• 한국위험물학회지
• /
• 제2권1호
• /
• pp.6-11
• /
• 2014

There have been frequent chemical leaks over the past 10 years. Particularly, inorganic acids like sulfuric acid, nitric acid, and hydrogen chloride take up 37 % of the total chemical accidents which took place for the past 10 years. When an acid chemical leak happens, fume is generated, diffusing into the air, which might cause serious damage to health of local residents and the environment. However, most of the acid-based chemicals, detecting and analysis methods have not been settled considering the frequency of accidents. In this study, we investigated detection and analysis methods to quickly analyze accident sites and evaluate the impacts on environments. Reviewing local and international test analysis methods of acids suggested that nitric acid, sulfuric acid, hydrogen chloride and hydrogen fluoride can be analyzed with IC. It was also found that UV is better for the analysis of hydrogen fluoride and GC/MS for acrylic acid. The analytical methods suggested in the official test methods basically have limitations of consuming much time at stages of preparation and analysis. Considering prompt responses to chemical accidents, further studies should be done to compare the applicability of rapid monitoring methods such as FT-IR, IMR-MS and SIFT-MS.

• 한국안전학회지
• /
• 제28권4호
• /
• pp.1-7
• /
• 2013

Train accidents can be directly connected to fatal accidents-collision, derailment, Fire, railway crossing accidents-resulting in tremendous human casualties. First of all, the railway derailment is not only related to most of railway accidents but also it can lead to much more catastrophic accompanying train overtured than other factors. Therefore, it is most important factor to ensure railway safety. some foreign countries have applied to the detector machines(e.g., ultrasonic detector car, sleep mode, current detector, optical sensing, optical fiber). Since it was developed in order to prevent train from being derailed. In korea, the existing track method has been used to monitor rail condition using track circuit. However, we found out it impossible for Communication Based Train Control system(CBTC), recent technology to detect rail condition using balise(data transmission devices) without no track circuit. For this reason, it is needed instantly to develop real-time monitoring system used to detect broken rails. Firstly, this paper presents domestic and international statues analysis of rail breaks technology. Secondly, the composition and the characteristics of the real-time monitoring system. Finally, the evidence that this system could assumed the location and type of broken rails was proved by the experiment of prototype and operation line tests. We concluded that this system can detect rail break section in which error span exist within${\pm}1m$.

• 한국인터넷방송통신학회논문지
• /
• 제24권3호
• /
• pp.177-182
• /
• 2024

본 논문에서는 2022년 10월 29일 한국에서 발생한 이태원 압사 사고를 기반으로 미래에 발생할 수 있는 인파 사고에 대하여 군중 밀집으로 인한 위험을 미리 예측하고, 예방하기 위한 목적으로 작성되었다. 단일 CCTV 같은 경우 관리자가 실시간으로 현재 상황을 판별할 수 있지만, 하루 종일 해당 화면만 들여다볼 수 없기 때문에 CCTV 화각으로 촬영된 영상들을 학습한 YOLO v4를 이용하여 객체를 탐지하고, 정해진 군집의 수가 초과하는 순간에 알림을 통해 군중 밀집으로 인한 안전사고를 예방하게 된다. YOLO v4 모델을 사용하게 된 이유는 이전 YOLO 모델보다 더욱 높은 정확성과 빠른 속도로 개선되어, 객체 탐지 기법이 더 용이해졌기 때문이다. 본 서비스를 AI-Hub 사이트에 등재된 CCTV 영상 데이터로 테스트하는 과정을 거치게 된다. 현재 한국에 CCTV는 기하급수적으로 증가하였고, 이를 실제 CCTV에 적용한다면 앞으로 일어나게 될 군중 밀집으로 인한 사고를 비롯한 다양한 사고를 예방할 수 있을 것으로 기대한다.

• 제어로봇시스템학회논문지
• /
• 제22권9호
• /
• pp.699-704
• /
• 2016

In this paper, we propose a development method for a drowsiness detection system using retinex theory and edge information for vehicle safety. Detection of a drowsy state of a driver is very important because the drowsiness of driver is often the main cause of many car accidents. After acquiring an image of the entire face, we executed the pre-process step using the retinex theory. We then applied a technique for the detection of the white pixels using edge information. Experimental results showed that the proposed method improved the accuracy of detecting drowsiness to nearly 98%, and can be used to prevent a car accident caused by the driver's drowsiness.

• 전기학회논문지
• /
• 제59권12호
• /
• pp.2306-2313
• /
• 2010

This paper describes a model based fault detection algorithm for an Advanced ESC System which consists of Hydraulic Control Unit (HCU) with built-in wheel pressure sensors. Advanced ESC System can be used for various value-added functions such as Stop & Go Function and Regenerative Brake Function. Therefore, HCU must have a reliable fault detection. Due to the huge amount of sensor signals, existing specific sensor based fault detection of HCU cannot guarantee the safety of vehicle. However, proposed algorithm dose not require the sensors. When model based fault detection algorithm detects severe failures of the HCU, it warns the driver in advance to prevent accidents due to the failures. For this purpose, a mathematical model is developed and validated in comparison to actual data. Simulation results and data acquired from an actual system are compared with each other to obtain the information needed for the fault detection process.

