...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>ISPRS Journal of Photogrammetry and Remote Sensing >Learning high-level features by fusing multi-view representation of MLS point clouds for 3D object recognition in road environments
【24h】

Learning high-level features by fusing multi-view representation of MLS point clouds for 3D object recognition in road environments

机译：通过融合在道路环境中的3D对象识别MLS点云的多视图表示来学习高级功能

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Most existing 3D object recognition methods still suffer from low descriptiveness and weak robustness although remarkable progress has made in 3D computer vision. The major challenge lies in effectively mining high-level 3D shape features. This paper presents a high-level feature learning framework for 3D object recognition through fusing multiple 2D representations of point clouds. The framework has two key components: (1) three discriminative low-level 3D shape descriptors for obtaining multi-view 2D representation of 3D point clouds. These descriptors preserve both local and global spatial relationships of points from different perspectives and build a bridge between 3D point clouds and 2D Convolutional Neural Networks (CNN). (2) A two-stage fusion network, which consists of a deep feature learning module and two fusion modules, for extracting and fusing high-level features. The proposed method was tested on three datasets, one of which is Sydney Urban Objects dataset and the other two were acquired by a mobile laser scanning (MLS) system along urban roads. The results obtained from comprehensive experiments demonstrated that our method is superior to the state-of-the-art methods in descriptiveness, robustness and efficiency. Our method achieves high recognition rates of 94.6%, 93.1% and 74.9% on the above three datasets, respectively.
机译：大多数现有的3D对象识别方法仍然遭受低描述性和弱稳健性，尽管在3D计算机视觉中取得了显着进展。主要挑战在于有效采矿高级别的3D形状。本文通过融合点云的多个2D表示，为3D对象识别提供了一个高级特征学习框架。该框架有两个关键组件：（1）三个判别低级3D形状描述符，用于获得3D点云的多视图2D表示。这些描述符从不同的观点保留来自不同观点的本地和全局空间关系，并在3D点云和2D卷积神经网络（CNN）之间构建桥梁。 （2）两阶段融合网络，由深度特色学习模块和两个融合模块组成，用于提取和融合高级功能。所提出的方法在三个数据集上进行了测试，其中一个是悉尼城市物体数据集，另外两个是由城市道路的移动激光扫描（MLS）系统获取。从综合实验中获得的结果表明，我们的方法优于描述性，鲁棒性和效率的最先进的方法。我们的方法分别在上述三个数据集中实现了94.6％，93.1％和74.9％的高度识别率。

著录项

  • 来源
  • 作者

    Luo Zhipeng; Li Jonathan; Xiao Zhenlong; Mou Z. Geroge; Cai Xiaojie; Wang Cheng;

  • 作者单位

    Xiamen Univ Sch Informat Sci & Engn Fujian Key Lab Sensing & Comp Smart Cities 422 Siming Rd South Xiamen 361005 FJ Peoples R China;

    Xiamen Univ Sch Informat Sci & Engn Fujian Key Lab Sensing & Comp Smart Cities 422 Siming Rd South Xiamen 361005 FJ Peoples R China|Univ Waterloo Dept Geog 200 Univ Ave West Waterloo ON N2L 3G1 Canada|Univ Waterloo Dept Environm Management & Syst Design Engn 200 Univ Ave West Waterloo ON N2L 3G1 Canada;

    Xiamen Univ Sch Informat Sci & Engn Fujian Key Lab Sensing & Comp Smart Cities 422 Siming Rd South Xiamen 361005 FJ Peoples R China;

    Xiamen Univ Sch Informat Sci & Engn Fujian Key Lab Sensing & Comp Smart Cities 422 Siming Rd South Xiamen 361005 FJ Peoples R China;

    Xiamen Univ Sch Informat Sci & Engn Fujian Key Lab Sensing & Comp Smart Cities 422 Siming Rd South Xiamen 361005 FJ Peoples R China;

    Xiamen Univ Sch Informat Sci & Engn Fujian Key Lab Sensing & Comp Smart Cities 422 Siming Rd South Xiamen 361005 FJ Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Convolutional neural networks; 3D object recognition; MLS point clouds; Multi-view representation; Two-stage fusion network;

    机译：卷积神经网络;3D对象识别;MLS点云;多视图表示;两级融合网络;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号