Search

Computer vision has emerged as a promising tool for improving safety at construction sites through automatic scene recognition. However, traditional approaches require significant labor-intensive and time-consuming efforts for annotations. Although weakly supervised learning has the advantage of localizing objects without location information, the conventional class activation map (CAM) technique struggles with small and linear object localization and background noise at construction sites. For effective scene recognition related to construction safety, the spatial relationships between precisely localized objects are crucial. Due to the limitations of traditional CAM techniques in localizing small and linear objects, using CAM for construction safety monitoring remains inaccurate. Therefore, this study proposes a weakly supervised learning approach with an improved CAM for enhancing object detection in construction sites. The improved CAM localizes objects of various scales and is robust against background interference. Spatial relationships between localized objects are employed to determine the status of scenes for construction safety monitoring. Experiment using datasets associated with falls from ladders (FFL) demonstrates that the improved CAM surpasses the traditional CAM in mIoU (mean intersection over union) for the object localization performance as well as in the accuracy and F1-Score for recognizing unsafe scenes. This demonstrates the robust potential of employing CAM as a weakly supervised learning strategy, underlining its substantial feasibility for preventing hazards in construction sites. The proposed framework can minimize annotation efforts, demonstrating the potential of CAM as a viable computer vision technique for efficiently detecting hazards at construction sites.

The construction sector is known for exposing workers to numerous potential hazards, with falls from heights being the leading cause. These fatal fall accidents not only result in human loss but also impose significant financial costs on construction projects. However, current safety planning and management is typically carried out manually using safety documents and 2D models, which are time-consuming and labor-intensive. There is also a lack of visualization for the placement of temporary safety facilities (TSFs) during construction. Meanwhile, Building Information Modeling (BIM) has the potential to be used as a comprehensive workspace planning for TSFs in a scheduling manner. Therefore, this study proposes the development of a construction safety dashboard to inform workers about fall hazards using spatial–temporal data stored in 4D BIM. The proposed approach includes four modules: (1) identification and assessment of risk from identified work activities, (2) development of 4D BIM model, (3) creation of a dashboard to share safety knowledge, and (4) validation of the dashboard through interviews with safety managers and site workers. This approach is tested on a stadium project, particularly focusing on roof work activities, where workers are most prone to fall hazards. The proposed method aims to provide ease for site workers to access safety knowledge, including risk identification (including risk, fatality, location, and time), visualization of TSFs, personal protective equipment, and safety work instructions. This interactive dashboard also enables safety managers to plan safety measures, allocate TSFs efficiently, and make well-informed decisions to effectively mitigate risks.

Performing risk assessments in construction requires collecting and analyzing project data and historical safety accident data, which is challenging due to the inherent complexities and dynamic nature of construction projects. To address these challenges, building information modeling (BIM) has been leveraged as a centralized digital repository that integrates data and provides a holistic 3D view of a project. Previous studies have highlighted BIM’s significant functions for risk assessment, such as visualization, simulation, and clash detection. However, these studies often overlook the incorporation of temporal information, which is crucial for assessing risks accounting for the dynamic conditions of construction sites. This study develops a 4D BIM-based risk-assessment framework by integrating spatial and temporal data to respond to dynamic site changes. The framework leverages 4D BIM to combine 3D model data with time-, resource-, and logistics-related information, enhancing the tracking and evaluation of construction progress. The study involves investigating major construction accidents, classifying their risk factors, establishing risk-factor identification algorithms, and implementing the framework on a web-based platform for validation. This approach offers a comprehensive risk-identification strategy, applicable to multiple accident types, with intuitive visualization using BIM models, benefiting from managers’ experiential knowledge and enabling effective risk assessments and mitigation strategies. Consequently, potential safety risks at construction sites can be efficiently identified using interconnected spatial and temporal data while tracking changes in risk levels in real time and visualizing them on a web-based platform.

In the construction industry, the imperative for visual surveillance mechanisms is underscored by the need for safety monitoring, resources, and progress tracking, especially with the adoption of vision intelligence technology. Traditional camera installation plans often move toward coverage and cost objectives without considering substantial coverage overlap, inflating processing and storage requirements, and complicating subsequent analyses. To address these issues, this research proposes a voxel-based site coverage and overlapping analysis for camera allocation planning in parametric BIM environments, called the PBA approach. The first step is to collect information from the BIM model, which is the input for the parametric modeling step. After that, the PBA approach simulates the virtual devices and the construction layout by employing visual language programming and then generates a coverage area. Lastly, the performance simulation and evaluation of various placement scenarios against predefined criteria are conducted, including visual coverage and overlapping optimization for eliminating data redundancy purposes. The proposed approach is evaluated through its application to construction projects. The results from these various implementations indicate a marked decrease in data overlap and an overall enhancement in surveillance efficacy. This research contributes a novel, BIM-centric solution to visual information adoption in the construction industry, offering a scalable approach to optimize camera placement while mitigating overlapping areas.

