• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.951-969
• /
• 2017

In this paper, we newly propose a traffic information service model that collects traffic information sensed by an individual vehicle in real time by using a smart device, and which enables drivers to share traffic information on all roads in real time using an application installed on a smart device. In particular, when the driver requests traffic information for a specific area, the proposed driver-personalized service model provides him/her with traffic information on the driving directions in advance by predicting the driving directions of the vehicle based on the learning of the driving records of each driver. To do this, we propose a traffic information management model to process and manage in real time a large amount of online-generated traffic information and traffic information requests generated by each vehicle. We also propose a road node-based indexing technique to efficiently store and manage location-based traffic information provided by each vehicle. Finally, we propose a driving learning and prediction model based on the hidden Markov model to predict the driving directions of each driver based on the driver's driving records. We analyze the traffic information processing performance of the proposed model and the accuracy of the driving prediction model using traffic information collected from actual driving vehicles for the entire area of Seoul, as well as driving records and experimental data.

• 한국정보통신학회논문지
• /
• 제26권6호
• /
• pp.827-833
• /
• 2022

본 연구는 교통정보를 수집하기 위한 검지기 와 돌발 상황 검지에 사용되는 다양한 알고리즘들의 분석을 통해 기존 교통정보 수집체계의 한계를 극복하여 심각도가 높은 2차 교통사고를 예방하고자 한다. 즉 본 연구는 2차 교통사고를 유발하는 돌발 상황과 기존 교통정보 수집체계를 분석하고 그에 알맞은 2차 교통사고의 선제적 예방이 가능한 솔루션 및 도로 전 구간에 대한 정확한 정보수집이 가능한 지능화된 새로운 교통정보 수집 및 전달체계를 제시한다. 실험결과 데이터 전송 신뢰도는 95% 기준 97%를, 데이터 전송 속도는 1000ms 기준 평균 209ms, 네트워크 장애복구 시간은 120sec 기준 50sec의 목표치를 달성하였다.

• 한국안전학회지
• /
• 제27권4호
• /
• pp.108-114
• /
• 2012

Traffic Accident Merging Index(TAMI) is developed for TMACS(Traffic Safety Information Management Complex System). TAMI is calculated by combining 'Severity Index' and 'Frequency'. This paper suggest the accurate TAMI prediction model by time series forecasting. Preventing the traffic accident by accurately predicting it in advance can greatly improve road traffic safety. Searches the model which minimizes the error of 230 local self-governing groups. TAMI of 2007~2009 years data predicts TAMI of 2010. And TAMI of 2010 compares an actual index and a prediction index. And the error is minimized the constant where selects. Exponential Smoothing model was selected. And smoothing constant was decided with 0.59. TAMI Forecasting model provides traffic next year safety information of the local government.

• 정보처리학회논문지B
• /
• 제15B권6호
• /
• pp.543-552
• /
• 2008

ATIS(Advanced Traveler Information System)는 교통 상황이나 주행 정보 등을 실시간으로 제공하여 이용자의 편익을 도모하는 시스템이다. ATIS를 위해 영상 이미지를 분석하여 교통정보를 수집 수집하는 방식은 크게 영역에 루프 검지기를 설정하여 측정하는 방식과, 영상 분석을 통해 차량을 검출하고 추적하는 방식으로 나뉜다. 본 연구에서는 차선마다 가상 검지기를 설치하는 방식을 기초로, 영상 분석 방법의 차량 위치 추적 방식을 응용하여 교통정보를 측정하는 시스템을 제안한다. 이때 가상 검지기 방식의 단점을 보완하기 위해 차선마다 다중의 가상 검지선을 설정하여, 검지 영역 내에 여러 대의 차량이 진입하거나 차량의 차선 변경 시에도 효과적으로 교통정보를 추출할 수 있게 하였고, 영상분석 방식의 문제점인 검지영역의 크기 증가에 따른 차량 추출 시간의 증가를 해결하기 위해 검지 영역 내에서 대표 픽셀을 추출하여 교통정보를 측정하였다. CCTV를 이용하여 취득한 영상에 제안하는 시스템을 이용하여 차량의 평균 속도와 차선별 교통량 측정한 결과 실제 교통량대비 평균 92.32%의 차량 검지율를 보였다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제5권4호
• /
• pp.426-439
• /
• 1999

