• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1100-1105
• /
• 2022

Denoising, registering, and detecting changes of 3D digital map are generally conducted by skilled technicians, which leads to inefficiency and the intervention of individual judgment. The manual post-processing for analyzing 3D point cloud data of construction sites requires a long time and sufficient resources. This study develops automation technology for analyzing 3D point cloud data for construction sites. Scanned data are automatically denoised, and the denoised data are stored in a specific storage. The stored data set is automatically registrated when the data set to be registrated is prepared. In addition, regions with non-homogeneous densities will be converted into homogeneous data. The change detection function is developed to automatically analyze the degree of terrain change occurred between time series data.

• Journal of the Korean Society of Safety
• /
• v.30 no.5
• /
• pp.20-28
• /
• 2015

Recently, railroad's preference greatly increased as the environment-friendly means of transportation as the importance in the aspects of environment and energy efficiency. So the government established the Korea Rail Network Authority which takes full charge of railroad construction in 20047 for regular railroad construction to combine major key points in the whole country with each other to be one city region by connecting them to each other to be within the commute time range of a hour and thirty minutes. And it has arranged large-scale railroad construction by establishing plans to build the 1st and 2nd national railroad networks as the national project and investing about 100 trillion won in it from 2006 to 2020. As large-scale railroad construction is promoted as the national project like this, there has been a string of safety accidents in it due to the large and complex construction project. As the government strengthened the safety accident prevention plans, safety accidents have tended to decrease in 2011. However, accidents of construction machinery have found to increase. Therefore, this study tried to investigate accident cases of the Korea Rail Network Authority for the recent 5 years and analyze accidents of construction machinery to prevent them in railroad construction sites and suggest accident prevention plans due to it by conducting, investigating, and analyzing the survey of its operators and superintendents of the construction sites and drawing the problems.

• Korean Journal of Construction Engineering and Management
• /
• v.22 no.5
• /
• pp.48-54
• /
• 2021

According to the Ministry of Employment and Labor's statistics on occupational fatalities in South Korea, more than half of the fatalities in the past five years have occurred in the construction industry. The stuck-by and caught-in-between accidents associated with construction equipment is the major source of fatalities from construction sites. In order to prevent such accidents in construction sites, the government has spent lots of efforts including proposing the "special law on construction safety" and encouraging the implementation of new technology for accident prevention. However, numerous accidents are still occurred at construction sites and further efforts are still required. In this manner, this study developed a collision prevention technique that can prevent collision between equipment and worker by recognizing location and type of the nearby objects through ultrasound scanning. The study conducted a pilot experiment and the analysis results demonstrate the feasibility of achieving high performance in both object recognition and location estimation. The developed technique will contribute to prevent collision accidents at construction sites and provide the supplemental knowledge on developing automated collision prevention system for construction equipment.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.1
• /
• pp.99-107
• /
• 2023

Recently, the rate of death and safety accidents at construction sites is the highest among all kinds of industries. In order to apply artificial intelligence technology to construction sites, it is essential to secure a dataset which can be used as a basic training data. In this paper, a number of image data were collected through actual construction site, for which major construction equipment objects mainly operated in civil engineering sites were defined. The optimal training dataset construction was completed by annotation process of about 90,000 image dataset. Reliability of the dataset was verified with the mAP of over 90 % in use of YOLO, a representative model in the field of object detection. The construction equipment training dataset built in this study has been released which is currently available on the public data portal of the Ministry of Public Administration and Security. This dataset is expected to be freely used for any application of object detection technology on construction sites especially in the field of construction safety in the future.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.4
• /
• pp.90-99
• /
• 2020

The construction industry is suffering from a large number of fatal accidents. As many field works are being conducted in a dangerous condition such as working at height and adverse weather, they are always exposed to safety accidents with high frequency and severity compared to other industries. Such risk is even larger in small construction sites, but studies that focus on combinatorial factors leading to fatal accidents in small construction sites are lacking. Thus, in order to reduce the fatal accidents in the construction industry, this study analyzed 1,438 occupational death accidents cases in small construction sites and, then, conducted the association rule analysis to extract ten combinatorial factors that frequently led to fatal accidents in small construction sites. Based on the extracted association rules, this study also discussed possible countermeasures to reduce the fatal accidents. The results were explained to experts, who agreed on the results of the study. This study contributes to the construction safety management theory by providing a detailed analysis of fatal accidents in small construction sites that can be used for developing and deploying safety policies and educations for small construction site workers.