Construction safety requires real-time monitoring due to its hazardous nature. Existing vision-based monitoring systems classify each frame to identify safe or unsafe scenes, often triggering false alarms due to object misdetection or false detection, which reduces the overall monitoring system’s performance. To overcome this problem, this research introduces a safety monitoring system that leverages a novel temporal-analysis-based algorithm to reduce false alarms. The proposed system comprises three main modules: object detection, rule compliance, and temporal analysis. The system employs a coordination correlation technique to verify personal protective equipment (PPE), even with partially visible workers, overcoming a common monitoring challenge on job sites. The temporal-analysis module is the key component that evaluates multiple frames within a time window, triggering alarms when the hazard threshold is exceeded, thus reducing false alarms. The experimental results demonstrate 95% accuracy and an F1-score in scene classification, with a notable 2.03% average decrease in false alarms during real-time monitoring across five test videos. This study advances knowledge in safety monitoring by introducing and validating a temporal-analysis-based algorithm. This approach not only improves the reliability of safety-rule-compliance checks but also addresses challenges of misdetection and false alarms, thereby enhancing safety management protocols in hazardous environments.

The provision of suitable training materials is crucial in preparing construction workers for the safety risks inherent in their work environments. However, retrieving relevant training resources for specific work tasks and worksites poses challenges due to the dispersed, unstructured, and multifarious nature of available content. This paper proposes a linked data and ontology-based system framework for effectively sharing and accessing educational safety contents from heterogeneous sources in a standardized way. The main technical solutions in the framework include an ontology that leverages the Resource Description Framework and Ontology Web Language to structure and publish educational safety training contents based on the linked data principles, and a content retrieval method which leverages the SPARQL protocol and RDF query language. Experimental results confirm that the proposed approach outperforms existing repositories in terms of search time, search result precision, and accuracy. It is envisaged that the framework would aid safety trainers in sharing, searching, and retrieving didactically appropriate materials to prepare workers for the unique safety challenges of their jobsite environments.

Detecting intrusion in hazardous areas is one of the priorities and duties of safety enhancement. With the emergence of vision intelligence technology, hazardous-area-detection algorithms can support safety managers in predicting potential hazards and making decisions. However, because of the dynamic and complex nature of the jobsite, high-risk zones have a different geometry and can be changed following the schedule and workspace of activity. This leads to hazardous areas being annotated manually. Thus, this study proposes a computer vision and a 4D BIM-based approach for intrusion detection in hazardous areas, called IDC4D. IDC4D comprises three modules: (1) the 4D BIM-based safety planning (4BSP) module, which analyzes the hazardous area; (2) the hazardous area registration (HAR) module, which delivers the hazardous area from the BIM model to the camera’s first frame image; and (3) the hazardous-area-intrusion-detection module (HAID), which applies the computer vision algorithm to identify the correlation between workers and hazardous areas. The efficiency of the IDC4D approach is validated by testing a maintenance project on the construction site. IDC4D supports the planner in choosing the plan and detecting the event of workers entering hazardous areas while working. It showed an average precision of 93% and 94% in phase 1 and phase 2, respectively. These findings provide insight into how varying geometries of diverse hazard areas can be handled for enhancing intrusion detection.

Noncompliance with safety rules is a major cause of unsatisfactory performance in construction safety worldwide. Although some research efforts have focused on using computer vision (CV) methods for safety rule inspection, these methods are still in their early stages and cannot be effectively applied on construction job sites. Therefore, it is necessary to present a feasible prototype and conduct a detailed analysis of safety rules to ensure compliance at the job site. This study aims to extend the validation of safety rule analysis through four case scenarios. The proposed structured classification of safety rules includes categorizing them based on project phases and work stages. The construction phase-related rules are divided into four groups: (1) before work, (2) with intervals, (3) during work, and (4) after work. To validate the proposed framework, this research developed prototypes for each group’s scenarios using deep learning algorithms, a storage database to record compliance with safety rules, and an Android application for edge computing, which is required in the “before work” and “after work” groups. The findings of this study could contribute to the development of a compact CV-based safety monitoring system to enhance the current safety management process in the construction industry.

