A Study on Prevention of Construction Opening Fall Accidents Introducing Image Processing

Abstract

While institutional matters such as improvement on Basic Guidelines for Construction Safety are greatly concerned to reduce falling accidents at construction sites, there are short of studies on how to practically predict accident signs at construction sites and to preemptively prevent them. As one of existing accident prevention methods, it was attempted to build the early warning system based on standardized accident scenarios to control the situations. However, the investment cost was too high depending on the site situation, and it did not help construction workers directly since it was developed to mainly provide support operational work support to safety managers. In the long run, it would be possible to develop the augmented reality based accident prevention method from the worker perspective by extracting product information from BIM, visually rendering it along with site installation materials term and comparing it with the site situation. However, to make this method effective, the BIM model should be implemented first and the technology that can promptly process site situations should be introduced. Accordingly, it is necessary to identify risk signs through lightweight image processing to promptly respond only with currently available resources. In this study, it was intended to propose the system concept that identified potential risk factors of falling accidents by histogram equalization, which was known as the fastest image processing method presently, used visual words, which could enhance model classification by wording image records, to determine the risk factors and notified them to the work manager.

Are Construction Managers from Mars and Workers from Venus? Exploring Differences in Construction Safety Perception of Two Key Field Stakeholders

“…To this end, the fundamental step is identifying the contributing and detrimental safety factors in a construction project. Examples of research conducted in this category are (1) studies focusing on accident theories, including Domino Theory [46], Hinze's Distraction Theory [11,47], and human error theory [48]; (2) studies that apply models to investigate accidents' causes such as the multiple causation model [49] and accident root cause tracing model [50]; (3) research on factors causing specific accident types, such as falls [51] and electrocution [52]; (4) the application of technology in detecting the causes such as image processing [53] and machine learning [54]; and (5) survey-based studies asking construction professionals [55].…”

Suggestions for Improving South Korea’s Fall Accidents Prevention Technology in the Construction Industry: Focused on Analyzing Laws and Programs of the United States

“…To solve this problem, South Korea has conducted several studies on fall accident prevention at construction sites. Hong et al introduced the use of image processing at construction sites in South Korea to identify potential risk factors, record them as images, and signal the manager to prevent fall accidents due to cognitive mistakes [21]. Lee et al studied quick emergency measures by periodically receiving worker location information in dangerous situations and alerting the manager through a smart module and monitoring system in order to create a safe working environment at the construction site [22].…”

Application of Stochastic Gradient Boosting Approach to Early Prediction of Safety Accidents at Construction Site

“…However, this method also has a limitation in that safety managers or practitioners make decisions based on subjective and limited experience and judgment. Recently, state-of-the-art technology, i.e., Big data analysis, Internet of ings, and image processing, applied to construction safety management [47][48][49]. And data mining techniques, i.e., decision tree analysis, association rule analysis, and machine learning, also applied to predict construction accidents proactively [3,5,10,12,13].…”