Multi-Task Intelligent Monitoring of Construction Safety Based on Computer Vision

被引:6
作者
Liu, Lingfeng [1 ]
Guo, Zhigang [1 ]
Liu, Zhengxiong [1 ]
Zhang, Yaolin [2 ]
Cai, Ruying [3 ]
Hu, Xin [4 ]
Yang, Ran [5 ]
Wang, Gang [3 ]
机构
[1] Shenzhen Municipal Grp Co Ltd, Shenzhen 518000, Peoples R China
[2] CCCC Property Hainan Co Ltd, Sanya 572000, Peoples R China
[3] Shenzhen Univ, Key Lab Resilient Infrastructures Coastal Cities, Shenzhen 518060, Peoples R China
[4] Chongqing Technol & Business Inst, Sch Urban Construct Engn, Chongqing 400067, Peoples R China
[5] CCDC Shuyu Engn Construct Co Ltd, Chengdu 610000, Peoples R China
基金
中国国家自然科学基金;
关键词
computer vision; construction safety; unsafe behaviors; intelligent monitoring; object detection; segmentation; pose; YOLO; WORKERS; FALLS;
D O I
10.3390/buildings14082429
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Effective safety management is vital for ensuring construction safety. Traditional safety inspections in construction heavily rely on manual labor, which is both time-consuming and labor-intensive. Extensive research has been conducted integrating computer-vision technologies to facilitate intelligent surveillance and improve safety measures. However, existing research predominantly focuses on singular tasks, while construction environments necessitate comprehensive analysis. This study introduces a multi-task computer vision technology approach for the enhanced monitoring of construction safety. The process begins with the collection and processing of multi-source video surveillance data. Subsequently, YOLOv8, a deep learning-based computer vision model, is adapted to meet specific task requirements by modifying the head component of the framework. This adaptation enables efficient detection and segmentation of construction elements, as well as the estimation of person and machine poses. Moreover, a tracking algorithm integrates these capabilities to continuously monitor detected elements, thereby facilitating the proactive identification of unsafe practices on construction sites. This paper also presents a novel Integrated Excavator Pose (IEP) dataset designed to address the common challenges associated with different single datasets, thereby ensuring accurate detection and robust application in practical scenarios.
引用
收藏
页数:23
相关论文
共 52 条
[1]  
Aharon N, 2022, Arxiv, DOI [arXiv:2206.14651, DOI 10.48550/ARXIV.2206.14651]
[2]   Construction Site Hazards Identification Using Deep Learning and Computer Vision [J].
Alateeq, Muneerah M. ;
Fathimathul Rajeena, P. P. ;
Ali, Mona A. S. .
SUSTAINABILITY, 2023, 15 (03)
[3]   Dataset and benchmark for detecting moving objects in construction sites [J].
An Xuehui ;
Zhou Li ;
Liu Zuguang ;
Wang Chengzhi ;
Li Pengfei ;
Li Zhiwei .
AUTOMATION IN CONSTRUCTION, 2021, 122 (122)
[4]   Tracking multiple construction workers through deep learning and the gradient based method with re-matching based on multi-object tracking accuracy [J].
Angah, Ohay ;
Chen, Albert Y. .
AUTOMATION IN CONSTRUCTION, 2020, 119
[5]  
Bolya D., 2019, arXiv, DOI DOI 10.48550/ARXIV.1904.02689
[6]   Automated vision tracking of project related entities [J].
Brilakis, Ioannis ;
Park, Man-Woo ;
Jog, Gauri .
ADVANCED ENGINEERING INFORMATICS, 2011, 25 (04) :713-724
[7]   Graphical fault tree analysis for fatal falls in the construction industry [J].
Chi, Chia-Fen ;
Lin, Syuan-Zih ;
Dewi, Ratna Sari .
ACCIDENT ANALYSIS AND PREVENTION, 2014, 72 :359-369
[8]   Image Segmentation Using Computational Intelligence Techniques: Review [J].
Chouhan, Siddharth Singh ;
Kaul, Ajay ;
Singh, Uday Pratap .
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING, 2019, 26 (03) :533-596
[9]   A deep learning-based method for detecting non-certified work on construction sites [J].
Fang, Qi ;
Li, Heng ;
Luo, Xiaochun ;
Ding, Lieyun ;
Rose, Timothy M. ;
An, Wangpeng ;
Yu, Yantao .
ADVANCED ENGINEERING INFORMATICS, 2018, 35 :56-68
[10]   Detecting non-hardhat-use by a deep learning method from far -field surveillance videos [J].
Fang, Qi ;
Li, Heng ;
Luo, Xiaochun ;
Ding, Lieyun ;
Luo, Hanbin ;
Rose, Timothy M. ;
An, Wangpeng .
AUTOMATION IN CONSTRUCTION, 2018, 85 :1-9