• Geophysics and Geophysical Exploration
• /
• v.6 no.3
• /
• pp.138-142
• /
• 2003

Crosswell seismic data were acquired in three sections crossing a tunnel of 3 different types; one was empty, another was ailed by sand, and the other was filled by rock debris. Both the P- and S-wave first arrivals were picked and the traveltime tomography was conducted to generate the P- and S- wave velocity tomograms on the all three sections. Among six tomograms, only one tomogram shows a low velocity zone that can be interpreted as a tunnel image. The tomogram is the P wave velocity image of a section that crosses an empty tunnel. The result of numerical analysis for the spatial resolution of the traveltime tomography was consistent to this finding.

• The Journal of Engineering Geology
• /
• v.17 no.4
• /
• pp.567-576
• /
• 2007

In order to assess the on-site applicability of 3D absolute displacement monitoring of tunnel using digital photogrammetry, the displacement of the optical target placed at the measurement section was investigated, as planned in the OO tunnel construction site. The targets on 3 measurement lines only were considered for each point of measurement for the reconstruction of 3D cubic model for the digital vision monitoring. For each 3D model, 3 or more images have to be obtained at each point. On the last 2 measurement lines, 6 targets (crown, left and right walls) were continuously overlapped to construct 3D models so that 6 or more apices can be shared by 2 3D models. In order to compare the measurement methods of 3D absolute displacements in tunnel excavation, i. e, total station and digital image measurement, both the digital image measurement and optical measurement were conducted for 10 times in the same work section. The time and measurement results of both methods were compared.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.11 no.4
• /
• pp.361-371
• /
• 2009

Resistivity tomography is very effective geophysical method to find out the resistivity distribution and its change in time around a tunnel. Thus, the resistivity tomogram can provide helpful information which is necessary for the effective maintenance of the tunnel. However, an air filled tunnel severely distorts tomography data, especially when the current or potential electrode is placed near the tunnel. Moreover, the distortion can often lead to misinterpretation of tomography monitoring data. To solve these problem, we developed a resistivity modeling and time-lapse inversion program which include a tunnel. In this study, using the developed program we assured that the inversion including a tunnel gives much more accurate image around a tunnel, compared with the conventional tomogram where the tunnel is not included. We also confirmed that the time-lapse inversion of resistivity monitoring data defines well resistivity changed areas around a tunnel in time.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.3-4
• /
• 2021

폐쇄된 터널 내부에서는 사고가 일어날 경우 외부에서는 터널 내 상황을 알 수가 없어 경미한 사고라 하더라도 대형 후속 2차 사고로 이어질 가능성이 크다. 또한영상탐지로사고 상황의 오검출을 줄이기 위해서, 본 연구에서는기존의 많은 CNN 모델 중 보유한 데이터에 가장 적합한 모델을 선택하는 과정에서 가장 좋은 성능을 보인 VGG16 모델을 전이학습 시키고 fully connected layer의 일부 layer에 Dropout을 적용시켜 Overfitting을일부방지하는 CNN 모델을 생성한 뒤Yolo를 이용한 영상 내 객체인식, OpenCV를 이용한 영상 프레임 내에서 객체의ROI를 추출하고이를 CNN 모델과 비교하여오검출을 줄이면서 사고를 검출하는 시스템을 제안하였다.

• Geophysics and Geophysical Exploration
• /
• v.11 no.4
• /
• pp.302-309
• /
• 2008

ERT imaging, especially 3-D method, is a very powerful means to obtain a very high resolution image of the subsurface for geotechnical or hydrogeological problems. In this paper, we introduce two examples of successful case histories, where the imaging targets were three-dimensional. First example is the case of 3-D fracture imaging for hydrogeologic application. In this example, the borehole deviation was a critical problem in the ERT imaging and we could obtain real 3-D attitude of fracture system by including the borehole deviation in the inversion. In the second case, we did field experiment to image the empty tunnel with the size of $2m{\times}2m$ and the target was very clearly imaged in 3-D space. In these examples, we could show that 3-D ERT imaging is a very powerful tool for the 3-D subsurface imaging and the method can provide enhanced imaging capabilities especially for the 3-D targets such as fractures and cavities or tunnel.

