• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.5
• /
• pp.631-636
• /
• 2019

Over the last decade, many researchers have investigated a number of vision-based construction object detection algorithms for the purpose of construction site monitoring. However, previous methods require the ground truth labeling, which is a process of manually marking types and locations of target objects from training image data, and thus a large amount of time and effort is being wasted. To address this drawback, this paper proposes a vision-based construction object detection framework that employs an active learning technique while reducing manual labeling efforts. For the validation, the research team performed experiments using an open construction benchmark dataset. The results showed that the method was able to successfully detect construction objects that have various visual characteristics, and also indicated that it is possible to develop the high performance of an object detection model using smaller amount of training data and less iterative training steps compared to the previous approaches. The findings of this study can be used to reduce the manual labeling processes and minimize the time and costs required to build a training database.

• Korean Journal of Construction Engineering and Management
• /
• v.13 no.1
• /
• pp.44-52
• /
• 2012

In the cost management of public construction projects, it is an important issue to develop an adequate cost data for estimating the predetermined amount by various methods. For a long time, a standard of estimation in korea is used as a basis for estimating the predetermined amount of public construction. However, they did not have a reasonable cost data based on a labor and equipment productivity analysis. For this reason, it is difficult to make a reasonable and efficient estimation of the costs, and this situation presents an urgent need for more accurate cost data to use in an early phase. This study analyzed the productivity of form work by the CYCLONE model, and presented the model on the number of optimal labor through sensitivity analysis. This CYCLONE model can be useful in analyzing productivity on the various sizes of form. Also, the regression model to estimate the daily output can be used in predicting the amount of labor. Considering the work duration in the regression model is expected to make the daily output estimation much more accurate.

• Journal of KIBIM
• /
• v.6 no.4
• /
• pp.35-41
• /
• 2016

Learning effect is an observation that the more times a task is performed, the less time is required to produce the same amount of outcomes. The construction industry heavily relies on repeated tasks where the learning effect is an important measure to be used. However, most construction durations are calculated and applied in real projects without considering the learning effects in each of the repeated activities. This paper applied the learning effect to the repeated activities in a small sized apartment construction project. The result showed that there was about 10 percent of difference in duration (one approach of the total duration with learning effects in 41 days while the other without learning effect in 36.5 days). To make the comparison between the two approaches, a large number of BIM based computer simulations were generated and useful patterns were recognized using machine learning algorithm named Decision Tree (See5). Machine learning is a data-driven approach for pattern recognition based on observational evidence.

• Journal of KIBIM
• /
• v.10 no.2
• /
• pp.12-20
• /
• 2020

Recently, interest in BIM technology has been growing in the domestic construction market as the number of construction projects requiring the application of BIM technology has increased. The use of BIM allows the use of various visualization functions through 3D models as well as drawing interference review, quantity calculation and integrated management of information. In particular, estimates of construction costs based on BIM can increase work efficiency by reducing the burden of calculating construction costs and managing them. In order to increase the efficiency of BIM-based cost estimates, it is necessary to improve the correlation between the BoQ(Bill of Quantity) information and the BIM model. For this purpose, the ratio of the amount and item to the detailed construction of the current BoQ was analyzed, especially the problem of the calculation of construction cost in the window work in this study. In addition, we would like to suggest a method for systematically linking the BoQ information with the BIM model by improving the BoQ information structure of the window work. It is expected that this will increase the efficiency of the quantity calculation and analysis work of construction cost of window work. In addition, it is expected that this method will help to analyze and predict changes in construction cost of windows and doors by facility characteristics and type.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.47 no.1
• /
• pp.39-48
• /
• 2019