According to the Center for Construction Research and Training (CPWR) and the Korea Occupational Safety & Health Agency (KOSHA), falls from ladders are a leading cause of fatalities. The current safety inspection process to enforce height-related rules is manual and time-consuming. It requires the physical presence of a safety manager, for whom it is sometimes impossible to monitor an entire area in which ladders are being used. Deep learning-based computer vision technology has the potential to capture a large amount of useful information from a digital image. Therefore, this paper presents a deep learning-based height assessment method using a single known value in an image to measure working height, monitor compliance to safety rules, and ensure worker safety. The proposed method comprises (1) extraction of safety rules from the KOSHA database related to the A-type ladder; (2) object detection (Single Shot Multibox Detector SSD) (3) a height-computing module (HCM) to estimate the working height of the worker (how high a worker is from the ground); and (4) classification of worker behavior (using the developed SSD-based HCM) based on the best practices derived from the KOSHA database. The developed algorithm has been tested on four different scenarios based on KOSHA safety rules, with heights ranging from under 1.2 m to over 2 m. Additionally, the proposed method was evaluated on 300 images for binary classification (safe and unsafe) and achieved an overall accuracy of 85.33%, verifying its feasibility for intelligent height estimation and compliance monitoring.

As a temporary facility, scaffolding has an essential role in providing a work environment at height in the construction industry. According to the Occupational Safety and Health Administration (OSHA), approximately 65% of laborers work on scaffolding. Scaffolding work information needs to be effectively managed with reliability to provide a safe environment. However, managing information of the scaffolding work process remains challenging in forgery risk and manual verification. Blockchain has been widely introduced as an accountable and efficient information management solution. This study presents a blockchain-based system for scaffolding work to grant reliability and efficiency of information management. The system is developed to secure applicability by considering three aspects: (1) optimal blockchain platform regarding characteristics of scaffolding work; (2) storage method to address the hindrance of blockchain; (3) information needed to be compared for verifying adequacy. The detailed configuration and process model for the system is categorically presented, and validated via a case study. The case study confirmed that the system was able to store the information in the block smoothly, verify the information using the smart contract successfully, and remain the block size constant by using off-chain. The proposed system has the potential of practical applicability and could contribute to mitigate potential safety risks associated with inadequate scaffolding work management. Furthermore, the proposed system development flow can be leveraged as a guideline to extend blockchain applications to diverse areas in the construction domain.

In South Korea, industrial accidents continue to increase in frequency, with construction accidents accounting for more than a third of all industrial accidents. Specifically, by preventing fall accidents, the death rate from accidents can be reduced by 50%. Fall protection is required to prevent fall accidents, and investigating the reinforcement of the worker’s safety harness and hook fastening becomes imperative. This requires automation of computer vision confirmation of the safety harness and hook fastening. As the accident risk can be reduced by an effective safety culture in the system, it is necessary to monitor safety on site through a construction safety automation system. Therefore, the objective of this study is to develop a computer vision process for safety harness and hook for preventing fall accidents in South Korea’s construction industry. This study focuses on system scaffolds that are widely used at construction sites. The application of this methodology to sample sites and field cases established its applicability. The proposed computer vision application methodology will serve as the foundation for visualization research in the construction industry, and image recognition will help reduce the safety accident rate. Accidents caused by failure to use a safety harness and hook can be reduced in South Korea as well as globally. Additionally, this methodology is applicable to roof construction, tower crane installation and dismantling work, as well as steel tower installation and dismantling.

In this paper, a calibration method for gyro bias that changes depending on the position of the IMU (inertial measurement unit) is proposed to improve the navigation performance of RLG-based RINS (ring-laser-gyro-based rotational inertial navigation system). RINS is a navigation device that compensates for the inertial sensor errors by utilizing the rotation of the IMU. In previous studies, the rotation scheme of the IMU is designed assuming that inertial sensor errors are not affected by position of the IMU. However, changes in temperature distribution, direction of gravity, and dithering according to the rotation of the IMU affect the inertial sensor errors, such as gyro bias. These errors could degrade the long-term navigation performance of RLG-based RINS. To deal with this problem, this paper proposed a compensation method of the gyro bias that changes depending on the position of the IMU. First, RINS is reviewed using a dual-axis 16-position rotation scheme and RLG. Next, the attitude error of RLG-based RINS is derived utilizing navigation equations. The effect of the gyro bias change caused by the change in the IMU attitude for the navigation performance of RINS is analyzed based on navigation equations and simulations. Finally, system-level indirect calibrations for the Z–axis up position and Z–axis down position are performed to calculate the gyro bias change caused by the IMU attitude. The accuracy of the proposed calibration method is verified by long-term navigation test. The test results show that the proposed calibration method improves the navigation performance of RINS compared with the conventional calibration method.

