MLMS-Net:多层次多尺度点云分类网络

薛豆豆 1; 程英蕾 1; 文沛 1; 2; 余旺盛 1; 秦先祥 1

doi:10.7652/xjtuxb202012009

您当前的位置：

首页 >

文章列表页 >

MLMS-Net:多层次多尺度点云分类网络

更新时间：2025-07-09

- MLMS-Net:多层次多尺度点云分类网络
- MLMS-Net: A Point Cloud Classification Network with Multi-Level and Multi-Scale
- 西安交通大学学报 2020年54卷第12期页码：70-78
- 作者机构：
  
  空军工程大学信息与导航学院,西安,710077
- 作者简介：
- 基金信息：
  
  : 2020-06-19。作者简介: 薛豆豆(1996—),男,硕士生;程英蕾(通信作者),女,教授。基金项目: 国家自然科学基金青年科学基金资助项目(61703423);国家自然科学基金资助项目(41601436)
- DOI：10.7652/xjtuxb202012009
  中图分类号： TP237
- 网络首发：2020-12-10，
  
  纸质出版：2020
- 稿件说明：
移动端阅览
薛豆豆 1, 程英蕾 1, 文沛 1, 等. MLMS-Net:多层次多尺度点云分类网络[J]. 西安交通大学学报, 2020,54(12):70-78.

MLMS-Net: A Point Cloud Classification Network with Multi-Level and Multi-Scale[J]. 2020, 54(12): 70-78.
薛豆豆 1, 程英蕾 1, 文沛 1, 等. MLMS-Net:多层次多尺度点云分类网络[J]. 西安交通大学学报, 2020,54(12):70-78. DOI： 10.7652/xjtuxb202012009.

MLMS-Net: A Point Cloud Classification Network with Multi-Level and Multi-Scale[J]. 2020, 54(12): 70-78. DOI： 10.7652/xjtuxb202012009.

摘要

针对传统点云分类网络提取特征较为单一

分类精度较低的问题

提出一种多层次多尺度点云分类网络MLMS-Net。首先使用预处理算法将原始点云分割为小样本

以得到批处理输入

提高训练效率; 然后使用K近邻算法和边缘特征向量分别提取点云的低层次结构特征和边缘特征

通过设置不同邻域值

有效获取上下文信息

通过点内和点间多层次表达获得局部细粒度描述; 接着对两种低层次特征分别构建卷积神经网络

随着网络层次的加深

特征抽象程度越来越高

区分程度也随之增加

从而有效提高准确性; 最后利用后处理模块融合深层特征

完成点云分类任务。使用Vaihingen数据集对MLMS-Net网络进行测试

其分类精度相较单层次网络提高了0.6%～15.9%。

Abstract

A point cloud classification network with multi-level and multi-scale(MLMS-Net)is proposed to improve the problem that the traditional point cloud classification network extracts single-level features and teh classification accuracy is low. First

a preprocessing algorithm is used to segment the original point cloud into small samples to obtain mini-batch and so as to improve training efficiency; Then the K-nearest neighbor algorithm and an edge feature vector are used to extract the low-level structure features and edge features of the point cloud

and the context information is effectively obtained through setting different neighborhood values. Local fine-grained descriptions are obtained through multi-level expression within and between points. Then convolutional neural networks are constructed for two low-level features separately. With the deepening of the network level

the degree of feature abstraction level is higher and higher

and the degree of distinction increases

so as to effectively improve the accuracy; Finally

the post-processing module is used to fuse the deep features

and the point cloud classification task is completed. The Vaihingen data set is used to test the MLMS-Net network

its classification accuracy is improved by 0.6% to 15.9% compared with that of the single-level network.

关键词

Keywords

references

NIEMEYER J, ROTTENSTEINER F, SOERGEL U, et al. Hierarchical higher order crf for the classification of airborne lidar point clouds in urban areas [C]∥23rd International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vienna, Austria: International Society for Photogrammetry and Remote Sensing, 2016: 655-662.

YANG Bisheng, FANG Lina, LI Qingquan, et al. Automated extraction of road markings from mobile lidar point clouds [J]. Photogrammetric Engineering Remote Sensing, 2012, 78(4): 331-338.

DALPONTE M, BRUZZONE L, GIANELLE D. A system for the estimation of single-tree stem diameter and volume using multireturn LIDAR data [J]. IEEE Transactions on Geoscience Remote Sensing, 2011, 49(7): 2479-2490.

YANG Zhishuang, TAN Bo, PEI Huikun, et al. Segmentation and multi-scale convolutional neural network-based classification of airborne laser scanner data[J]. Sensors, 2018, 18(10): 3347-3357.

