• 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

一种用于动态（4D）多视图立体视觉系统相机网络设计的新方法。

A Novel Approach for Dynamic (4d) Multi-View Stereo System Camera Network Design.

作者信息

Osiński Piotr, Markiewicz Jakub, Nowisz Jarosław, Remiszewski Michał, Rasiński Albert, Sitnik Robert

机构信息

STARS Impresariat Filmowy SA, 8 Józefa Str., 31-056 Cracow, Poland.

Institute of Micromechanics and Photonics, Warsaw University of Technology, 8 Sw. Andrzeja Boboli Str., 02-525 Warsaw, Poland.

出版信息

Sensors (Basel). 2022 Feb 17;22(4):1576. doi: 10.3390/s22041576.

DOI:10.3390/s22041576
PMID:35214477
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8875458/
Abstract

Image network design is a critical factor in image-based 3D shape reconstruction and data processing (especially in the application of combined SfM/MVS methods). This paper aims to present a new approach to designing and planning multi-view imaging networks for dynamic 3D scene reconstruction without preliminary information about object geometry or location. The only constraints are the size of defined measurement volume, the required resolution, and the accuracy of geometric reconstruction. The proposed automatic camera network design method is based on the Monte Carlo algorithm and a set of prediction functions (considering accuracy, density, and completeness of shape reconstruction). This is used to determine the camera positions and orientations and makes it possible to achieve the required completeness of shape, accuracy, and resolution of the final 3D reconstruction. To assess the accuracy and efficiency of the proposed method, tests were carried out on synthetic and real data. For a set of 20 virtual images of rendered spheres, completeness of shape reconstruction was up by 92.3% while maintaining accuracy and resolution at the user-specified level. In the case of the real data, the differences between predictions and evaluations for average density were in the range between 33.8% to 45.0%.

摘要

图像网络设计是基于图像的三维形状重建和数据处理中的一个关键因素（特别是在联合结构光运动/多视图立体视觉方法的应用中）。本文旨在提出一种新的方法，用于设计和规划多视图成像网络，以实现动态三维场景重建，而无需关于物体几何形状或位置的初步信息。唯一的限制是定义的测量体积的大小、所需的分辨率以及几何重建的精度。所提出的自动相机网络设计方法基于蒙特卡罗算法和一组预测函数（考虑形状重建的精度、密度和完整性）。这用于确定相机的位置和方向，并使得能够实现最终三维重建所需的形状完整性、精度和分辨率。为了评估所提方法的准确性和效率，对合成数据和真实数据进行了测试。对于一组20个渲染球体的虚拟图像，形状重建的完整性提高了92.3%，同时将精度和分辨率保持在用户指定的水平。在真实数据的情况下，平均密度的预测值与评估值之间的差异在33.8%至45.0%的范围内。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/c8064facc536/sensors-22-01576-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/668a51f9a5fd/sensors-22-01576-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/0332210e2921/sensors-22-01576-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/d32194f46528/sensors-22-01576-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/6258dc528084/sensors-22-01576-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/394be90825e0/sensors-22-01576-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/9b402bd37244/sensors-22-01576-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/087221da2fa8/sensors-22-01576-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/4c8fcdad2231/sensors-22-01576-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/31ff7f232cd9/sensors-22-01576-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/26304d17b966/sensors-22-01576-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/2e18aee37dcc/sensors-22-01576-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/c766d491198e/sensors-22-01576-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/74852728a977/sensors-22-01576-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/f950549c3bb8/sensors-22-01576-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/fdc6e85db6ba/sensors-22-01576-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/207b643aba4f/sensors-22-01576-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/d86dcff18cc1/sensors-22-01576-g017a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/a1ac5ceff030/sensors-22-01576-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/48dfacf9ed26/sensors-22-01576-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/9292ea27f6bd/sensors-22-01576-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/c8064facc536/sensors-22-01576-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/668a51f9a5fd/sensors-22-01576-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/0332210e2921/sensors-22-01576-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/d32194f46528/sensors-22-01576-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/6258dc528084/sensors-22-01576-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/394be90825e0/sensors-22-01576-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/9b402bd37244/sensors-22-01576-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/087221da2fa8/sensors-22-01576-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/4c8fcdad2231/sensors-22-01576-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/31ff7f232cd9/sensors-22-01576-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/26304d17b966/sensors-22-01576-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/2e18aee37dcc/sensors-22-01576-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/c766d491198e/sensors-22-01576-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/74852728a977/sensors-22-01576-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/f950549c3bb8/sensors-22-01576-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/fdc6e85db6ba/sensors-22-01576-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/207b643aba4f/sensors-22-01576-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/d86dcff18cc1/sensors-22-01576-g017a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/a1ac5ceff030/sensors-22-01576-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/48dfacf9ed26/sensors-22-01576-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/9292ea27f6bd/sensors-22-01576-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5e05/8875458/c8064facc536/sensors-22-01576-g021.jpg

