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.

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.

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.

Construction sites are considered as complicated work environments. Various concurrent activities may overlap apropos to time and workspace, predisposing them to spatial–temporal exposure and repetitive accidents. Detecting the characteristics of repetitive accidents before the construction stage contributes to prevent injuries and fatalities caused by spatial—temporal conditions at construction job sites. To resolve this problem, this study proposes a novel hazard identification approach through spatial–temporal exposure analysis called HISTEA, which integrated scenario analysis of accident cases into 4D building information modeling (BIM). The proposed approach consists of three modules: (1) spatial–temporal hazard investigation (SHI) to analyze the accident cases and develop the hazard database of the spatial–temporal overlap condition of pair-wise activities; (2) spatial–temporal condition identification (SCI) to determine the conflict among different activities, considering the workspace and time overlap from the 4D BIM model; and (3) safety information integration (SII) to deliver safety knowledge to the project team through a web-based application. To illustrate and validate this approach, a HISTEA prototype for foundation work has been developed to be used at the pre-construction stage. The developed prototype is based on the analysis of 496 accident reports extracted from the integrated management information system (IMIS) of the Occupational Safety and Health Administration for the SHI module database. The proposed approach is expected to proactively aid project teams in detecting hazards that ultimately reduce repetitive accidents caused by overlapping activities.

Many construction workers are getting injured or killed in fires and explosion accidents each year. The workers are prone to severe fatal accidents due to unavailability of permanent firefighting system in many construction sites, thus they typically rely on portable firefighting equipment (PFE) to minimize fire damage. Many occupational health and safety agencies have developed safety regulations for PFE installation and monitoring in construction. However, in the traditional construction fire safety management process, the installation spots for PFE's are visually identified in a 2D floor plan and then top-down supervisory approach is used to inspect the active availability of the PFE's. Such manually operated conventional methods of PFE installation and monitoring are expensive, prone to manipulation, and do not provide sufficient motivation for voluntarily following fire safety policies. Therefore, this research study develops a fire safety rule-based PFE installation approach and proposes an alternative method for shifting the top-down inspection approach to the bottom-up voluntarily approach for convenient, transparent, and automated safety inspection information delivery. To validate the bottom-up approach concept, a visual language algorithm is initially developed for PFE installation planning system (PFE-IPS) in BIM, followed by an optical character recognition (OCR) and blockchain -based android application for safety inspection information system (SIIS). This article also presents two case studies to evaluate the feasibility and practicality of the developed systems. The proposed approach out-turn reduces the safety manager's manual efforts and burdens of government safety auditors while enhancing efficiency and reliability.