• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.6 no.3
• /
• pp.57-66
• /
• 2007

Weaving is defined as the crossing of two or more traffic streams traveling in the same general direction along a significant length of highway without the aid of traffic control devices. Compared with other freeway sections, perturbation is easy to happen at weaving section. Because there are a lot of lane-changing maneuvers at the weaving section, traffic is subject to turbulence in excess of that normally presents on freeway basic section. This turbulence causes operational problems and its impact must be considered. The purpose of this paper is to perform a basic study on flow characteristics by lane, which can be achieved through analyzing breakdown phenomenon in the microscopic approach. The study made use of data derived from the aerial photography for the microscopic analysis. This research produced the 30-second interval data such as flows, speeds, and densities for the macroscopic analysis and derived the vehicular data to draw time-space diagram for the microscopic analysis. The paper analyzed the traffic characteristics using flows, speeds and densities variation and investigated the conditions of breakdown occurrence with the time-space diagrams. The breakdown phenomenon was identified at weaving section and the propagation from free flow to synchronized flow was observed in this study. In the future, the findings help develop the traffic operational algorithm to manage the traffic congestion under ubiquitous circumstance since the conditions of breakdown Phenomenon can be understood more.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.58-64
• /
• 2021

As the number of registered vehicles increases, traffic congestion will worsen worse, which may act as an inhibitory factor for urban social and economic development. Through accurate traffic flow prediction, various AI techniques have been used to prevent traffic congestion. This paper uses the data from a VDS (Vehicle Detection System) as input variables. This study predicted traffic flow in five levels (free flow, somewhat delayed, delayed, somewhat congested, and congested), rather than predicting traffic flow in two levels (free flow and congested). The Catboost model, which is a machine-learning algorithm, was used in this study. This model predicts traffic flow in five levels and compares and analyzes the accuracy of the prediction with other algorithms. In addition, the preprocessed model that went through RandomizedSerachCv and One-Hot Encoding was compared with the naive one. As a result, the Catboost model without any hyper-parameter showed the highest accuracy of 93%. Overall, the Catboost model analyzes and predicts a large number of categorical traffic data better than any other machine learning and deep learning models, and the initial set parameters are optimized for Catboost.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.2
• /
• pp.1-11
• /
• 2013

This research proposed integrated expressway traffic management strategy using ramp metering and toll mainline metering. This research suggested a traffic signal optimization model for integrated operation of ramp and mainline metering based on Demand-Capacity Model that is used to optimize allowable input volume for ramp metering in FREQ model. The objective function of this model is sectional throughput volume maximization, and this model can calculate optimal signal timings for mainline metering and ramp metering. This study conducted an effectiveness analysis of integrated metering strategy using PARAMICS and its API. It targeted Seoul's Outer Ring Expressway between Gimpo and Siheung toll gate. As a simulation result, integrated operation of mainline and ramp metering provided more smooth traffic flow, and throughput volume of mainline increased to 14% in congested section. In addition, a queue of 400 meter was formed at metering point of toll gate. This research checked that integrated traffic management strategy facilitates more efficient traffic operation of mainline and ramp from diffused traffic congestion.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.66-83
• /
• 2021

Vehicles experience changes in driving behavior due to the various facilities on the freeway. These sections may cause repetitive traffic congestion when the traffic volume increases, so safety issues may be raised. Therefore, the purpose of this study is to perform microscopic traffic analysis on these sections using drone images and to identify the causes of traffic problems. In the case of drone image, since trajectory data of individual vehicles can be obtained, empirical analysis of driving behavior is possible. The analysis section of this study was selected as the weaving section of Pangyo IC and the sag section of Seohae Bridge. First, the trajectory data was extracted through the drone image. And the microscopic traffic analysis performed on the speed, density, acceleration, and lane change through cell-unit analysis using Generalized definition method. This analysis results can be used as a basic study to identify the cause of the problem section in the freeway. Through this, we aim to improve the efficiency and convenience of traffic analysis.

• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.69-70
• /
• 2015

본 논문에서는 운행중인 차량이 수집한 위치별 교통 이벤트 (지체, 정체, 사고, 노면상태 등)를 다른 운행 차량과 실시간으로 공유하여 안전운행 서비스를 제공하기 위한 방법을 제안한다. 운행중인 차량은 차량내의 스마트 기기나 전용 기기를 이용해 수집한 교통이벤트를 실시간으로 서버로 전송하고 서버는 전송된 교통이벤트를 위치별, 시간별로 색인하고 중복된 교통이벤트를 분류하여 저장한다. 이런 모든 과정은 처리 속도 향상을 위해 Spark의 RDD를 이용해서 인-메모리에서 처리된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.617-618
• /
• 2018