Based on the bidding data of the national marketplace for public procurement service from 2003 to 2015, this study investigated and analyzed the bidding trends of the landscape management public consignment service by analyzing total bidding, type, client, region, license. The results are as follows. First, the total number of bids for civilian consignment services in landscape management increased by 1,112 cases, corresponding to a 487.7% increase over 10 years, and the total bidding amount increased by 144,504 million won, corresponding to a 382.5% increase. Second, in 10 years, the proportion of landscape management in landscaping works increased by 10%, and the bidding amount increased by 3%. Third, in the analysis of bidding trends by type, green areas showed the greatest growth in the number of bids, while the greenery of buildings showed the highest increase in the bid amount. Fourth, local autonomous entities, Gyeonggi province, and the landscaping planting construction industry showed the highest increase in the number of bids and the amount in each field such as client, region, and license. In summary, the number of cases and the bidding amount is increasing year by year. Considering the increasing number of users and demands thereof, the number of bids and the amount of consignment service for landscape management will continue to increase. The purpose of this study is to investigate and systematically analyze the tendency of bidding for 10 years for the private consignment service of landscape management in the current situation, where the importance of landscape management is increasingly emphasized. Another purpose of this study is to discern the necessity of the landscape management business and to provide the basis for incorporating the landscape management business into the professional construction industry in the future, thus providing opportunities for widening the expertise and diversity of the landscaping field. For the following study, the legal basis of landscape management, qualification, equipment standards, calculation of management cost per unit, and the appropriateness of the management cost should be considered.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.253-254
• /
• 2021

In the field of construction, research on smart construction technology is being actively pursued as a measure to increase productivity and efficiency. The technology that links 3D scanning and BIM of smart construction technology is in the limelight as a technology for checking the state of buildings in the field of architecture. It is thought that these techniques will be of great help in solving problems when the amount of inspection targets is large, such as confirmation of the rebar arrangement intervals, and therefore a large number of human resources are required. Therefore, in this study, we would like to apply 3D scanning to rebar construction to confirm whether the rebar arrangement can be confirmed according to the design drawing. In the study, the wall rebar of the rebar placed at the actual construction site was directly scanned to extract data, and the rebar placing status was confirmed through type analysis. As a result of analyzing the reinforcing bar arrangement state based on the data obtained by 3D scanning, it was found that the technology can be utilized.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.6
• /
• pp.534-539
• /
• 2013

Recently, the number of vehicles equipped with cameras that are generally used to recognize surroundings is increasing. For robust recognition, a huge amount of tests under various environments are performed. Furthermore, the installation position or orientation of the camera is also changed depending on the vehicle. This change also accompanies many tests. Correspondingly, a large cost and a great deal of manpower are required to perform these tests. This paper proposes a method to cut these costs while conducting enough tests through the construction of a database of videos and a geometric transformation of images.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2011.11a
• /
• pp.135-136
• /
• 2011

A standard of estimation is used as a basis for estimating the predetermined amount of public construction. However, they raise several points of reasonable labor to be presented to a standard of estimation. For this reason, it is difficult to make a reasonable and efficient estimation of the costs, and this situation presents an urgent need for an accurate way of making such a calculation.This study analyzed the productivity of reinforced concrete work by the CYCLONE model, and the estimated optimal labor through sensitivity analysis, and presented the model on the number of optimal labor through sensitivity analysis.

• Journal of Korean Institute of Industrial Engineers
• /
• v.42 no.4
• /
• pp.270-279
• /
• 2016

A glass product manufacturing company transports a large number of flat glass products from a manufacturing firm to a building construction site. The products are transported using specially designed racks, which assure fewer glass breakages during the deliveries. This study determines the sizes of the racks which minimize the total logistics cost including costs for rack purchasing, handling, transportation, and inventory costs. The determination of the rack size should consider tradeoff relationships between the amount of glasses piled in a rack and the number of racks loaded on a truck, and affects the required number of racks and the truck operational cost. A truck loading algorithm is proposed to maximize a high truck utilization, and an enumeration method is proposed to determine the optimal combination of rack sizes considering the total logistics cost. The numerical example is solved by using a real data.

• Journal of Industrial Convergence
• /
• v.20 no.5
• /
• pp.1-9
• /
• 2022

Today, apartment houses account for a very high proportion of the types of residence. This study analyzed the difference between the bidding construction cost using the long-term repair allowance and using the general repair cost, and analyzed the difference of factors affecting the amount of use of these two items. For this purpose, related data on apartment housing complexes located in seven representative districts of Busan from 2017 to 2021 were collected and analyzed from the apartment housing management information system. As a result of statistical analysis, the type of bidding variable had the greatest negative(-) effect on the bidding construction cost, and the next factor that affected was different between the amount of long-term repair allowance used and general repair cost used. In addition, there was a difference in statistical significance in the type of bidding by construction year for the number of bidding works between the case of using the long-term repair allowance and the case of using the general repair cost. The results of this analysis will help to find ways to reduce bidding construction costs. However, it is expected to find additional meaning by including more detailed variables such as technical ability.