본 논문에서는 웹(World Wide Web)에서 사용자가 손쉽고 편리하게 이용할 수 있는 멀티미디어 대중교통 안내시스템 개발 경험을 소개한다. 개발된 시스템은 클라이언트와 서버 시스템, 경로탐색 시스템, 교통정보 저장 시스템, 노선 및 정류장 관리 시스템으로 구성되어 있다. 클라이언트에서 작동되는 사용자 인터페이스는 직관적으로 이해가 쉽고, 사용이 편리하며 인터액티브한 멀티미디어 대중 교통안내 서비스를 제공한다. 서버 시스템은 교통정보 수집 시스템으로부터 입력되는 데이타와, 경로탐색 시스템, 교통정보 저장 시스템과 연동되어 클라이언트의 요구사항을 처리하고 그 결과를 사용자에게 돌려준다. 수정된 A* 알고리즘을 이용하는 경로탐색 시스템은 최적경로를 탐색하며, 교통정보 저장 시스템은 현재 교통상황, 정류장, 노선, 지도 등의 정보를 저장한다. 노선 및 정류장 관리시스템은 시스템 관리자가 노선 또는 정류장 관리를 서버 화면의 지도상에서 효율적으로 수행할 수 있는 도구이다. 본 논문에서 다루는 대중교통 안내시스템은 Java로 구현하였기 때문에 확장과 이식이 용이하며, 시스템 유지보수 비용이 적게 드는 장점을 가지고 있다. 그리고, 웹 브라우저가 동작되는 환경에서는 어디서나 쉽게 접근이 가능하며 향후 구축될 Intelligent Transportation Systems(ITS)의 한 모듈로써 바로 작동될 수 있을 뿐만 아니라, 현재 인터넷상에서 제공되는 다양한 서비스와도 연동이 가능하다.Abstract This paper introduces our experience for developing a public transportation guidance system, which facilitates the World-Wide Web(WWW) to provide users with easier access and use. The proposed system is composed of four subsystems: client/server system, path search system, traffic data storage system, and traffic raw-data management system. The user interface in clients utilizes Java to furnish users with multimedia data accessibility and interactivity. The server processes clients' requests based on the traffic data coming from remote sensing devices and interacts with the path search system and traffic data storage system to provide users with the results. The path search system, which uses a modified A* algorithm, produces optimal solutions based on dynamic traffic data. The traffic data storage system stores the current traffic information together with the geographical information about the b$us_way routes. The traffic raw-data management system is a graphical user interface which enables the system manager to handle the traffic information easily on the map in the terminal screen. The system has considerable benefits such as portability, scalability, and flexibility since it is implemented using Java. Also, it can be extended to an integrated Intelligent Transportation Systems(ITS) which includes a variety of information on the Internet as well as traffic information.n.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2003년도 추계학술대회 논문집(II)
• /
• pp.311-318
• /
• 2003

Traffic management means the management of streams of people, vehicle and cargo. Its aim is to help creating an efficient, safe and environmentally friendly transport system. Traffic management can roughly be divided in traffic control and monitoring, traffic information and demand management. The main purpose of this thesis is providing the basis for developing the next generation train traffic management system by comparing domestic and abroad train traffic management system. The composition of this thesis has been discussed in the following order of the comparison of train traffic management system's function, the introduction of Autonomous Decentralized system, the comparison between CTC and ATOS. the comparison between the hierarchy system and Autonomous Decentralized system, the study of introduction plan of Autonomous Decentralized-type train traffic management system and conclusion.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.597-598
• /
• 2018