• Proceedings of the Korea Contents Association Conference
• /
• 2012.05a
• /
• pp.291-292
• /
• 2012

본 연구는 여러 가지 센서를 이용하여 자동차 전용 도로터널의 차량 사고시의 음향을 인식하여 사고인식률을 높이는 화재 예고 시스템에 관한 연구이다. 현행의 CCTV나 자동화재탐재설비에서 감지하는 열센서나 영상전송자료를 파악하기에 앞서, 이차적 재해 가능성을 유의미한 수준에서 미리 예고하고 대응할 수 있는 사전예고시스템을 구성하였다. 유선설치기반의 센서로 대부분 구성된 도로터널 내에서 비교적 설비가 저렴한 무선센서를 사용함으로서 기존 터널에서의 적용성을 증대시켰다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.17 no.1
• /
• pp.1-9
• /
• 2015

This paper introduces the development of imaging luminance meter which measures the luminances of external/internal road tunnel. The developed imaging luminance meter complies with both L20 method and Veiling luminance method of the international standards, CIE88. In this paper the L20 method is mainly presented because most of tunnels currently adapt L20 method. The developed system has an embedded computer to operate at stand-alone. The system has a ethernet port, a heater, a fan, a defroster, a wiper and sun shielder. Compensation algorithm is applied for correcting non-linear responses to the luminance and integration time. The accuracy of measurement is less than 1% when it calibrated at the public certification institute. The developed system was also tested at the real field, road tunnel. The test results were very similar with the reference luminance meter and showed that the developed system operates well at the real field. Partial sensor saturations were happened to show the less luminance, because there were the high reflecting objects in the real field. Further study should be followed for high luminance measurement.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.607-608
• /
• 2011

In this paper, we propose stopped vehicle detection algorithm in the tunnel. It is shown that our method distinguished objects from background estimated image, and then detected stopped vehicles efficiently based on the experimental analysis about the color information of their lamps. The simulation results show the detection rate is achieved over 95% in the tunnel image.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.263-266
• /
• 2004

본 논문에서는 터널 구조물에서 발생하는 균열의 인식과 이에 대한 정보를 획득하기 위한 방법에 대한 연구를 수행하였다. 터널 구조물에서 발생하는 균열의 경우, 건설 분야의 특수성 때문에 기존의 경계점 인식(edge detection) 알고리즘을 적용하는 경우 정밀도 저하의 문제가 발생한다. 이러한 문제점을 해결하고 더불어 정밀도를 향상시킬 수 있는 방법으로 영상에서 균열을 인식하는 균열 인식 단계와 인식된 균열의 길이, 두께 등을 측정하는 균열 정보 획득 단계로 구분하였다. 균열 인식 단계에서는 균열의 시작점과 끝점을 기준으로 휴리스틱(Heuristic) 알고리즘을 사용하여 픽셀 값의 분포에 따라 균열의 중심선을 계산하여 균열을 인식한다. 균열 정보 획득 단계에서는 균열 인식 단계에서 얻은 정보를 통해 균열의 길이, 진행 방향 정보, 그리고 균열의 두께를 계산한다. 균열의 길이 및 진행 방향 정보는 균열 인식 단계에서 얻어진 정보를 통하여 계산하며, 균열 두께 측정은 각 픽셀의 누적 값을 이용하여 계산하는 원형 검출기(Daugman 알고리즘)를 변형하여 사용하였다.

• Tunnel and Underground Space
• /
• v.21 no.6
• /
• pp.439-449
• /
• 2011

The characteristics of rock fractures for engineering rock classification are investigated by analyzing three dimensional point cloud generated from adjusted digital images of a tunnel face during construction and the tunnel is reinforced based on the supporting pattern suggested by the RMR and the Q system using parameters extracted from those images. As results, it is possible saving time required from face mapping to tunnel reinforcing work, enhancing safety during face mapping work in tunnels and reliability of both the mapping information and selecting supporting pattern by storing the files of digital images and related information which can be checked again, if necessary sometime in the future.