• Journal of the Korean Geosynthetics Society
• /
• v.19 no.4
• /
• pp.41-50
• /
• 2020

Since cracks in concrete structures expedite corrosion of reinforced concrete over a long period of time, regular on-site inspections are essential to ensure structural usability and prevent degradation. Most of the safety inspections of facilities rely on visual inspection with naked eye, so cost and time consuming are severe, and the reliability of results differs depending on the inspector. In this study, a portable measuring device that can be used for safety diagnosis and maintenance was developed as a device that measures the width and length of concrete cracks through image analysis of cracks photographed with a camera. This device captures the cracks found within a close distance (3 m), and accurately calculates the unit pixel size by laser distance measurement, and automatically calculates the crack length and width with the image processing algorithm developed in this study. In measurement results using the crack image applied to the experiment, the measurement of the length of a 0.3 mm crack within a distance of 3 m was possible with a range of about 10% error. The crack width showed a tendency to be overestimated by detecting surrounding pixels due to vibration and blurring effect during the binarization process, but it could be effectively corrected by applying the crack width reduction function.

• Journal of Korean Society of Forest Science
• /
• v.102 no.1
• /
• pp.90-96
• /
• 2013

This study was conducted to investigate a stability trend within 6 above average and 4 blow average erosion control dams, which were selected by The Korean Association of Soil and Water Conservation and were built in 1990s in Gyeonggi and Gangwon Province. The study was aimed to measure rebound hardness of upstream face, flood way and downstream face from those dams selected by using 'Concrete Test Hammer'. The main purposes of the study are selection of compression strength prediction equation and scope of wavelength, which successfully demonstrate non-destructive test results for erosion control dams. There is an opportunity to increase disaster prevention ability when stability vulnerability of concrete erosion control dam is detected in a timely manner. Results of the compression strength investigation express that there is a consistency with visual inspection of stability that has been processed by The Korean Association of Soil and Water Conservation. We concluded that a prediction equation, which was developed by Architectural Institute of Japan (AIJ), shows highest suitability in Korean erosion control dams when stability investigation is performed. The detailed criteria for the test result are 'stable', 'detail inspection required' and 'poor' for over 300 $kgf/cm^2$, 250~300 $kgf/cm^2$ and below 250 $kgf/cm^2$ respectively. Standards for stability of Korean erosion control dam and a compression strength prediction equation (that corresponds to the standards of the stability) should be established on the basis of chronological data of erosion control dam compression strength. Systematical approach for stability inspection that carries out remodeling or repair when problem on erosion control structures are detected through visual inspection and simple stability test, is necessary for the future disaster prevention.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.2
• /
• pp.281-290
• /
• 2022

In Korea, the number of national facilities for which a safety inspection is mandatory is increasing, and a safer safety inspection method is needed. This study aimed to increase the efficiency of the bridge safety inspection by enabling rapid exterior inspection while securing the safety of inspectors by using drones to perform the safety inspections of bridges, which had mainly relied on visual inspections. For the research, the Youngjong Grand Bridge in Incheon was selected as a test bed and was divided into four parts: the warren truss, suspension bridge main cable, main tower, and pier. It was possible to establish a five-step standard procedure for drone safety inspections. The step-by-step contents of the standard procedure obtained as a result of this research are: Step 1, facility information collection and analysis, Step 2, analysis of vulnerable parts and drone flight planning, Step 3, drone photography and data processing, Step 4, condition evaluation by external inspection, Step 5, building of external inspection diagram and database. Therefore, if the safety inspections of civil engineering facilities including bridges are performed according to this standard procedure, it is expected that these inspection can be carried out more systematically and efficiently.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.65-68
• /
• 2021

