Fast 3D site reconstruction using multichannel dynamic and static object separation

被引:0
|
作者
Ma, Shufan [1 ]
Fang, Qi [1 ]
Zhou, Heyang [2 ]
Yin, Yihang [1 ]
Ye, Fangda [1 ]
机构
[1] Cent South Univ, Sch Civil Engn, Changsha 410004, Peoples R China
[2] BlueLogic LLC, Sheridan, WY 82801 USA
基金
中国国家自然科学基金;
关键词
3D reconstruction; 3D positioning; Computer vision; Monocular cameras; Object segmentation; MOTION;
D O I
10.1016/j.autcon.2024.105807
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Three-dimensional (3D) models, characterized by their visualization, accuracy, and interactive information presentation, effectively facilitate collaboration and optimize management throughout the construction process. However, existing 3D reconstruction methods frequently fail to simultaneously satisfy the requirements for onsite applicability and fast performance. To address this challenge, this paper proposes a monocular camera- based 3D reconstruction method designed for onsite applicability and introduces dynamic-static separation to reduce the computational burden for faster processing. This approach enables the preestablishment of 3D models for static and dynamic objects. The positioning, pose, and orientation information of objects can be quickly integrated from multiple channels for fast 3D site reconstruction. Experimental results demonstrate that target objects can be identified across multiple channels and quickly integrated into 3D models. This paper offers both theoretical and practical contributions by enabling 3D reconstruction of construction sites using monocular cameras, which enhances project safety management and supports the implementation of digital twins.
引用
收藏
页数:18
相关论文
共 50 条
  • [11] Object DGCNN: 3D Object Detection using Dynamic Graphs
    Wang, Yue
    Solomon, Justin
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [12] Static-Map and Dynamic Object Reconstruction in Outdoor Scenes Using 3-D Motion Segmentation
    Jiang, Cansen
    Paudel, Danda Pani
    Fougerolle, Yohan
    Fofi, David
    Demonceaux, Cedric
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2016, 1 (01) : 324 - 331
  • [13] Automated Reconstruction of 3D Object
    Ravas, Rudolf
    Syrova, Livia
    PROCEEDINGS OF 13TH INTERNATIONAL SYMPOSIUM ON MECHATRONICS, 2010, : 31 - 33
  • [14] Separation of Line Drawings Based on Split Faces for 3D Object Reconstruction
    Zou, Changqing
    Yang, Heng
    Liu, Jianzhuang
    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 692 - 699
  • [15] Implementation of 3D Object Reconstruction using Radon Transform
    Sobani, Siti Syazalina Mohd
    Daud, Siti Asmah
    Mahmood, Nasrul Humaimi
    2013 FIRST INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, MODELLING AND SIMULATION (AIMS 2013), 2013, : 284 - 288
  • [16] 3D Object Reconstruction Using Full Pixel Matching
    Yaguchi, Yuichi
    Iseki, Kenta
    Viet, Nguyen Tien
    Oka, Ryuichi
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS, 2009, 5702 : 873 - 880
  • [17] Dense Reconstruction Using 3D Object Shape Priors
    Dame, Amaury
    Prisacariu, Victor A.
    Ren, Carl Y.
    Reid, Ian
    2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 1288 - 1295
  • [18] 3D Object Reconstruction using Stationary RGB Camera
    Junior, Jose G. dos S.
    Lima, Gustavo C. R.
    Pinto, Adam H. M.
    Lima, Joao Paulo S. do M.
    Teichrieb, Veronica
    Quintino, Jonysberg P.
    da Silva, Fabio Q. B.
    Santos, Andre L. M.
    Pinho, Helder
    PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 5, 2022, : 793 - 800
  • [19] Fast Shape-From-Focus method for 3D object reconstruction
    Martisek, Dalibor
    OPTIK, 2018, 169 : 16 - 26
  • [20] A PSO Approach In The 3D Object Reconstruction Using Supershapes
    Remmach, Hassnae
    Sadgal, Mohamed
    Elfazziki, Aziz
    PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON NETWORKING, INFORMATION SYSTEMS & SECURITY (NISS19), 2019,