李晓天, 姜刚, 张玉. 基于改进层次分析的机载LiDAR点云分类 [J]. 甘肃科学学报, 2019, 31(1): 86-91.

LI Xiaotian, JIANG Gang, ZHANG Yu. Classification of airborne LiDAR point cloud based on improved analytic hierarchy process [J]. Journal of Gansu Sciences, 2019, 31(1): 86-91.

HORVAT D, ZALIK B, MONGUS D. Context-dependent detection of non-linearly distributed points for vegetation classification in airborne LiDAR [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 116(6): 1-14.

YANG Zhishuang, JIANG Wanshou, XU Bo, et al. A convolutional neural network-based 3D semantic labeling method for ALS point clouds [J]. Remote Sensing, 2017, 9(9): 936-948.

SU Hang, MAJI S, KALOGERAKIS E, et al. Multi-view convolutional neural networks for 3d shape recognition [C]∥ 2015 IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2015: 945-953.

RIEGLER G, ULUSOY A O, BISCHOF H, et al. OctNetFusion: learning depth fusion from data [C]∥7th International Conference on 3D Vision. Piscataway, NJ, USA: IEEE, 2017: 57-66.

何鄂龙, 王红平, 陈奇, 等. 一种改进的空间上下文点云分类方法 [J]. 测绘学报, 2017, 46(3): 362-370.

HE Elong, WANG Hongping, CHEN Qi, et al. An improved contextual classification method of point cloud [J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(3): 362-370.

ZHOU YIN, TUZEL O. Voxelnet: end-to-end learning for point cloud based 3d object detection [C]∥ 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 4490-4499.

ANANDAKUMAR M, RAMIYA, RAMA R, et al. A super voxel-based spectro-spatial approach for 3D urban point cloud labelling [J]. International Journal of Remote Sensing, 2016, 37(17): 4172-4200.

邵磊, 董广军, 于英, 等. 结合多尺度体素和高阶条件随机场的点云分类 [J]. 计算机辅助设计与图形学学报, 2019, 31(3): 385-392.

SHAO Lei, DONG Guangjun, YU Ying, et al. A point cloud classification method based on multi-scale voxel and higher order random fields [J]. Journal of Computer-Aided Design Computer Graphics, 2019, 31(3): 385-392.

CHARLES R Q, SU HAO, KAICHUN M, et al. PointNet: deep learning on point sets for 3D classification and segmentation [C]∥ 30th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2017: 77-85.

CHARLES R Q, YI Li, SU Hao, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space [C]∥ 31st Annual Conference on Neural Information Processing Systems. New York, USA: Neural Information Processing Systems Foundation, 2017: 5100-5109.

白静, 徐浩钧. MSP-Net: 多尺度点云分类网络 [J]. 计算机辅助设计与图形学学报, 2019, 31(11): 1917-1924.

BAI Jing, XU Haojun. MSP-Net: multi-scale point cloud classification network [J]. Journal of Computer-Aided Design Computer Graphics, 2019, 31(11): 1917-1924.

SIMONOVSKY M, KOMODAKIS N. Dynamic edge-conditioned filters in convolutional neural networks on graphs [C]∥ 30th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2017: 29-38.

WANG Yue, SUN Yongbin, LIU Ziwei, et al. Dynamic graph CNN for learning on point clouds [J]. ACM Transactions on Graphics, 2019, 38(5): 112-124.

FAUVEL M, CHANUSSOT J, BENEDIKTSSON J A, et al. A spatial-spectral kernel-based approach for the classification of remote-sensing images [J]. Pattern Recognition, 2012, 45(1): 381-392.

YOUSEFHUSSIEN M, KELBE D, IENTILUCCI EJ, et al. A multi-scale fully convolutional network for semantic labeling of 3D point clouds [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 143(5): 191-204.

ZHAO Ruibing, PANG Mingyong, WANG Jidong. Classifying airborne lidar point clouds via deep features learned by a multi-scale convolutional neural network [J]. International Journal of Geographical Information Science, 2018, 32(5): 960-979.

WANG Zhen, ZHANG Lliqiang, ZHANG Liang, et al. A deep neural network with spatial pooling(DNNSP)for 3D point cloud classification [J]. IEEE Transactions on Geoence and Remote Sensing, 2018, 56(8): 4594-4604.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

蜉蝣优化双通道网络在齿轮箱故障诊断中的应用

一种适用于混合三端直流输电线路的故障定位方法

采用格拉姆角场-卷积神经网络-时序卷积网络混合模型的锂离子电池健康状态估计

一种基于FPGA的卷积神经网络协处理器设计

一种高分辨率遥感图像视感知目标检测算法