본 논문에서는 유니티 엔진을 활용하여 도로교통 시뮬레이터 에셋을 제안한다. 제안하는 에셋은 유니티 좌표계 내에서 오브젝트를 이용하여 가상의 도로를 설계함으로서 도로교통 시뮬레이터의 진입장벽과 단순 작업비용을 낮추고, 가상의 도로에서 다양한 속성을 가진 차량과 신호등을 생성하고 시뮬레이션 함으로서 차량과 교통신호, 도로설계 등이 교통에 미치는 영향을 시각화하여 관찰 할 수 있다. 제안한 에셋을 이용하여 도로를 보다 용이하게 설계하여 도로교통 시뮬레이션을 할 수 있으며, 간단한 시나리오를 제작하여, 도로정체의 원인을 설명 할 수 있다. 사용자가 도로설계 시의 작업량을 더 줄일 수 있도록 도로생성 부분에서 보다 다양한 기능 지원과 시뮬레이터의 타당성 검토를 위한 추가적인 시나리오 테스트 등이 향후 과제이다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.1
• /
• pp.85-92
• /
• 2007

Traffic accident number is decreasing tendency every year. But, large size accident or hit-and-run case increases continuously. As well as, traffic accident causes real form of accident ambit thats why, social expense rises. For that reason we are going to present our plan that can prevent traffic accident when traffic accident occurs, we presented our idea that can arbitrate traffic accident quickly. Driver can know more correctly traffic circumstance through hearing and sight by using DMB. Finally, we suggested plan that supply traffic information that is more effective by TPEG.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.353-361
• /
• 2020

Due to the rapid urbanization, various traffic problems such as traffic jams during commute and regular traffic jams are occurring. In order to solve these traffic problems, it is necessary to quickly and accurately estimate and analyze traffic volume. ITS (Intelligent Transportation System) is a system that performs optimal traffic management by utilizing the latest ICT (Information and Communications Technology) technologies, and research has been conducted to analyze fast and accurate traffic volume through various techniques. In this study, we proposed a deep learning-based vehicle detection method using UAV (Unmanned Aerial Vehicle) video for real-time traffic analysis with high accuracy. The UAV was used to photograph orthogonal videos necessary for training and verification at intersections where various vehicles pass and trained vehicles by classifying them into sedan, truck, and bus. The experiment on UAV dataset was carried out using YOLOv3 (You Only Look Once V3), a deep learning-based object detection technique, and the experiments achieved the overall object detection rate of 90.21%, precision of 95.10% and the recall of 85.79%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.15-18
• /
• 2013

본 논문에서는 교통상황을 실시간으로 반영하여 최적의 이동경로를 제공하는 적응형 내비게이션 시스템을 제안한다. 본 시스템은 세 가지 요소로 구성되어있다. 첫 번째로 도로교통망 중 한 구획의 도로상황정보를 수집하고 공유하는 Traffic Control Center (TCC). 두 번째로 개별적인 도로나 교차로에 설치되어 차량으로부터 도로상황정보를 수집하는 Road Side Unit(RSU). 마지막으로 차량들 간의 망 형성을 위해서 사용되는 Dedicated Short Range Communications(DSRC)를 기반으로 차량에 설치된 단말기가 있다. DSRC를 기반으로 RSU와의 통신하는 단말기는 실시간 도로교통정보를 기반으로 운전자에게 최적의 경로를 제공한다. 이동속도와 같은 교통정보는 단말기에서 측정되고, RSU로 전송된다. RSU는 이 정보를 처리하여 해당 도로의 도로상황지수를 생성하고, 주기적으로 TCC에 전송한다. TCC는 RSU로부터 도로상황지수를 통합하여 TCC의 관할 구획의 모든 차량에 대해 도로교통정보를 만든다. 마지막으로 단말기는 효율적인 경로안내를 위해 최적의 경로를 도출하여 운전자에게 제공한다. 따라서 단말기, RSU, TCC간의 상호작용을 통해 AINS는 동적인 교통상황(정체, 교통사고 등)을 기반으로 새로운 형태의 적응형 지능 내비게이션을 제공할 수 있다.

• Journal of Korean Society of Transportation
• /
• v.22 no.2 s.73
• /
• pp.87-93
• /
• 2004

A five-day work week has a great impact on the life styles of employed persons and their families. At the same time, the changes also impact on the transportation system because travel patterns, demand, and pattern of congestion change during weekends. The negative impacts on the transportation system should be examined in order to conceive measures to maintain dependable levels of service during weekends. The first step to pursue the issue is to identify the road segments heavily affected by augmented leisure trips. In this study, characteristics of highway segments are engineered by principal analysis using data from TCS database. Scores from principal analysis are employed to distinguish highway segments for leisure trips from total 197 segments considered in this study. In addition, indexes from principal analysis are proposed to identify highway segments for leisure trips.