최근의 미래교통시스템은 주로 교통체계를 활용한 교통정보의 수집과 관리, 제공을 함으로서 교통안전을 도모하고 있다. 그러나 본 논문에서는 현재 활용되고 있는 교통 인프라인 교통안전표지를 활용한 교통안전을 제안하고자 한다. 교통안전표지를 호스트로 하여 센싱 된 데이터를 차량이 수신하게 됨으로서 차량간 또는 인프라간 통신을 하게 된다. 센싱 데이터의 정보를 활용함으로서 다양한 정보를 얻게 되는데, 공사구간 뿐만 아니라 교통사고 등도 활용이 가능하다. 따라서 본 논문은 센싱 데이터의 프레임을 간단하게 설계하고, 향후 지속적인 연구를 통하여 교통안전에 이바지하고자 한다.

• 한국IT서비스학회지
• /
• 제14권4호
• /
• pp.257-267
• /
• 2015

We propose a vehicle-mounted, location-aware mobile digital signage system that can be used for public transportation through mobile communication. This paper proposes the installations of the LED display panels at the backside of the bus., which display traffic information to cars behind the bus. Information to be displayed would include, but is not limited to, road information, public commercials and private commercials. We propose the system architecture and further implement the prototype of mobile digital signage system for demonstration. The system is based on the Client-Server system. Each bus has a client terminal which detects the current location by a GPS receiver and sends its location information to the server using mobile communication function. The terminal device receives advertisements and traffic information from the server and displays it to the large LCD or LED panel installed at the inside and outside of the bus. We use the Android smartphone as a client system, which inherently equipped with GPS and mobile communication function. GPS detects the location of bus and reports its geo-location data to the traffic information center server via a wireless communication network. On the server side, we developed a specially designed control server, where it communicates with the other traffic information center and updates and manages the databases contents being displayed by each position. The server contains location dependent variable information and returns selected information back to the vehicle in real time. Spatial database is used to process location based data. Server system periodically receives the real time traffic information from the road information center database. And it process the information by bus location and bus line number. In this paper, we propose a mobile digital signage service and explain the system implementation of this service.

• 한국공간정보시스템학회 논문지
• /
• 제11권2호
• /
• pp.162-169
• /
• 2009

The real-time traffic data is generated continuous and unbounded stream data type while intelligent transport system (ITS) needs to provide various and high quality services by combining with spatial information. Traditional database techniques in ITS has shortage for processing dynamic real-time stream data and static spatial data simultaneously. In this paper, we design and implement an advanced traffic monitoring system (ATMS) with the integration of existed data stream management system (DSMS) and spatial DBMS using IntraMap. Besides, the developed ATMS can deal with the stream data of DSMS, the trajectory data of relational DBMS, and the spatial data of SDBMS concurrently. The implemented ATMS supports historical and one time query, continuous query and combined query. Application programmer can develop various intelligent services such as moving trajectory tracking, k-nearest neighbor (KNN) query and dynamic intelligent navigation by using components of the ATMS.

• 한국공간정보시스템학회 논문지
• /
• 제11권2호
• /
• pp.45-53
• /
• 2009

The fast progress on multimedia data acquisition technologies has enabled collecting vast amount of videos in real time. Although the amount of information gathered from these videos could be high in terms of quantity and quality, the use of the collected data is very limited typically by human-centric monitoring systems. In this paper, we propose a framework for analyzing long traffic video using series of content-based analyses tools. Our framework suggests a method to integrate theses analyses tools to extract highly informative features specific to a traffic video analysis. Our analytical framework provides (1) re-sampling tools for efficient and precise analysis, (2) foreground extraction methods for unbiased traffic flow analysis, (3) frame property analyses tools using variety of frame characteristics including brightness, entropy, Harris corners, and variance of traffic flow, and (4) a visualization tool that summarizes the entire video sequence and automatically highlight a collection of frames based on some metrics defined by semi-automated or fully automated techniques. Based on the proposed framework, we developed an automated traffic flow analysis system, and in our experiments, we show results from two example traffic videos taken from different monitoring angles.