본 연구에서는 Dilated U-Net 기반의 이미지 복원기법을 통해 콘크리트 균열 추출 성능 개선 방안을 제안한다. 콘크리트 균열은 구조물의 미관상의 문제뿐 아니라 추후 큰 안전사고의 원인이 될 수 있어 초기대응이 중요하다. 현재는 점검자가 직접 육안으로 검사하는 외관 검사법이 주로 사용되고 있지만, 이는 정확성 및 비용, 시간, 그리고 안전성 면에서 한계를 갖고 있다. 이에 콘크리트 구조물 표면에 대해 획득한 영상 처리 기법을 사용한 검사 방식 도입의 관심이 늘어나고 있다. 또한, 딥러닝 기술의 발달로 딥러닝을 적용한 영상처리의 연구 역시 활발하게 진행되고 있다. 본 연구는 콘크리트 균열 추개선출 성능 개선을 위해 Dilated U-Net 기반의 이미지 복원기법을 적용하는 방안을 제안하였고 성능 검증 결과, 기존 U-Net 기반의 정확도가 98.78%, 조화평균 82.67%였던 것에 비해 정확도 99.199%, 조화평균 88.722%로 성능이 되었음을 확인하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.475-475
• /
• 2021

전 세계적으로 기후변화에 따른 예측하기 어려운 국지성호우의 발생빈도가 증가하고 있으며, 수반되는 돌발홍수를 사전에 대비하기 위해 하천운영의 중요성이 강조되고 있다. 일반적인 하천 시설물 점검 및 보수 계획 수립 시, 시설물의 중요도나 하천의 현황 보다는 행정적인 편의성을 고려하여 구간에 따른 육안 점검 등을 통해 일률적으로 수행되고 있다. 그러나 현재 우리나라의 하천 시설물 중 약 40% 이상이 준공연수가 30년을 초과한 것으로 파악되고 있으며, 노후화된 하천 시설물의 정확한 상태평가에 따른 보수보강 계획수립이 필요한 실정이다. 이를 위해서는 하천 시설물 관리에 있어 다양한 문제점과 관련된 자료를 수집하여 DB화하고, 모델링 및 정밀검사 등을 통해 다양한 각도에서 분석되어야 한다. 본 연구에서는 시설물통합정보관리시스템(Facilty Management System; FMS)에서 제공하는 하천 시설물 관리대장 중 테스트베드에 위치한 수문의 개별부재에 대한 상태 평가지수를 활용하여 시설물의 생애주기를 통합적으로 고려할 수 있는 성능평가모델을 제안하였다. 본 연구에서 제안된 성능평가모델은 하천 시설물의 합리적인 관리체계를 통해 분석된 결과로부터 시설관리자가 하천 관리 및 계획수립에 있어 의사결정을 할 수 있도록 정보를 제공하는 지원 도구로 활용 가능할 것으로 판단된다.

• The Journal of Engineering Geology
• /
• v.25 no.2
• /
• pp.227-235
• /
• 2015

In recent years, owing to the frequent occurrence of natural disasters, the inspection and maintenance of structures have become increasingly important on a national scale. However, because most structural inspections are carried out manually, and due to the lack of objectivity in data acquisition, quantitative data are not always available. As a result, researchers are seeking ways to collect and standardize survey data using terrestrial laser scanning, thereby bypassing the limitations associated with visual investigations. However, field data acquired using a laser scanner have been required to measure changes in structure geometry resulting from passive deterioration. In this study, we demonstrate that it is possible to identify the processes of structural deterioration (e.g., efflorescence, leakage, delamination) using intensity data from terrestrial laser scanning. Additionally, we confirm the viability of automated classification of alteration type and objectification of the polygon area by establishing intensity characteristics. Finally, we show that our method is effective for structural inspection and maintenance.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.746-753
• /
• 2022

