration Based on a Hybrid Algorithm Combining Fourier and Spatial Domain Techniques. [R] . C. Seanor J. Murray-Krezan P. J. McNicholl P. N. Crabtree 2012

机译：基于傅立叶和空间域技术的混合算法的鲁棒全局图像配准。

PDC-Net: Robust point cloud registration using deep cyclic neural network combined with PCA

摘要

著录项

相似文献

相关主题

期刊订阅