• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.347-352
• /
• 2007

Recently, automated construction machines have been developed for technically solving construction industry problems such as labor, productivity, quality and the profit decrease. In domestic construction industry, a research for developing an intelligent excavation robot has been performed. The primary objective of this research is to analysis state-of-the art technologies in order to recognize local ground shape in real-time and compute soil volume of earth moving. This research analyzed five elemental technologies for 3D modeling of local ground shape and selected an optimal technology among the five technologies through using AHP method. It is anticipated that the optimal technology selected for 3D modeling of local ground shape can be effectively used to develop the intelligent excavation robot.

• Korean Journal of Construction Engineering and Management
• /
• v.10 no.2
• /
• pp.145-154
• /
• 2009

For developing an Automation equipment in construction, it is a key issue to develop 3D modeling technology which can be used for automatically recognizing environmental objects. Recently, for the development of "Intelligent Excavating System(IES), a research developing the real-time 3D terrain modeling technology has been implemented from 2006 in Korea and a stereo vision system is selected as the optimum technology. However, as a result of performance tests implemented in various earth moving environment, the 3D images obtained by stereo vision included considerable noise. Therefore, in this study, for getting rid of the noise which is necessarily generated in stereo image matching, the noise elimination algorithm of stereo-vision images for 3D terrain modeling was developed. The consequence of this study is expected to be applicable in developing an automation equipments which are used in field environment.

• Journal of the Korean Geophysical Society
• /
• v.7 no.4
• /
• pp.247-253
• /
• 2004

In this paper, 3D recognizing algorithm which is based on the external shape feature is presented. Since many objects have the regular shape, if we posses the database of pattern and we recognize the object using the database of the object's pattern, it is possible to inspect and/or recognize the objects of many fields. This paper handles on the 3D object recognition algorithm using the geometrical pattern matching by 3D database.

• Tunnel and Underground Space
• /
• v.29 no.6
• /
• pp.508-522
• /
• 2019

Because of the slope failure, not only property damage but also human damage can occur, slope stability analysis should be conducted to predict and reinforce of the slope. This paper, defines the ground areas that can be characterized in terms of slope failure such as Rockmass jointset, Rockmass fault, Soil, Leakage water and Crush zone in sloped images. As a result, it was shown that the deep learning instance segmentation network can be used to recognize and automatically segment the precise shape of the ground region with different characteristics shown in the image. It showed the possibility of supporting the slope mapping work and automatically calculating the ground characteristics information of slopes necessary for decision making such as slope reinforcement.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.4
• /
• pp.353-362
• /
• 2020

Korea was recognized as a relatively safe area for earthquake. However, due to considerable damage to facilities caused by the earthquake in Gyeongju and Pohang, interest in the maintenance and repair of structures is increasing. So interest in vibration damping technology applicable to existing structures is also increasing. However, vibration damping technology has a problem in that its usability is reduced due to damage of the damping device when a strong earthquake occurs. Recently, in order to solve such a problem, study is being conducted to apply a superelastic shape memory alloys (SSMA) capable of recentering bracing. Therefore, in this study, nonlinear dynamic analysis is performed to evaluate the seismic performance of the buckling-restrained braced frame (BRBF) applied SSMA to bracing.

• Journal of the Korean Geotechnical Society
• /
• v.19 no.2
• /
• pp.39-48
• /
• 2003

Previous analytical models for key blocks have been based on the assumption of infinite persistent discontinuities. In this paper, a key block analysis method considering the finite persistence of discontinuities is proposed as a stability evaluation method in tunnel constructions, and then applied to an actual example site. Three-dimensional rock block identification with consideration of the persistence of discontinuities is performed by using discontinuity disk model. The removability and stability analyses of rock blocks formed by the identification method are performed. The identification method can handle convex and concave shape blocks. In order to demonstrate the applicability of this developed numerical method to the stability evaluation in tunnel constructions, the analytical results are examined and compared one another.

• Journal of the Korean Geotechnical Society
• /
• v.20 no.8
• /
• pp.103-111
• /
• 2004

There are some problems in evaluating the bearing capacity of decomposed granite soils by general equations on account of their inherent compressibility and crushability. In order to investigate this kind of the engineering characteristics on decomposed granite soils in detail, it is necessary to how the micro property of the single particle composing the granite soils, and then the relevance to the macro characteristics of the soils has to be cleared. The reason why the single particle properties are not studied is first the difficulty to find out some regulating parameters, and secondly little understanding of its significance. Furthermore, the water in the decomposed granite soils accelerates the particle crushing. Consequently, increasing of compressibility and decreasing of shear strength would occur. Actually, when the ground settlement is a big issue in the embanked ground using the decomposed granite soils, the sensitive change of compressibility due to the change of water content in the ground becomes conspicuous. In this study, the single particle strength characteristics are studied and microscopic particle shape analyses are performed. In addition the compressibility of the decomposed granite soils and water content effect on the compressibility are analysed based on the test results.

• Journal of the Korean GEO-environmental Society
• /
• v.11 no.11
• /
• pp.55-62
• /
• 2010

The settlements by liquefaction seldom occur uniformly because of soil homogeneity, however differential settlements are major cause of the damages to structures. From the past researches, author paid attention to the fact that stress history during undrained cyclic shear process affects greatly on the volumetric strains of the post-liquefaction. Therefore, the effect of the residual shear strain in cyclic shear process was examined in this study. The experiment apparatus based on strain control with volumetric strain control device was used for the study to investigate the effect of the residual strain on the relationship between volumetric strain and effective stress of clean and granite sandy soil. It could be seen an insignificant difference in the volumetric strain after liquefaction under various residual shear strain conditions in the case of clean sand. On the other hand, in granite sandy soil, the volumetric strain after liquefaction was small when the lower level of the residual shear strain was applied. And, the residual shear strain during cyclic shear affected the shape of the relation curve between effective stress and volumetric strain as well.

• Journal of the Korean Geosynthetics Society
• /
• v.20 no.4
• /
• pp.113-124
• /
• 2021

Underground environmental infrastructure and energy production facilities, which are recognized as avoidable facilities such as landfills, are emerging as an important social issue due to urbanization and economic growth. In order to safely construct a large-scale plant facility in the underground space, it is necessary to increase the utilization of the limited space layout and minimize unnecessary columns. In this study, the plant modularization method(Pipe Rack Module) was reviewed to solve the problems of work constraints, assembly and demolition, process system interconnection, and maintenance that occur when plant facilities are underground. In addition, plant module analysis was performed by applying various load conditions (earthquake load, device load, earth pressure load, etc.) to improve spatial layout usability and secure structure stability. Based on the analysis results under various boundary condition, the implications regarding the minimum installation interval and module arrangement (draft) of basic modules required for the construction of an underground combined plant were derived.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.137-147
• /
• 2023

LiDAR is used in autonomous driving and various industrial fields to measure the size and distance of an object. In addition, the sensor also provides intensity images based on the amount of reflected light. This has a positive effect on sensor data processing by providing information on the shape of the object. LiDAR guarantees higher performance as the resolution increases but at an increased cost. These conditions also apply to LiDAR intensity images. Expensive equipment is essential to acquire high-resolution LiDAR intensity images. This study developed artificial intelligence to improve low-resolution LiDAR intensity images into high-resolution ones. Therefore, this study performed parameter analysis for the optimal super-resolution neural network model. The super-resolution algorithm was trained and verified using 2,500 LiDAR intensity images. As a result, the resolution of the intensity images were improved. These results can be applied to the autonomous driving field and help improve driving environment recognition and obstacle detection performance