Purpose: The purpose of this study is to review the safety of small tunnels for food storage excavation in the 1960s~1970s and to improve the stability of small tunnels. Method: A visual inspection and a hammer test were used to conduct safety tests, and the visual inspection is one of the tests conducted for non-destructive testing, and the hammer test is one of the types of hitting methods of rebound hardness. Result: According to the integrated analysis of the survey area data, there are generally good appearance, but there are many small cracks and complex geological conditions, requiring continuous observation and attention. Seven of the 23 tunnels require safety diagnosis, one collapse, one safe, and 14 require continuous observation and attention. Conclusion: All parts of small tunnels should be checked and recorded from time to time, and stability is expected to be improved when reinforcing small tunnels proposed in this study.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.9-12
• /
• 2021

드론 Photogrammetry는 높은 기술적 활용가치가 있는 기술로서, 결과물로 생성하는 3D 디지털 공간정보 모델이 시설물의 비육안 안전점검 및 진단에 활용될 수 있을 뿐만 아니라 디지털 트윈 구축을 위한 가장 기초적이고 핵심적인 수치 데이터를 제공하기 때문이다. 본 연구에서는 드론 Photogrammetry의 적정 품질을 구현하기 위한 임무비행의 다양한 영향인자에 대해 고찰하였다. K-water연구원 누수탐사실습장을 대상으로 드론 사진 촬영 시 비행고도, 비행속도, 중첩도, 카메라 Pitch각의 영향에 대해 연구를 수행하였다. 본 연구에서 비행시간에 영향을 미치는 인자로서 비행고도, 중첩도, 비행속도의 순으로 중요도가 있음을 알 수 있었다. 드론 임무 비행 시 후처리 결과에 가장 큰 영향을 미치는 인자는 중첩도로 나타났다. 중첩도 60% 임무비행은 3D 모델의 geometry 왜곡이 큰 편으로 나타났다. 비행 고도는 GSD (Ground Sampling Distance)와 직접 연계되므로 중요하며, 낮은 고도일수록 높은 품질의 모델링이 가능하다. April Tag를 통한 지상기준점 자동 패턴 인식 기능은 후처리 과정에서 시간 절약이 가능하여 유용하였다. 비행속도에 의한 결과물의 품질은 큰 차이가 없었으나, 수직 구조물의 모서리 부분에 다소 차이가 있었다. 짐벌 Pitch각도에 의한 정사영상 품질의 차이는 크지 않았으나 수직구조물과 평면적 구조물에 따라 각기 다른 촬영각도를 적용하는 것이 바람직하다. 본 연구성과는 향후 보다 다양한 환경에서의 데이터 수집을 통해 최적 디지털 현실 모델링에 기여할 것으로 판단된다.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.35-42
• /
• 2020

In this study, we propose a crack detection method using limited data with a U-Net based image inpainting technique that is a modified unsupervised anomaly detection method. Concrete cracking occurs due to a variety of causes and is a factor that can cause serious damage to the structure in the long term. In general, crack investigation uses an inspector's visual inspection on the concrete surfaces, which is less objective in judgment and has a high possibility of human error. Therefore, a method with objective and accurate image analysis processing is required. In recent years, the methods using deep learning have been studied to detect cracks quickly and accurately. However, when the amount of crack data on the building or infrastructure to be inspected is small, existing crack detection models using it often show a limited performance. Therefore, in this study, an unsupervised anomaly detection method was used to augment the data on the object to be inspected, and as a result of learning using the data, we confirmed the performance of 98.78% of accuracy and 82.67% of harmonic average (F1_Score).

• Journal of the Korean Geotechnical Society
• /
• v.28 no.2
• /
• pp.15-21
• /
• 2012

It is difficult to determine the strength and the permeability of a soil levee quantitatively because the damages of a levee have been evaluated only by visual inspection in Korea. Therefore, it is necessary to develop a simplified measurement device for measuring the strength and permeability of a levee. In this paper, a new in-situ permeability measuring device which can measure strength and permeability based on GWP is developed and its applicability to the field permeability test of a soil levee is introduced. From the laboratory and in-situ experiments, the new measuring device has the potential of measuring the soil permeability simply and accurately.