• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.302-302
• /
• 2021

지하차도의 경우 국지 및 돌발홍수가 발생할 경우 대부분 침수됨에도 불구하고 2020년 7월 23일 부산 지역에 밤사이 시간당 80mm가 넘는 폭우가 발생하면서 순식간에 지하차도 천장까지 물이 차면서 선제적인 차량 통제가 우선적으로 수행되지 못하여 미처 대피하지 못한 3명의 운전자 인명사고가 발생하였다. 수재해를 비롯한 재난 관리를 빠르게 수행하기 위해서는 기존의 정부 및 관주도 중심의 단방향의 재난 대응에서 벗어나 정형 데이터와 비정형 데이터를 총칭하는 빅데이터의 통합적 수집 및 분석을 수행이 필요하다. 본 연구에서는 부산지역의 지하차도와 인접한 지하터널 CCTV 자료(센서)를 통한 재난 발생 시 인명피해를 최소화 정보 제공을 위한 Object Detection(객체 탐지)연구를 수행하였다. 지하터널 침수가 발생한 부산지역의 CCTV 영상을 사용하였으며, 영상편집에 사용되는 CCTV 자료의 음성자료를 제거하는 인코딩을 통하여 불러오는 영상파일 용량파일 감소 효과를 볼 수 있었다. 지하차도에 진입하는 물체를 탐지하는 방법으로 YOLO(You Only Look Once)를 사용하였으며, YOLO는 가장 빠른 객체 탐지 알고리즘 중 하나이며 최신 GPU에서 초당 170프레임의 속도로 실행될 수 있는 YOLOv3 방법을 적용하였으며, 분류작업에서 보다 높은 Classification을 가지는 Darknet-53을 적용하였다. YOLOv3 방법은 기존 객체탐지 모델 보다 좀 더 빠르고 정확한 물체 탐지가 가능하며 또한 모델의 크기를 변경하기만 하면 다시 학습시키지 않아도 속도와 정확도를 쉽게 변경가능한 장점이 있다. CCTV에서 오전(일반), 오후(침수발생) 시점을 나눈 후 Car, Bus, Truck, 사람을 분류하는 YOLO 알고리즘을 적용하여 지하터널 인근 Object Detection을 실제 수행 하였으며, CCTV자료를 이용하여 실제 물체 탐지의 정확도가 높은 것을 확인하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.6 no.3
• /
• pp.35-43
• /
• 2001

Imposing electromagnetic field using transmitter of buried metal object in skill that detect underground object sensing person atonement in being widowed on the land being magnetized upside numerical value of buried metal object searching way used most widely current by skill be. This paper proposed about mode and detection system of underground object that sense the changed magnetic and judge real radish buried metal object sign of the cook because this treatise forms magnetic in land and design and composition of display device. Also, through simulation of detection system of underground object, showed that can measure radish judgment sign of the cock of underground object

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.189-200
• /
• 2022

Ground subsidence on urban roads is a social issue that can lead to human and property damages. Therefore, it is crucial to detect underground cavities in advance and repair them. Underground cavity detection is mainly performed using ground penetrating radar (GPR) surveys. This process is time-consuming, as a massive amount of GPR data needs to be interpreted, and the results vary depending on the skills and subjectivity of experts. To address these problems, researchers have studied automation and quantification techniques for GPR data interpretation, and recent studies have focused on deep learning-based interpretation techniques. In this study, we described a hyperbolic event detection process based on deep learning for GPR data interpretation. To demonstrate this process, we implemented a series of algorithms introduced in the preexisting research step by step. First, a deep learning-based YOLOv3 object detection model was applied to automatically detect hyperbolic signals. Subsequently, only hyperbolic signals were extracted using the column-connection clustering (C3) algorithm. Finally, the horizontal locations of the underground cavities were determined using regression analysis. The hyperbolic event detection using the YOLOv3 object detection technique achieved 84% precision and a recall score of 92% based on AP50. The predicted horizontal locations of the four underground cavities were approximately 0.12 ~ 0.36 m away from their actual locations. Thus, we confirmed that the existing deep learning-based interpretation technique is reliable with regard to detecting the hyperbolic patterns indicating underground cavities.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.2
• /
• pp.131-137
• /
• 2016

In this paper, a feasibility on a ground-penetrating radar for detecting subsurface cavities near buried pipes has been investigated. The experimental setup was implemented by employing an impulse ground-penetrating radar system, a xy Cartesian coordinate robot, an underground material filled tank, a metal pipe and a simulated cavity model. In particular, the simulated cavity model was constructed by packing Styrofoam chips and balls, which have both similar electrical properties to an air-filled cavity and a solid shape. Through typical three experiments, B-scan data of the radar have been acquired and displayed as 2-D gray-scale images. According to the comparison of B-scan images, we show that the subsurface cavities near the buried pipes can be detected by using the radar survey.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2001.09a
• /
• pp.94-103
• /
• 2001

An experiment was conducted using a sand and gravel-filled tank model, to investigate the influence on the GPR response of vadose zone gasoline vapor phase effects and residual gasoline distributed by a fluctuating water table. After background GPR measurements were made with only water in the tank, gasoline was injected into the bottom of the model tank to simulate a subsurface discharge from a leaking pipe or tank. Results from the experiment show the sensitivity of GPR to the changes in the moisture content and its effectiveness for monitoring minor fluctuation of the water table. The results also demonstrate a potential of GPR for detecting possible vapor phase effects of volatile hydrocarbons in the vadose zone as a function of time, and for detecting the effects of residual phase of hydrocarbons in the water saturated system. In addition, the results provide the basis for a strategy that has the potential to successfully detect and delineate LNAPL contamination at field sites where zones of residual LNAPL in the water saturated system are present in the subsurface.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.92-92
• /
• 2020