• 한국빅데이터학회지
• /
• 제7권1호
• /
• pp.15-27
• /
• 2022

최근 5년간 차량 단독사고 교통사고 치사율이 전체 사고보다 4.7배 높은 것으로 집계되고 있으며, 차량 단독사고를 즉각적으로 감지하고 대응할 수 있는 시스템 구축이 필요하다. 본 연구는 가드레일에 충격과 차량 진입 감지 IoT(Internet of Thing) 센서를 부착하여 가드레일 충격 발생 시 사고 현장의 영상을 인공지능 기술을 통해 분석하고 구조기관에 전송하여 빠른 구조작업을 수행하여 피해를 최소화 시킬 수 있는 방법론을 제시한다. 해당 구간 내 차량 진입과 가드레일 충격 감지를 위한 IoT 센서 모듈과 차량 이미지 데이터 학습을 통한 인공지능 기반 객체 탐지 모듈을 구현하였다. 그리고, 센서 정보와 영상 데이터 등을 통합적으로 관리하는 모니터링 및 운영 모듈도 구현하였다. 시스템 유효성 검증을 위하여 충격 감지 전송속도와 자동차 및 사람 객체 탐지 정확도, 센서 장애감지 정확도를 측정한 결과, 모두 목표치를 충족하였다. 향후에는 실제 도로에 적용하여 실데이터를 적용한 유효성을 검증하고 상용화할 계획이다. 본 시스템은 도로 안전 향상에 이바지할 것이다.

• 제어로봇시스템학회논문지
• /
• 제22권5호
• /
• pp.361-366
• /
• 2016

In this paper, we propose a technique for drowsiness detection using the histogram and edge information of eyes. The drowsiness of vehicle drivers is the main cause of many vehicle accidents. Therefore, the checking of eye images in order to detect the drowsiness status of a driver is very important for preventing accidents. In our suggested method, we analyze the changes of the histograms and edges of eye region images, which are acquired using a CCD camera. The experimental results show that our proposed method enhances the accuracy of detecting drowsiness to nearly 99%, and can be used for preventing vehicle accidents caused by the driver's drowsiness.

• International Journal of Railway
• /
• 제3권3호
• /
• pp.106-112
• /
• 2010

Accidents at level crossing have large portion on train accidents, and causes economical loss by train delay and operational interruption. Various safety equipments are employed to reduce the accident at level crossing, but existing warning device, and crossing barrier are simple train-oriented protection equipments. In this paper, intelligent railway level crossing system is proposed to prevent and reduce accidents. For train driver's prompt action, image of level crossing and obstacle warning message are continuously provided to train driver through wireless communication in level crossing control zone. Obstacle warning messages, which are extracted by computer vision processing of captured image at level crossing, are recognized by train driver through message color, flickering and warning sound. It helps train driver to decide how to take an action. Meanwhile, for vehicle driver's attention, location and speed of approaching train are given to roadside equipments. We identified the effect of proposed system through test installation at Sea train and Airport level crossing of Yeong-dong line.

• 한국인터넷방송통신학회논문지
• /
• 제19권1호
• /
• pp.77-83
• /
• 2019

산업 재해의 주요 원인에는 추락사고, 가스 누출 등이 있다. 기존의 안전모와 스마트 디바이스 결합 제품들은 편의성에 초점을 맞춰져 있어 위와 같은 사고를 예방하기 위한 기능이 미흡하다. 본 논문에서는 추락사고 인지와 가스 누출 감지 기능에 중점을 둔 스마트 안전모 개발을 다루었다. 또한 효율적으로 근로자를 관리할 수 있는 관리 시스템을 개발하였다. 이 시스템의 핵심 기능은 근로자의 위험 상태를 감지하여 관리자에게 전달하고 근로자의 상태를 확인하는 것이다. 실험을 통해 가연성 가스 측정 능력의 효용성을 검증하였다. 하지만 보드와 센서의 지속적인 동작으로 인해 상당한 전력 소모가 발견됨에 따라 대용량 배터리로 교체하는 등의 대응 방안이 요구된다는 점도 발견하였다.

• 한국해양공학회지
• /
• 제35권1호
• /
• pp.91-97
• /
• 2021

Marine accidents caused by ships have brought about economic and social losses as well as human casualties. Most of these accidents are caused by small and medium-sized ships and are due to their poor conditions and insufficient equipment compared with larger vessels. Measures are quickly needed to improve the conditions. This paper discusses a video-integrated collision prediction and fall detection system to support the safe navigation of small- and medium-sized ships. The system predicts the collision of ships and detects falls by crew members using the CCTV, displays the analyzed integrated information using automatic identification system (AIS) messages, and provides alerts for the risks identified. The design consists of an object recognition algorithm, interface module, integrated display module, collision prediction and fall detection module, and an alarm management module. For the basic research, we implemented a deep learning algorithm to recognize the ship and crew from images, and an interface module to manage messages from AIS. To verify the implemented algorithm, we conducted tests using 120 images. Object recognition performance is calculated as mAP by comparing the pre-defined object with the object recognized through the algorithms. As results, the object recognition performance of the ship and the crew were approximately 50.44 mAP and 46.76 mAP each. The interface module showed that messages from the installed AIS were accurately converted according to the international standard. Therefore, we implemented an object recognition algorithm and interface module in the designed collision prediction and fall detection system and validated their usability with testing.