In total, 44.3% of particle matter 10 (PM10) is fugitive dust, and one of the main sources of fugitive dust generation in Korea is construction work (22%). Construction sites account for 84% of the total business places that have reported fugitive dust generation. Currently, the concentration of fine dust at construction sites is being remotely monitored by government inspection agencies through IoT sensors, but it is difficult to trust that appropriate fine dust reduction measures are being taken, because contractors can avoid taking these measures by submitting false reports or photos. In addition, since the fine dust monitoring system under government management is not an open platform and centralized system, residents near construction sites encounter difficulties in accessing information about fine dust. Therefore, in this study, we designed and constructed a blockchain network model to transparently and reliably provide network participants with the information associated with IoT data and fine dust reduction measures. To operate the blockchain network, we designed the chaincode, DApp, and network architecture. In addition, information on fine dust concentration and reduction measure photos were shared with the participants via the blockchain search tool (Hyperledger Explorer). The proposed blockchain network is expected to form a trust protocol among contractors, government inspection agencies, and citizens.

Soil excavation is a fundamental step of building and infrastructure development. Despite strong enforcement of construction best practices and regulations, accidents in construction industry are comparatively higher than other industries. Likewise, significant increase in injuries and fatalities are recently reported on geotechnical activities such as excavation pits and trenches. Academic researchers and industry professionals have currently devoted vital attention to acquire construction safety in preconstruction phase of the project. They have developed various algorithms to enhance safety in preconstruction phase such as automated generation of scaffolding and its potential risk analysis, checking BIM model for fall risks, and limited access zone allocation in wall masonry. However, safety in geotechnical works at preconstruction phase is yet unexplored. This paper proposed automatic safety rule compliance approach for excavation works leveraging algorithmic modeling tools and BIM technologies. The focused approach comprises of the following three modules: information extraction and logic design (IELD), information conversion and process integration (ICPI), and automodeling and safety plan generation (ASPG). Specifically, the scope of the paper is limited to major risks such as cave-ins, fall, safety egress, and prohibited zones risks. A set of rules-based algorithms was developed in commercially available software using visual programming language (VPL) that automatically generates geometric conditions in BIM and visualizes the potential risks and safety resources installation along with their quantity take-off and optimized locations. A case study has been presented to validate the proof of concept; automated modeling tool for excavation safety planning generated the required results successfully. It is anticipated that the proposed approach has potential to help the designers through automated modeling and assist decision makers in developing productive and practical safety plans compared to the conventional 2D plans for excavation works at the preconstruction phase. Moreover, it is realized that the same approach can be extended to other rule-dependent subjects in construction.

Fires pose an enormous threat to human safety and many spectacular fires in under-construction buildings were reported over the past few years. Many construction sites only rely on fire extinguishers, as under-construction buildings do not contain a permanent fire protection system. Traditional safety planning lacks a justified approach for the firefighting equipment installation planning in the construction job site. Even though many government agencies made safety regulations for firefighting equipment installations, it is still a challenge to translate and execute these rules at the job site. Currently, the construction industry is devoted to discovering all the possible applications of Building Information Modelling (BIM) technology in the entire phases of the project life cycle. BIM technology enables the presentation of facilities in 3-D and offers rule-based modeling through visual programming tools. Therefore, this paper focuses on a visual language approach for rule translation and a multi-agent-based construction fire safety planning simulation in BIM. The proposed approach includes three core modules, namely: (a) Rule Extraction and Logic Development (RELD) Module, (b) Design for Construction Fire Safety (DCFS) Module, and (c) Con-fire Safety Plan Simulation (CSPS) Module. In addition, the DCFS module further includes three submodules, named as (1) Firefighting Equipment Installation (FEI) Module, (2) Bill of Quantities (BoQs) for firefighting Equipment (BFE) Module, and (3) Escape Route Plan (ERP) Module. The RELD module converts the OSHA fire safety rule into mathematical logic, and the DCFS module presents the development of the Con-fire Safety Planning approach by translating the rules from mathematical logic into computer-readable language. The three sub-modules of the DCFS module visualize the outputs of this research work. The CSPS module uses a multi-agent simulation to verify the safety rule compliance of the portable firefighting equipment installation plan the system in a BIM environment. A sample project case study has been implemented to validate the proof of concept. It is anticipated that the proposed approach has the potential to helps the designers through its effectiveness and convenience while it could be helpful in the field for practical use.

Various combining methods have been proposed to utilize multi-satellite-based augmentation system (SBAS) correction to provide accurate position in the global navigation satellite system (GNSS) receiver. However, the proposed methods have not been objectively compared and analyzed, making it difficult to know which ones are effective for multi-GNSS positioning. This paper presents efficient methods of combining multi-SBAS corrections in multi-GNSS positioning by comparing three methods: correction domain integration, measurement domain integration, and position domain integration. The performance of the three methods were analyzed through a covariance analysis that was expanded to multi-GNSS and multi-SBAS. Then, the results were verified by experiments using real measurements and corrections. Furthermore, implementation issues, such as computational complexity, availability, and flexibility, are analyzed. As a result, three methods had the same precision, but different complexity, availability, and flexibility. These results will be important guidelines to design, implement, and analyze navigation systems based on multi-GNSS with multi-SBAS corrections.