최근 지진 발생 빈도와 규모가 증가함에 따라 지진재해에 취약한 지하구조물의 내진성능 향상 및 신속한 복구에 관한 연구가 활발히 진행되고 있다. 대표적인 지하구조물 중 하나인 상수관망은 음용수를 안전하고 원활하게 공급하는 사회기반시설물로써 대부분의 시설물이 지하에 매설되어 있어 지진재해에 매우 취약하다. 지진으로 인해 상수관망 내 누수 및 파손 등의 피해가 발생할 경우, 물 공급이 중단되어 경제적 손실과 사회 전반적인 불편이 우려되므로 피해 관로의 신속한 파악과 복구가 이루어져야 한다. 상수관로에 발생하는 피해는 크게 누수와 파손으로 구분할 수 있다. 관로가 파손된 경우 용수가 표층으로 새어나오기 때문에 탐지가 용이하지만, 누수의 경우 표층으로 드러나는 피해가 없어 탐지 및 수리가 어려운 단점이 있다. 이러한 누수가 장기간 방치될 경우, 해당 시스템의 유수율 감소로 인한 경제적인 손실과 더불어 공급수압의 저하, 그리고 오염물 침투의 위험이 존재한다. 이러한 피해를 막기 위해서는 신속히 누수 지점을 파악한 후, 피해 관로의 교체 혹은 보수가 이루어져야 한다. 현장에서 누수를 직접 탐지하는 방법은 정확도가 높은 반면, 많은 인력과 장비 그리고 비용이 소모되는 단점이 존재한다. 따라서 현장 누수탐지에 앞서 컴퓨터를 이용한 간접 누수탐지 기법이 지속적으로 개발될 필요가 있다. 본 연구에서는 현장 누수탐지의 탐지효율을 향상시키기 위해 수압, 유량 등의 관측 데이터와 수리해석 모의 및 최적화 기법을 활용한 컴퓨터 기반의 다중누수 탐지모형을 개발하였다. 개발 모형은 국내에서 운영 중인 소블럭 상수관망시스템에 적용하여 검증하고 탐지효율을 분석하였다. 컴퓨터 모의를 이용한 다중누수 탐지모형은 지진이나 홍수와 같은 대규모 재난 발생 후, 상수관망시스템의 신속한 복구 및 운영 정상화를 위한 도구로 활용될 수 있을 것으로 기대한다.

• Journal of the Korean Geophysical Society
• /
• v.6 no.4
• /
• pp.261-268
• /
• 2003

Lots of various utilities are buried under the surface. The effective management of underground utilities is becoming the very important subject for the harmonious administration of the city. Ground Penetrating Radar(GPR) survey including other various underground survey methods, is mainly used to detect the position and depth of buried underground utilities. However, GPR is not applicable, under the circumstances of shallow depth and places, where subsurface materials are inhomogeneous and are composed of clay, salt and gravels. The aim of this study is to overcome these limitations of GPR and other underground surveys. High-frequency electromagnetic (HFEM) method is developed for the non-destructive precise deep surveying of underground utilities. The method is applied in the site where current underground surveys are useless to detect the underground big pipes, because of poor geotechnical environment. As a result, HFEM survey was very successful in detecting the buried shallow and deep underground pipes and in obtaining the geotechnical information, although other underground surveys including GPR were not applicable. Therefore this method is a promising new technique in the lots of fields, such as underground surveying and archaeology.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.1
• /
• pp.61-67
• /
• 2018

The effects of subsurface inhomogeneities on the detection of buried metal pipes in ground-penetrating radar(GPR) signals are investigated numerically. To model the electrical properties of the subsurface inhomogeneities, the continuous random media(CRM) generation technique is introduced. For the electromagnetic simulation of GPR signals, the finite-difference time-domain(FDTD) method is implemented. As a function of the standard deviation and the correlation length of the relative permittivity distribution for a randomly inhomogeneous ground, the GPR signals of the buried metal pipes are compared using numerical simulations. As the subsurface inhomogeneities increase, the GPR signals of the buried pipes are distorted because of the effect of the subsurface clutter.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2005.05a
• /
• pp.181-186
• /
• 2005

Gravity method produces subsurface density distribution, which is direct information of soundness of basement. Therefore, microgravity is one of the most effective method for detections of limestone cavities, abandoned mine-shafts and other tunnels, The paper show the effectiveness of microgravity by three different field cases.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.39-46
• /
• 2019

In recently years, it has become important to detect underground objects of various marterials including metals, such as detecting the location of sink holes and pipe. For this reason, ground penetrating radar(GPR) technology is attracting attention in the field of underground detection. GPR irradiates the radar wave to find the position of the object buried underground and express the reflected wave from the object as image. However, it is not easy to interpret GPR images because the features reflected from various objects underground are similar to each other in GPR images. Therefore, in order to solve this problem, in this paper, to estimate the piping position in the GRP image according to the threshold value using the CNN (Convolutional Neural Network) model based on deep running, which is widely used in the field of image recognition, As a result of the experiment, it is proved that the pipe position is most reliably detected when the threshold value is 7 or 8.