• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.499-504
• /
• 2006

터널 내 화재 발생 시 대규모의 인명, 재산 피해가 발생하는데 이러한 상황을 조기에 탐지함으로써 피해를 최소화하기 위한 시스템이 필요하다. 또한 터널 내 설치된 CCTV를 사람이 24시간 감시하기에는 너무 어려운 점이 많다. 이에 따라 적절한 영상 처리를 통한 화염 및 연기 검출 시스템을 통해 경보를 알려줄 경우, 보다 편리하고 사람이 모니터 앞에 없을 때 화재 발생 시 화재를 검출할 수 있어 피해를 최소화 할 수 있다. 본 논문에서는 영상처리 기법을 이용하여 터널 안에서 발생한 화재 및 연기를 고속으로 탐지하기 위한 알고리즘을 제안하였다. 터널 안에서의 화재 탐지는 차량 조명 및 터널내의 조명등과 같은 여러 가지 상황에 의해 산불 탐지 알고리즘과 다른 독자적인 알고리즘의 개발이 요구된다. 본 논문에서 제시한 두 가지 알고리즘은 기존 알고리즘보다 정확한 위치 탐지와 초기 단계에서의 탐지가 가능하도록 되었다. 또한 우리는 실험 결과를 통해 각각의 성능을 비교함으로써 제시한 알고리즘의 타당성을 보여주었다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.5
• /
• pp.813-827
• /
• 2017

Surveillance cameras installed in tunnels capture the various video frames effected by dynamic and variable factors. In addition, localizing and managing the cameras in tunnel is not affordable, and quality of capturing frame is effected by time. In this paper, we introduce a new method to detect and track the vehicles in tunnel by using surveillance cameras installed in a tunnel. It is difficult to detect the video frames directly from surveillance cameras due to the motion blur effect and blurring effect on lens by dirt. In order to overcome this difficulties, two new methods such as Differential Frame/Non-Maxima Suppression (DFNMS) and Haar Cascade Detector to track cars are proposed and investigated for their feasibilities. In the study, it was shown that high precision and recall values could be achieved by the two methods, which then be capable of providing practical data and key information to an automatic accident detection system in tunnels.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.3
• /
• pp.419-432
• /
• 2019

Most of deep learning model training was proceeded by supervised learning, which is to train labeling data composed by inputs and corresponding outputs. Labeling data was directly generated manually, so labeling accuracy of data is relatively high. However, it requires heavy efforts in securing data because of cost and time. Additionally, the main goal of supervised learning is to improve detection performance for 'True Positive' data but not to reduce occurrence of 'False Positive' data. In this paper, the occurrence of unpredictable 'False Positive' appears by trained modes with labeling data and 'True Positive' data in monitoring of deep learning-based CCTV accident detection system, which is under operation at a tunnel monitoring center. Those types of 'False Positive' to 'fire' or 'person' objects were frequently taking place for lights of working vehicle, reflecting sunlight at tunnel entrance, long black feature which occurs to the part of lane or car, etc. To solve this problem, a deep learning model was developed by simultaneously training the 'False Positive' data generated in the field and the labeling data. As a result, in comparison with the model that was trained only by the existing labeling data, the re-inference performance with respect to the labeling data was improved. In addition, re-inference of the 'False Positive' data shows that the number of 'False Positive' for the persons were more reduced in case of training model including many 'False Positive' data. By training of the 'False Positive' data, the capability of field application of the deep learning model was improved automatically.

• Geophysics and Geophysical Exploration
• /
• v.13 no.1
• /
• pp.96-101
• /
• 2010

A pulse radar system has been developed recently to detect dormant underground tunnels that are deeply located at depths of hundreds of metres. To check the ability of the radar system to detect an obliquely oriented tunnel, five different borehole pairs in the tunnel test site were chosen so that the horizontal lines-of-sight cut the tunnel axis obliquely, in $15^{\circ}$ steps. The pulse radar signatures were measured over a depth range of 20 m around the centre of the air-filled tunnel. Three canonical parameters, consisting of the arrival time, attenuation, and dispersion time were extracted from the first and second peaks of the measured radar signatures. Using those parameters, the radar system can detect obliquely oriented tunnels at various angles up to 45 from the transmitter-receiver line of sight.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.4
• /
• pp.59-70
• /
• 2008

