• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

视频地图：一种考虑数字高程模型（DEM）和语义信息的实时正射地理图像。

Video map: A realtime orthographic geo-image considering DEM and semantic information.

作者信息

Zhang Xingguo, Li Xiaodi, Ren Shuai, Liu Mohan, Yang Sen

机构信息

School of Geographic Sciences, Xinyang Normal University, Xinyang, China.

出版信息

PLoS One. 2025 May 14;20(5):e0323669. doi: 10.1371/journal.pone.0323669. eCollection 2025.

DOI:10.1371/journal.pone.0323669
PMID:40367246
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12077791/
Abstract

Aiming at the problem that it is difficult to accurately calibrate massive Pan-Tilt-Zoom Camera (PTZ) cameras on telecommunication tower and the visualization effect of orthographic geo-image is poor, this paper proposes a new method of realtime orthographic geo-image generating, which is considering Digital Elevation Model (DEM) and semantic information (ROGI-DS). First, through integrating tower cameras with 3D GIS, a camera calibration method based on view fitting (3D GIS-GeoC) is designed. Then, using the trained semantic segmentation model (TCSM), the sky area can automatically be identified and removed. Finally, based on the results of camera calibration and viewshed analysis, and the orthographic geo-image are generated. The results show that: (1) 3D GIS-GeoC method outperforms the traditional Perspective-n-Point (PnP) algorithm;(2) The tower camera semantic segmentation model (TCSM) achieves an accuracy of 96.7%; (3) ROGI-DS method improves the accuracy and visualization of orthographic geo-image under different terrain constraints, and can be used real-time monitoring of natural resources and emergency reliefs.

摘要

针对电信塔上大量云台摄像机难以精确校准以及正射地理影像可视化效果不佳的问题，本文提出了一种考虑数字高程模型（DEM）和语义信息的实时正射地理影像生成新方法（ROGI-DS）。首先，通过将塔上摄像机与3D GIS集成，设计了一种基于视图拟合的摄像机校准方法（3D GIS-GeoC）。然后，利用训练好的语义分割模型（TCSM），自动识别并去除天空区域。最后，基于摄像机校准和视域分析结果，生成正射地理影像。结果表明：（1）3D GIS-GeoC方法优于传统的透视n点（PnP）算法；（2）塔摄像机语义分割模型（TCSM）的准确率达到96.7%；（3）ROGI-DS方法在不同地形约束下提高了正射地理影像的精度和可视化效果，可用于自然资源实时监测和应急救援。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/078b90435fcf/pone.0323669.g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/c9d0f61056b0/pone.0323669.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/2b9f77cbc48c/pone.0323669.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/294c6495438c/pone.0323669.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/33763b61df17/pone.0323669.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/15a72515d46b/pone.0323669.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/7fc3f8097f34/pone.0323669.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/45b5f9e08a2c/pone.0323669.g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/2d5e569c716e/pone.0323669.g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/f73e0c5ecdae/pone.0323669.g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/631be7d4a8e3/pone.0323669.g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/b30d16ea848f/pone.0323669.g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/bcd9a6247fa8/pone.0323669.g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/83c7e551980a/pone.0323669.g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/3a26922c03ce/pone.0323669.g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/078b90435fcf/pone.0323669.g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/c9d0f61056b0/pone.0323669.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/2b9f77cbc48c/pone.0323669.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/294c6495438c/pone.0323669.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/33763b61df17/pone.0323669.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/15a72515d46b/pone.0323669.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/7fc3f8097f34/pone.0323669.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/45b5f9e08a2c/pone.0323669.g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/2d5e569c716e/pone.0323669.g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/f73e0c5ecdae/pone.0323669.g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/631be7d4a8e3/pone.0323669.g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/b30d16ea848f/pone.0323669.g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/bcd9a6247fa8/pone.0323669.g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/83c7e551980a/pone.0323669.g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/3a26922c03ce/pone.0323669.g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bbde/12077791/078b90435fcf/pone.0323669.g015.jpg

