Multi-image 3D reconstruction data evaluation

被引:217
作者
Koutsoudis, Anestis [1 ]
Vidmar, Blaz [2 ]
Ioannakis, George [1 ]
Arnaoutoglou, Fotis [1 ]
Pavlidis, George [1 ]
Chamzas, Christodoulos [3 ]
机构
[1] Res Ctr Athena, Multimedia Dept, Inst Language & Speech Proc, Xanthi 67100, Greece
[2] Univ Ljubljana, Fac Civil & Geodet Engn, Ljubljana 1000, Slovenia
[3] Democritus Univ Thrace, Fac Elect & Comp Engn, GR-67100 Xanthi, Greece
关键词
3D range scanning; Structure-From-Motion; Dense multi-view 3D reconstruction; Total station survey; 3D data comparison; Unmanned aerial vehicle;
D O I
10.1016/j.culher.2012.12.003
中图分类号
K85 [文物考古];
学科分类号
0601 ;
摘要
A number of software solutions based on the Structure-From-Motion (SFM) and Dense Multi-View 3D Reconstruction (DMVR) algorithms have been made recently available. They allow the production of high quality 3D models by using unordered image collections that depict a scene or an object from different viewpoints. In this work, we question the quality of the data produced by a commercial SFM-DMVR software. An Ottoman monument located in the region of Xanthi, Greece has been selected as a case study. We attempted to quantify the quality of the SFM-DMVR data in relation to the data produced by a Time-of-Flight terrestrial 3D range scanner. We have implemented a number of comparisons between different parts of the monument in order to assess the mesh deviations and the reconstruction's accuracy. In order to further ensure the validity of our evaluation phase, we performed additional distance measurements between feature points on the monument's surface by using a total station and empirical measurements. The applicability of the SFM-DMVR method was questioned by creating a complete 3D digital replica of the monument. (C) 2013 Elsevier Masson SAS. All rights reserved.
引用
收藏
页码:73 / 79
页数:7
相关论文
共 50 条
[31]   Trajectory triangulation: 3D reconstruction of moving points from a monocular image sequence [J].
Avidan, S ;
Shashua, A .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (04) :348-357
[32]   EFFECTS OF CUBESAT DESIGN PARAMETERS ON IMAGE QUALITY AND FEATURE EXTRACTION FOR 3D RECONSTRUCTION [J].
Stoddard, Jordyn ;
Messinger, David ;
Kerekes, John .
2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2014, :1995-1998
[33]   Improving Computational Efficiency of 3D Point Cloud Reconstruction from Image Sequences [J].
Chang, Chih-Hsiang ;
Kehtarnavaz, Nasser .
2013 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), 2013, :510-513
[34]   Online 3D Edge Reconstruction of Wiry Structures From Monocular Image Sequences [J].
Choi, Hyelim ;
Lee, Minji ;
Kang, Jiseock ;
Lee, Dongjun .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (11) :7479-7486
[35]   RESEARCH ON CLUSTERING MATCHING STRATEGY OF 3D RECONSTRUCTION BASED ON IMAGE FUSION FEATURES [J].
Sun, Tiebo ;
Liu, Jinhao ;
Kan, Jiangming ;
Sui, Tingting ;
Li, Jiang ;
Ji, Miaoxin .
UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN SERIES C-ELECTRICAL ENGINEERING AND COMPUTER SCIENCE, 2020, 82 (03) :87-106
[36]   A 3D Reconstruction Framework from Image Sequences Based on Point and Line Features [J].
Deng, Baosong ;
Yu, Ronghuan ;
Deng, Tieqing ;
Wu, Lingda .
EQUIPMENT MANUFACTURING TECHNOLOGY AND AUTOMATION, PTS 1-3, 2011, 317-319 :962-+
[37]   3D Reconstruction of an Accident Site [J].
Kholodkov, K. I. ;
Gukov, A. A. ;
Scherbakov, V. M. ;
Aleshin, I. M. ;
Gukov, A. A. .
IZVESTIYA ATMOSPHERIC AND OCEANIC PHYSICS, 2024, 60 (08) :963-969
[38]   3D Reconstruction of Space Objects from Multi-Views by a Visible Sensor [J].
Zhang, Haopeng ;
Wei, Quanmao ;
Jiang, Zhiguo .
SENSORS, 2017, 17 (07)
[39]   RepC-MVSNet: A Reparameterized Self-Supervised 3D Reconstruction Algorithm for Wheat 3D Reconstruction [J].
Liu, Hui ;
Xin, Cheng ;
Lai, Mengzhen ;
He, Hangfei ;
Wang, Yongzhao ;
Wang, Mantao ;
Li, Jun .
AGRONOMY-BASEL, 2023, 13 (08)
[40]   Image-based 3D Reconstruction: Neural Networks vs. Multiview Geometry [J].
Schoening, Julius ;
Heidemann, Gunther .
2018 IEEE THIRD INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, APPLICATIONS AND SYSTEMS (IPAS), 2018, :91-97