• Journal of the Korean Society of Safety
• /
• v.32 no.3
• /
• pp.48-53
• /
• 2017

Many construction accidents can be lead to a death occurring at construction sites. These are considerably due to potentially-hazardous equipment and machine or unexpected collapsion at earth work due to land slide and so on. Almost 50% of the total death and injury, occurred in construction sites in 2015. 66% of those serious accidents are due to falling occurring from construction sites when they work. Therefore, causes and recommendations of each accident should be deeply thought and analysed The indirect causes are directly related to safe consciousness of the construction workers. Actually, their safety consciousness are not high, even very low, it is thought. Questionnaire survey sheets have been distributed to Seoul, Incheon, and Gyunggi-Do area, first. And then, the authors have collected those directly at sites, in order to increase collection rate of the sheets. The totally, collected sheets are 295 sheets. And, they are analysed using SPSS version 19 package program. Workers internal consciousness has been investigated and reviewed and analysed by statistical method such as frequency rate, crossed, and correlated analysis. And finally the conclusions for the above analyses are as follows; Heavy weight worth a crew of more than two workers should be necessarily considered for the advanced safety plan and needed for making a highly potential hazard group at construction sites. Safety consciousness, earing p.p.e, workman ship should be mainly considered for investing safety costs with an aspect of human factor.

• Journal of the Society of Disaster Information
• /
• v.18 no.2
• /
• pp.395-404
• /
• 2022

Purpose: Small-scale construction sites have insufficient systematic safety management activities, and due to the characteristics of the construction site, the production structure is complex due to external environmental factors, and the risk of construction equipment is very high. We would like to propose a checklist method among practical risk assessment techniques that can derive risk factors for disaster prevention at small construction sites and reduce disasters. Method: Risk factors were derived by analyzing literature research and disaster cases, and detailed work for a checklist of risk assessment suitable for small-scale construction sites was classified based on risk factor items. Result: Hazard factors were divided into 6 major categories, and 29 detailed types of work were classified based on actual work types, and 80 detailed works were classified accordingly. Conclusion: By arranging risk factors suitable for small-scale construction sites according to the classification system, the lack of expertise in the construction site can be supplemented, and risk factors can be derived more easily and disaster reduction can be expected through establishment of safety measures.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.6
• /
• pp.821-830
• /
• 2023

This research aims to identify risk factors for fall accidents at small and medium-sized construction sites through a comprehensive regression analysis. Initially, the study involved collecting a decade's worth of fall accident data from these sites. A t-test confirmed a significant variation in the treatment duration following fall accidents between two distinct groups: small and medium-sized versus large construction sites. Subsequently, a regression analysis was conducted to establish a model highlighting the risk factors associated with safety accidents. The factors influencing fall accidents were determined to be, in descending order of impact, the time of the accident, the day of the accident, and the occupational classification. The findings from this study are expected to serve as foundational data for enhancing policies and conducting statistical analyses tailored to construction site sizes. They also provide crucial information for future research on risk quantification at small and medium-sized construction sites.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.609-615
• /
• 2024

The construction industry's fatality count stands at 402, comprising approximately 46% of total industrial accidents. Notably, construction costs less than 5 billion won account for about 69%, so strengthening safety management at small and medium-sized construction sites is required. In this study, 19,511 accident investigation data were collected using web scraping. Through statistical analysis of the collected structured data and text mining analysis of the unstructured data, accident types and causes of accidents were analyzed by construction costs at sites less than 5 billion won. As a result, it was confirmed that there were differences in accident types and causes depending on the construction costs. It is hoped that the results of this study will be used for customized safety management at small and medium-sized construction sites.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.4
• /
• pp.505-513
• /
• 2009

Recently, researches on the construction information for construction of high-tech cities are under performed. RTLS(Real-Time location system) for gathering the dynamic location information of construction resources in construction sites, such as workers, materials and equipments, is one of the developments. Especially, construction resources can be managed efficiently with the dynamic location information and the improvement of safety and the reduction of cost are expected. To introduce the RTLS to the construction sites, the installation location of AP(Access Point) must be simulated using the 3-dimensional visibility analysis considering the propagation distance of AP. In this research, 3-dimensional signal simulation software based on the spatial data using surveying terrestrial LiDAR is developed. The simulated results are compared with the signal strength of field experiments for 4 test sites. As a result, the signal strength from the propagation model is most similar to that of field experiment at the front of the main building and the maul playground of Konkuk University. The visibilities in that sites are higher than other sites. among 4 test sites.