相似文献

1
Video map: A realtime orthographic geo-image considering DEM and semantic information.视频地图：一种考虑数字高程模型（DEM）和语义信息的实时正射地理图像。
PLoS One. 2025 May 14;20(5):e0323669. doi: 10.1371/journal.pone.0323669. eCollection 2025.
2
Dynamic calibration of pan-tilt-zoom cameras for traffic monitoring.用于交通监控的云台变焦摄像机的动态校准。
IEEE Trans Syst Man Cybern B Cybern. 2006 Oct;36(5):1091-103. doi: 10.1109/tsmcb.2006.872271.
3
Keeping a pan-tilt-zoom camera calibrated.保持云台变焦摄像机的校准。
IEEE Trans Pattern Anal Mach Intell. 2013 Aug;35(8):1994-2007. doi: 10.1109/TPAMI.2012.250.
4
Multiresolution and wide-scope depth estimation using a dual-PTZ-camera system.使用双云台摄像机系统进行多分辨率和宽范围深度估计。
IEEE Trans Image Process. 2009 Mar;18(3):677-82. doi: 10.1109/TIP.2008.2011178.
5
Multi-View AAM Fitting and Construction.多视图主动形状模型拟合与构建
Int J Comput Vis. 2008 Feb 1;76(2):183-204. doi: 10.1007/s11263-007-0050-3.
6
3D Static Point Cloud Registration by Estimating Temporal Human Pose at Multiview.基于多视角估计时间人体姿态的 3D 静态点云配准
Sensors (Basel). 2022 Jan 31;22(3):1097. doi: 10.3390/s22031097.
7
Arbitrary viewpoint video synthesis from multiple uncalibrated cameras.基于多个未校准摄像机的任意视角视频合成。
IEEE Trans Syst Man Cybern B Cybern. 2004 Feb;34(1):430-9. doi: 10.1109/tsmcb.2003.817108.
8
A single-camera method for three-dimensional video imaging.一种用于三维视频成像的单相机方法。
J Neurosci Methods. 2002 Oct 15;120(1):65-83. doi: 10.1016/s0165-0270(02)00191-7.
9
A master-slave surveillance system to acquire panoramic and multiscale videos.一种用于获取全景和多尺度视频的主从式监控系统。
ScientificWorldJournal. 2014 Mar 3;2014:491549. doi: 10.1155/2014/491549. eCollection 2014.
10
Calibration by correlation using metric embedding from nonmetric similarities.使用非度量相似性的度量嵌入进行关联校准。
IEEE Trans Pattern Anal Mach Intell. 2013 Oct;35(10):2357-70. doi: 10.1109/TPAMI.2013.34.

本文引用的文献

1
Estimating rainfall intensity based on surveillance audio and deep-learning.基于监测音频和深度学习估算降雨强度。
Environ Sci Ecotechnol. 2024 Jul 8;22:100450. doi: 10.1016/j.ese.2024.100450. eCollection 2024 Nov.
2
The role of complexity for digital twins of cities.城市数字孪生体的复杂性作用。
Nat Comput Sci. 2023 May;3(5):374-381. doi: 10.1038/s43588-023-00431-4. Epub 2023 May 1.
3
Visual Camera Re-Localization From RGB and RGB-D Images Using DSAC.基于 DSAC 的 RGB 和 RGB-D 图像的视觉相机重定位
IEEE Trans Pattern Anal Mach Intell. 2022 Sep;44(9):5847-5865. doi: 10.1109/TPAMI.2021.3070754. Epub 2022 Aug 4.
4
Towards the sustainable development of smart cities through mass video surveillance: A response to the COVID-19 pandemic.通过大规模视频监控实现智慧城市的可持续发展：对COVID-19大流行的应对措施。
Sustain Cities Soc. 2021 Jan;64:102582. doi: 10.1016/j.scs.2020.102582. Epub 2020 Nov 5.
5
Variational Level Set Evolution for Non-Rigid 3D Reconstruction From a Single Depth Camera.基于单深度相机的非刚性三维重建的变分水平集演化
IEEE Trans Pattern Anal Mach Intell. 2021 Aug;43(8):2838-2850. doi: 10.1109/TPAMI.2020.2976065. Epub 2021 Jul 1.
6
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs.DeepLab：基于深度卷积网络、空洞卷积和全连接条件随机场的语义图像分割。
IEEE Trans Pattern Anal Mach Intell. 2018 Apr;40(4):834-848. doi: 10.1109/TPAMI.2017.2699184. Epub 2017 Apr 27.
7
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.更快的 R-CNN：基于区域建议网络的实时目标检测。
IEEE Trans Pattern Anal Mach Intell. 2017 Jun;39(6):1137-1149. doi: 10.1109/TPAMI.2016.2577031. Epub 2016 Jun 6.