In this paper, we proposed image processing technique for automatic real-time fire and smoke detection in tunnel environment. To avoid the large scale of damage of fire occurred in variety environments, it is purposeful to propose many studies to minimize and to discover the incident as fast as possible. But we need new specific algorithm because tunnel environment is quite different and it is difficult to apply previous fire detection algorithm to tunnel environment. Therefore, in this paper, we proposed specific algorithm which can be applied in tunnel environment. To minimize false detection in tunnel we used color and motion information. And it is possible to detect exact position in early stage with detection, test, verification procedures. In addition, by comparing properties of each algorithm throughout experiment, we have proved the validity and efficiency of proposed algorithm.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.9 no.1
• /
• pp.19-28
• /
• 2007

Tunnel management is a time-consuming and expensive task. In particular, visual analysis of tunnel inspection often requires extended time and cost and shows problems on data gathering, storage and analysis. This study proposes a new approach to extract information for tunnel management by using a laser scanning technology. A prototype tunnel laser scanner developed was used to obtain point clouds of a railway tunnel surface. Initial processing of laser scanning data was to separate those laser pulses returned from the installations attached to tunnel liner using radiometric and geometric characteristics of laser returns. Once the laser returns from the installations were separated and removed, physically damaged parts on tunnel lining are detected. Based on the plane formed by laser scanner data, damaged parts are detected by analysis of proximity. The algorithms presented in this study successfully detect the physically damaged parts which can be verified by the digital photography of the corresponding location on the tunnel surface.

• Land and Housing Review
• /
• v.14 no.3
• /
• pp.145-155
• /
• 2023

Recently, with the widespread adoption of Building Information Modeling (BIM) technology in the construction industry, various object detection algorithms have been used to verify errors between 3D models and actual construction elements. Since the characteristics of objects vary depending on the type of construction facility, such as buildings, bridges, and tunnels, appropriate methods for object detection technology need to be employed. Additionally, for object detection, initial object images are required, and to obtain these, various methods, such as drones and smartphones, can be used for image acquisition. The study uses a 360° camera optimized for internal tunnel imaging to capture initial images of the tunnel structures of railway and road facilities. Various object detection methodologies including the YOLO, SSD, and R-CNN algorithms are applied to detect actual objects from the captured images. And the Faster R-CNN algorithm had a higher recognition rate and mAP value than the SSD and YOLO v5 algorithms, and the difference between the minimum and maximum values of the recognition rates was small, showing equal detection ability. Considering the increasing adoption of BIM in current railway and road construction projects, this research highlights the potential utilization of 360° cameras and object detection methodologies for tunnel facility sections, aiming to expand their application in maintenance.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.583-598
• /
• 2022

As human-based tunnel inspections are affected by the subjective judgment of the inspector, making continuous history management difficult. There is a lot of deep learning-based automatic crack detection research recently. However, the large public crack datasets used in most studies differ significantly from those in tunnels. Also, additional work is required to build sophisticated crack labels in current tunnel evaluation. Therefore, we present a method to improve crack detection performance by inputting existing datasets into a deep learning model. We evaluate and compare the performance of deep learning models trained by combining existing tunnel datasets, high-quality tunnel datasets, and public crack datasets. As a result, DeepLabv3+ with Cross-Entropy loss function performed best when trained on both public datasets, patchwise classification, and oversampled tunnel datasets. In the future, we expect to contribute to establishing a plan to efficiently utilize the tunnel image acquisition system's data for deep learning model learning.

• 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 Korean Geotechnical Society
• /
• v.39 no.7
• /
• pp.31-37
• /
• 2023

Since tunnels are built underground, it is impossible to check visually the location and degree of deterioration of steel ribs. Therefore, in tunnel maintenance, GPR images are generally used to detect steel ribs. While research on GPR image analysis employing artificial neural networks has primarily focused on detecting underground pipes and road damage, there have been limited applications for analyzing tunnel GPR data, specifically for steel rib detection, both internationally and domestically. In this study, a one-step object detection algorithm called YOLO, based on a convolutional neural network, was utilized to automate the localization of steel ribs using GPR data. The performance of the algorithm is then analyzed. Two datasets were employed for the analysis. A dataset comprising 512 original images and another dataset consisting of 2,048 augmented images. The omission rate, which represents the ratio of undetected steel ribs to the total number of steel ribs, was 0.38% for the model using the augmented data, whereas the omission rate for the model using only the original data was 7.18%. Thus, from an automation standpoint, it is more practical to employ an augmented dataset.