土木与环境工程学报（中英文）2024，Vol.46Issue(1)：173-181,9.DOI:10.11835/j.issn.2096-6717.2021.141
基于深度学习三维重建技术的建筑施工进度管理自动化系统构建
Collaborative management of construction schedule based on deep learning 3D reconstruction technology
摘要
Abstract
With the increasing complexity of construction project management,more and more automatic and intelligent construction schedule management methods are concerned by the traditional management.However,the existing mainstream methods are limited by high cost and complex use,which are difficult to apply to intricate construction schedule management scenarios.By comparing the characteristics of various kinds of 3D reconstruction technology,this study built a collaborative management system of construction schedule based on deep learning 3D Reconstruction Technology(DLR-P).By collecting the real-time image information of the construction site,the system completes the reconstruction from 2D information to 3D,and realizes the automatic control of the construction progress combined with BIM dynamic model technology.In view of the system,this study conducted a case study in the construction site of a project in Banan District of Chongqing,and analyzed the data in the process of system operation.The results show that the average 3D reconstruction time of construction schedule collaborative management system(DLR-P)based on deep learning is 61 seconds,which can meet the basic schedule management requirements,realize the automatic management of construction schedule,and effectively improve the efficiency.Compared with the existing mode,it has great advantages in the operation cost and convenience.关键词
深度学习/三维重建/施工进度管理/智能建造Key words
deep learning/3D reconstruction/construction schedule management/intelligent construction分类
土木建筑引用本文复制引用
苏阳,毛超,郭鹏飞..基于深度学习三维重建技术的建筑施工进度管理自动化系统构建[J].土木与环境工程学报（中英文）,2024,46(1):173-181,9.基金项目
中央高校基本科研业务费社科专项交叉与应用提升项目(2021CDJSKJC22)Special Cross and Application Improvement Project of Social Sciences for Basic Scientific Research Business Expenses of Central Universities(No.2021CDJSKJC22) （2021CDJSKJC22）
