Vision-based real-time process monitoring and problem feedback for productivity-oriented analysis in off-site construction

被引:14
作者
Chen, Xue [1 ]
Wang, Yiheng [2 ]
Wang, Jingwen [3 ]
Bouferguene, Ahmed [4 ]
Al-Hussein, Mohamed [1 ]
机构
[1] Univ Alberta, Dept Civil & Environm Engn, Edmonton, AB, Canada
[2] Huazhong Univ Sci & Technol, Sch Civil Engn & Mech, Dept Construct Management, Wuhan, Hubei, Peoples R China
[3] Guangzhou Univ, Sch Mech & Elect Engn, Guangzhou, Guangdong, Peoples R China
[4] Univ Alberta, Campus St Jean, Edmonton, AB, Canada
基金
加拿大自然科学与工程研究理事会; 中国博士后科学基金;
关键词
Computer vision; Off -site construction; Productivity; Real-time process monitoring; Problem feedback; Video analysis; ON-SITE; TRACKING; RECOGNITION; MANAGEMENT; RESOURCES;
D O I
10.1016/j.autcon.2024.105389
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The widespread adoption of surveillance cameras in work environments has enabled the direct and non-intrusive detection of productivity-related issues in the field of construction. In this research, a process monitoring and problem feedback framework is developed based on closed-circuit television footage and computer vision analysis to achieve real-time visual control of the work process and facilitate data-driven decision-making in offsite construction. To enhance the automation of productivity-related problem recognition, a novel video analysis algorithm is developed to process the inputted video footage and provide feedback with respect to nine productivity issues. The z-score and Exponential Moving Average methods are employed to eliminate detection errors, and the spatial density analysis method is adopted to visually analyze spatial information. The observed performance of the proposed framework demonstrates that it can accurately acquire data from footage and provide process monitoring and problem feedback in real time.
引用
收藏
页数:19
相关论文
共 86 条
[31]   Active Contour-Based Visual Tracking by Integrating Colors, Shapes, and Motions [J].
Hu, Weiming ;
Zhou, Xue ;
Li, Wei ;
Luo, Wenhan ;
Zhang, Xiaoqin ;
Maybank, Stephen .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (05) :1778-1792
[32]  
Inkila K., 2005, Photogrammetric Journal of Finland, V19, P34
[33]   Vision-Based Productivity Monitoring of Tower Crane Operations during Curtain Wall Installation Using a Database-Free Approach [J].
Jeong, Insoo ;
Hwang, Jeongbin ;
Kim, Junghoon ;
Chi, Seokho ;
Hwang, Bon-Gang ;
Kim, Jinwoo .
JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2023, 37 (04)
[34]   A SWOT analysis for promoting off-site construction under the backdrop of China's new urbanisation [J].
Jiang, Rui ;
Mao, Chao ;
Hou, Lei ;
Wu, Chengke ;
Tan, Jiajuan .
JOURNAL OF CLEANER PRODUCTION, 2018, 173 :225-234
[35]  
Jocher G., 2023, YOLO By Ultralytics
[36]   Crack Detection and Segmentation Using Deep Learning with 3D Reality Mesh Model for Quantitative Assessment and Integrated Visualization [J].
Kalfarisi, Rony ;
Wu, Zheng Yi ;
Soh, Ken .
JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2020, 34 (03)
[37]   AI-based risk assessment for construction site disaster preparedness through deep learning-based digital twinning [J].
Kamari, Mirsalar ;
Ham, Youngjib .
AUTOMATION IN CONSTRUCTION, 2022, 134
[38]   Classification and analysis of deep learning applications in construction: A systematic literature review [J].
Khallaf, Rana ;
Khallaf, Mohamed .
AUTOMATION IN CONSTRUCTION, 2021, 129
[39]   Vision-based nonintrusive context documentation for earthmoving productivity simulation [J].
Kim, Hongjo ;
Ham, Youngjib ;
Kim, Wontae ;
Park, Somin ;
Kim, Hyoungkwan .
AUTOMATION IN CONSTRUCTION, 2019, 102 :135-147
[40]   Application of dynamic time warping to the recognition of mixed equipment activities in cycle time measurement [J].
Kim, Hyunsoo ;
Ahn, Changbum R. ;
Engelhaupt, David ;
Lee, SangHyun .
AUTOMATION IN CONSTRUCTION, 2018, 87 :225-234