• 한국전자통신학회논문지
• /
• 제16권1호
• /
• pp.135-144
• /
• 2021

철도 시스템에서는 인프라 기반의 열차 검측시스템을 통해 열차의 위치정보를 획득하는 것이 일반적이다. 하지만 미검출 및 오검출에 의해 잘못된 위치정보가 제공될 수 있으며, 이로 인한 사고를 야기할 수 있는 문제점을 갖고 있다. 따라서 본 연구에서는 센서 기반 복합항법시스템을 사용하여 열차의 위치정보를 제공하는 방법을 제안한다. 그러나 정확한 정보제공을 위해 복합 항법 시스템의 신뢰성을 검증해야 한다. 따라서 본 논문에서는 실 궤적을 기반으로 기준 궤적과 센서 데이터를 생성하고 다양한 시나리오에 따른 복합 항법 시스템의 성능을 실 궤적 상에서 분석할 수 있는 시뮬레이터를 개발한다.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제53권9호
• /
• pp.545-551
• /
• 2004

CBTC(Communication Based Train Control) System can improve train operation efficiency by realizing moving block system which makes a continuous train interval control in accordance with the position and speed of train. Adopting radio transmission to make a continuous detection of train position and transmit the control data from the ground to a train, CBTC needs dedicated train operation and control algorithm which should be quite different from the conventional track-circuit-based train control system. This paper provides a train operation display and control algorithm for CBTC system in making train interval control, train route control and train supervision. Signalling pattern diagram is devised to analyze the train interval control mechanism of moving block system, and interlocking logic is devised to represent the train route control mechanism of moving block system. For train supervision, train occupation status on railway are displayed by using the segment which virtually divide the whole railway. The proposed method has been successfully applied to the development of CBTC system for the standardized AGT(automatic guided transit) which is under construction now in Korea, and also can be applied to any other CBTC system.

• 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.

• 한국산학기술학회논문지
• /
• 제13권12호
• /
• pp.6098-6104
• /
• 2012

현재 철도 역사의 승객 위험영역과 보안영역 등의 감시를 위해 수십대의 CCTV를 널리 이용하고 있다. 그중에서 가장 빈번한 사고가 발생되는 곳은 승객의 열차 승하차가 이루어지는 승강장 영역이다. 하지만 사고 예방과 신속한 대응을 위해 역무원이 여러 대의 CCTV를 항시 모니터링 하기는 불가능하다. 따라서 위험상황을 자동으로 인지할 수 있는 영상처리 기술을 이용한 승강장 모니터링 시스템이 요구되며, 이를 위해서는 우선적으로 승강장에서의 정확한 열차상태 판단이 필요하다. 본 논문은 비전기반 승강장 모니터링 시스템을 위한 승강장에서의 열차상태에 대한 검지방법을 제안한다. 제안된 검지 방법은 승강장에서의 열차 점유영역을 분석하여 열차의 진입(IN), 진출(OUT), 정지(ON), 없음(OFF)의 4가지 생태를 판별한다. 제안된 검지방법의 성능 평가을 위해 서울메트로 4호선 동작역과 남태령역을 대상으로 열차상태 검지결과를 제시하였다.

• Journal of Information Processing Systems
• /
• 제18권4호
• /
• pp.524-534
• /
• 2022

In this paper, we produce Trash Object Detection (TOD) dataset to solve trash detection problems. A well-organized dataset of sufficient size is essential to train object detection models and apply them to specific tasks. However, existing trash datasets have only a few hundred images, which are not sufficient to train deep neural networks. Most datasets are classification datasets that simply classify categories without location information. In addition, existing datasets differ from the actual guidelines for separating and discharging recyclables because the category definition is primarily the shape of the object. To address these issues, we build and experiment with trash datasets larger than conventional trash datasets and have more than twice the resolution. It was intended for general household goods. And annotated based on guidelines for separating and discharging recyclables from the Ministry of Environment. Our dataset has 10 categories, and around 33K objects were annotated for around 5K images with 1280×720 resolution. The dataset, as well as the pre-trained models, have been released at https://github.com/jms0923/tod.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 1998년도 추계학술대회 논문집
• /
• pp.595-600
• /
• 1998

Train wheels tend to wear abrasion due to frequent Starlings and brakings. They are important factors of train safety and noise. However, it is difficult and inaccurate to measure their shape and profile manually. Profile measurement system of train wheel with image processing is proposed. The system consists of CCD cameras, PCI image grabber board, and PC operated on Windows '95. Image processing algorithms such as filtering, histogram equalization, and edge detection are presented, and some processing results are illustrated.

• 전기학회논문지
• /
• 제65권7호
• /
• pp.1303-1310
• /
• 2016

The track circuit carries out a train detection using a electrical closed loop, and incidentally it detects the rail rupture using the track circuit current flowing rail. However, in the case of the axle counter or the Radio based train control system, it requires a new way for detecting the rail rupture because of not using the track circuit. To solve this problem, it periodically checks non-steady state of rail by the track inspection car. but real-time detection of the rail rupture is impossible. Therefore, this paper analyzed feasibility to realize a real-time detection of rail rupture by using the return current.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.226-231
• /
• 2011

This research was done to prove the optimal position to detect a train reader when using a multiple fusion sensor. The experiment was done using four Train installed RFID Readers located on the train. These readers were read by sensors installed at intervals of 50 meters on the up and down sections of the Line 8, from Amsa station to Moran station. We analyze errors in the recognition range according to the Tag's number of recognition due to RFID of train speed, and propose a method of estimation for an accurate estimation of the position of train At this the Least-Squares Method is applied to judge the position of train accurately from the error because of Tag's number of recognition and RFID of train speed. also It is verified through simulation.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 B
• /
• pp.1556-1558
• /
• 2005

As a result of the advancement of radio communications technologies, some investigations are in progress to apply this technologies to a train control system. Most of these investigations are focused on the train safety distance control between a preceding train and a succeeding train, an interlocking system uses train circuits to control the railway path. To make the best use of advantages and improve the safety of radio communications based train control systems, the interlocking system must use radio communications technologies. And the safety level of this system must be equal to track circuit based interlocking systems. This paper describes the train location detection method, the system configuration and the system safety of the new system.

• 한국철도학회논문집
• /
• 제14권4호
• /
• pp.341-347
• /
• 2011

한국의 고속철도에 승객의 안전과 편의를 제공하기 위하여 열차 내에 IT기술 및 센서 기술을 적용한 시스템의 개발을 연구하였다. 열차 내 화장실은 밀폐된 공간으로 외부의 도움이 필요한 상황이 발생하더라도 승객 스스로가 요청하기 전까지 외부에서는 승객의 상황을 확인하기 어렵다. 본 논문에서는 화장실 내에 개인의 프라이버시를 침해하지 않으면서도 응급상황 발생 시 센서를 통하여 외부에서 이를 감지하고 조치를 취할 수 있는 시스템의 개발내용을 정리하였다. 시스템의 요구사항을 분석하고 이를 통해 시스템을 설계하고 구현하였으며, 테스트 계획을 세우고 모의테스트를 진행함으로써 시스템의 작동상태를 확인하였다. 개발된 시스템은 향후 열차 화장실뿐만 아니라 다양한 곳에 설치하여 활용이 가능할 것이다.