相似文献

1
A Novel Approach for Dynamic (4d) Multi-View Stereo System Camera Network Design.一种用于动态（4D）多视图立体视觉系统相机网络设计的新方法。
Sensors (Basel). 2022 Feb 17;22(4):1576. doi: 10.3390/s22041576.
2
Scale-Aware Multi-View Reconstruction Using an Active Triple-Camera System.使用主动式三相机系统的尺度感知多视图重建
Sensors (Basel). 2020 Nov 25;20(23):6726. doi: 10.3390/s20236726.
3
SLAM-based dense surface reconstruction in monocular Minimally Invasive Surgery and its application to Augmented Reality.基于 SLAM 的单目微创手术中密集表面重建及其在增强现实中的应用。
Comput Methods Programs Biomed. 2018 May;158:135-146. doi: 10.1016/j.cmpb.2018.02.006. Epub 2018 Feb 8.
4
MVS-T: A Coarse-to-Fine Multi-View Stereo Network with Transformer for Low-Resolution Images 3D Reconstruction.MVS-T：一种用于低分辨率图像3D重建的基于Transformer的由粗到精多视图立体网络。
Sensors (Basel). 2022 Oct 9;22(19):7659. doi: 10.3390/s22197659.
5
3D Reconstruction of Space Objects from Multi-Views by a Visible Sensor.利用可见传感器从多视图进行空间物体的三维重建
Sensors (Basel). 2017 Jul 22;17(7):1689. doi: 10.3390/s17071689.
6
Reconstruction method and optimum range of camera-shooting angle for 3D plant modeling using a multi-camera photography system.基于多相机拍摄系统的三维植物建模相机拍摄角度重建方法及最佳范围
Plant Methods. 2020 Aug 31;16:118. doi: 10.1186/s13007-020-00658-6. eCollection 2020.
7
Research on Multi-View 3D Reconstruction Technology Based on SFM.基于结构光运动恢复的多视图三维重建技术研究
Sensors (Basel). 2022 Jun 9;22(12):4366. doi: 10.3390/s22124366.
8
A Super-Resolution and 3D Reconstruction Method Based on OmDF Endoscopic Images.一种基于OmDF内镜图像的超分辨率和三维重建方法。
Sensors (Basel). 2024 Jul 27;24(15):4890. doi: 10.3390/s24154890.
9
Rapid 3D Reconstruction for Image Sequence Acquired from UAV Camera.基于无人机相机采集图像序列的快速三维重建
Sensors (Basel). 2018 Jan 14;18(1):225. doi: 10.3390/s18010225.
10
All-around 3D plant modeling system using multiple images and its composition.使用多幅图像的全方位三维植物建模系统及其构成
Breed Sci. 2022 Mar;72(1):75-84. doi: 10.1270/jsbbs.21068. Epub 2022 Feb 2.

引用本文的文献

1
Automatic Shuttlecock Fall Detection System in or out of a Court in Badminton Games-Challenges, Problems, and Solutions from a Practical Point of View.羽毛球比赛中球场内外自动羽毛球降落检测系统——从实用角度看挑战、问题和解决方案。
Sensors (Basel). 2022 Oct 22;22(21):8098. doi: 10.3390/s22218098.

本文引用的文献

1
Accuracy and Reproducibility of Facial Measurements of Digital Photographs and Wrapped Cone Beam Computed Tomography (CBCT) Photographs.数码照片和曲面体层锥束计算机断层扫描（CBCT）照片面部测量的准确性和可重复性
Diagnostics (Basel). 2021 Apr 23;11(5):757. doi: 10.3390/diagnostics11050757.
2
FlyCap: Markerless Motion Capture Using Multiple Autonomous Flying Cameras.FlyCap：使用多个自主飞行相机的无标记动作捕捉
IEEE Trans Vis Comput Graph. 2018 Aug;24(8):2284-2297. doi: 10.1109/TVCG.2017.2728660. Epub 2017 Jul 18.
3
Optimal Camera Placement for Motion Capture Systems.
运动捕捉系统的最佳相机位置。
IEEE Trans Vis Comput Graph. 2017 Mar;23(3):1209-1221. doi: 10.1109/TVCG.2016.2637334. Epub 2016 Dec 8.
4
Two-stage automated measurement process for high-resolution 3D digitization of unknown objects.用于未知物体高分辨率三维数字化的两阶段自动测量过程。
Appl Opt. 2016 Oct 10;55(29):8162-8170. doi: 10.1364/AO.55.008162.
5
Accurate multiple view 3D reconstruction using patch-based stereo for large-scale scenes.基于补丁的立体视觉的精确多视图 3D 重建用于大规模场景。
IEEE Trans Image Process. 2013 May;22(5):1901-14. doi: 10.1109/TIP.2013.2237921. Epub 2013 Jan 10.