...
  • 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 >Crowd-sourced pictures geo-localization method based on street view images and 3D reconstruction
【24h】

Crowd-sourced pictures geo-localization method based on street view images and 3D reconstruction

机译：基于街景图像和3D重建的人群源图片地理定位方法

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

People are increasingly becoming accustomed to taking photos of everyday life in modern cities and uploading them on major photo-sharing social media sites. These sites contain numerous pictures, but some have incomplete or blurred location information. The geo-localization of crowd-sourced pictures enriches the information contained therein, and is applicable to activities such as urban construction, urban landscape analysis, and crime tracking. However, geo-localization faces huge technical challenges. This paper proposes a method for large-scale geo-localization of crowd-sourced pictures. Our approach uses structured, organized Street View images as a reference dataset and employs a three-step strategy of coarse geo-localization by image retrieval, selecting reliable matches by image registration, and fine geo-localization by 3D reconstruction to attach geographic tags to pictures from unidentified sources. In study area, 3D reconstruction based on close-range photogrammetry is used to restore the 3D geographical information of the crowd-sourced pictures, resulting in the proposed method improving the median error from 256.7 m to 69.0 m, and the percentage of the geo-localized query pictures under a 50 m error from 17.2% to 43.2% compared with the previous method. Another discovery using the proposed method is that, in respect of the causes of reconstruction error, closer distances from the cameras to the main objects in query pictures tend to produce lower errors and the component of error parallel to the road makes a more significant contribution to the Total Error. The proposed method is not limited to small areas, and could be expanded to cities and larger areas owing to its flexible parameters. (C) 2018 Published by Elsevier B.V.
机译：人们越来越习惯于在现代城市中拍摄日常生活的照片，并将其上传到主要的照片共享社交媒体网站上。这些站点包含许多图片，但有些站点的位置信息不完整或模糊。众包图片的地理定位丰富了其中包含的信息，适用于诸如城市建设，城市景观分析和犯罪追踪等活动。但是，地理本地化面临着巨大的技术挑战。本文提出了一种大规模的人群来源图片地理定位方法。我们的方法使用结构化，组织化的街景图像作为参考数据集，并采用了三步策略：通过图像检索进行粗略的地理定位，通过图像配准选择可靠的匹配项以及通过3D重建将图像进行地理定位以将地理标签附加到图片上来自不明来源。在研究区域中，基于近距离摄影测量的3D重建被用于恢复众包图片的3D地理信息，从而使该方法将中位误差从256.7 m提高到69.0 m，并将地理误差的百分比与以前的方法相比，在50 m误差下的本地化查询图片从17.2％到43.2％。使用提出的方法的另一个发现是，就重建误差的原因而言，从摄像机到查询图片中主要对象的距离越近，产生的误差就越小，并且与道路平行的误差分量对误差的贡献更大。总误差。所提出的方法不限于小区域，并且由于其灵活的参数可以扩展到城市和更大的区域。 （C）2018由Elsevier B.V.发布

著录项

  • 来源
  • 作者

    Cheng Liang; Yuan Yi; Xia Nan; Chen Song; Chen Yanming; Yang Kang; Ma Lei; Li Manchun;

  • 作者单位

    Nanjing Univ, Collaborat Innovat Ctr South Sea Studies, Nanjing, Jiangsu, Peoples R China;

    Nanjing Univ, Jiangsu Prov Key Lab Geog Informat Sci & Technol, Nanjing, Jiangsu, Peoples R China;

    Nanjing Univ, Jiangsu Prov Key Lab Geog Informat Sci & Technol, Nanjing, Jiangsu, Peoples R China;

    Nanjing Univ, Jiangsu Prov Key Lab Geog Informat Sci & Technol, Nanjing, Jiangsu, Peoples R China;

    Nanjing Univ, Collaborat Innovat Ctr South Sea Studies, Nanjing, Jiangsu, Peoples R China;

    Nanjing Univ, Collaborat Innovat Ctr South Sea Studies, Nanjing, Jiangsu, Peoples R China;

    Nanjing Univ, Collaborat Innovat Ctr South Sea Studies, Nanjing, Jiangsu, Peoples R China;

    Nanjing Univ, Collaborat Innovat Ctr South Sea Studies, Nanjing, Jiangsu, Peoples R China;

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

    Street view images; Geo-localization; Image retrieval; 3D reconstruction; Accuracy analysis;

    机译：街景图像地理定位图像检索3D重建精度分析;

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