• Journal of Korean Society of Transportation
• /
• v.23 no.6 s.84
• /
• pp.19-30
• /
• 2005

The objective of this research is to keep track of path travel time using methods of collecting traffic data. Users of traffic information are looking for extensive information on path travel time, which is referred to as the time taken for traveling from the origin to the destination. However, all the information available is the average path travel times, which is a simple sum of the average link travel times. The average path travel time services are not up to the expectation of traffic information consumers. To improve provide more accurate path travel time services, this research makes a number of different estimates of various path travel times on one path, assuming it will be under the same condition, and provides a range of estimates with their probabilities to the consumers, who are looking for detailed information. To estimate the distribution of the path travel times as a combination of link travel times. this research analyzes the relation between the link travel time and path travel time. Based on the result of the estimation. this research develops the algorithm that combines the distribution of link travel time and estimates the path travel time based on the link travel times. This algorithm was tested and proven to be highly reliable for estimating the path traffic time.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.6
• /
• pp.121-132
• /
• 2018

Weather is an important factor affecting roadway transportation in many aspects such as traffic flow, driver 's driving patterns, and crashes. This study focuses on the relationship between weather and road surface condition and develops a model to estimate the road surface condition using machine learning. A road surface sensor was attached to the probe vehicle to collect road surface condition classified into three categories as 'dry', 'moist' and 'wet'. Road geometry information (curvature, gradient), traffic information (link speed), weather information (rainfall, humidity, temperature, wind speed) are utilized as variables to estimate the road surface condition. A variety of machine learning algorithms examined for predicting the road surface condition, and a two - stage classification model based on 'Random forest' which has the highest accuracy was constructed. 14 days of data were used to train the model and 2 days of data were used to test the accuracy of the model. As a result, a road surface state prediction model with 81.74% accuracy was constructed. The result of this study shows the possibility of estimating the road surface condition using the existing weather and traffic information without installing new equipment or sensors.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.90-93
• /
• 2009

본 논문은 자동차 자동운행 시스템 연구 분야의 한 부분인 자동차 운행 중 도로상에 위치한 교통 신호등을 추적을 통해 검출하고, 인식하기 위한 방법과 관련된 연구이다. 교통 신호등은 색상 정보를 포함한 광원을 갖는 물체로서 표현되어지고 운전자에게 안전을 위해 준수해야 할 신호정보로써 제공되어 진다. 본 논문에서는 이러한 교통신호등의 인식을 위해 명도 분포도를 이용하여 관심영역을 필터링하고, 마스크와 HSI 색 공간영역에서의 색상과 채도, 밝기 정보를 이용한 유효값을 검출, 좌표변환, 보간법, YUV 모델을 이용한 그레이 영상으로의 변환, 닫힘 연산, 선명화 연산, 템플릿 매칭 방법을 적용함으로써 가로등과 같은 주변 환경이 갖는 색정보로부터 교통 신호등의 신호를 검출하고 인식하도록 하였다.

• Journal of Korea Spatial Information System Society
• /
• v.9 no.1
• /
• pp.79-90
• /
• 2007

In this paper we proposed and implemented an incident detection model which combines fuzzy algorithm and traffic pattern in order to enhance the efficiency of incident detection for the highways with lamps. Most of the existing algorithms dealt with highways without lamps and can not be used for detecting incidents in the highways with lamps. The data used for model building are traffic volume, occupancy, and speed data. They have been collected by a loop sensor at 5 minutes interval at a point in the Internal Circular Highway of Seoul for the period of 3 months. In this model, the three parameters collected by sensor were fuzzified and combined with the daily traffic pattern of the link. The test of efficiency of the propsed model was performed by comparing the result of proposed model with traditional APID algorithm and fuzzy algorithm without the pattern data respectively. The result showed significant amount of improvement in reducing the false incident detection rate by 18%.

• Journal of Internet Computing and Services
• /
• v.3 no.6
• /
• pp.35-41
• /
• 2002

The Car Navigation System(CNS) requires lots of memory and calculating time because it works on the large and complex digital map. And the traffic circumstances vary time by time, so the traffic informations should be processed if we want to get mere realistic result. This paper proposes an effective path searching algorithm which uses less memories and calculating time by applying directional information between the starting place and destination place and by using realtime traffic informations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1394-1396
• /
• 2013

플리커와 같은 대용량 영상저장 및 공유 사이트가 인기를 끌면서 이미지 정보의 양은 점점 늘어나고 있고 사용자들은 정확한 이미지 정보 검색을 요구하고 있다. 태그기반의 이미지 검색에서 정확도를 높이기 위하여 태그들의 의미적 연관성을 이용하는 등 다양한 연구가 진행되고 있다. 본 논문에서는 특징점 추출에 기반하여 이미지를 분류하는데 뛰어난 성능을 가진 SIFT알고리즘을 사용하여 플리커 이미지를 분류하는 방법을 제안한다. 위키피디아 의미 연관성을 이용해 태그 정보로 1차 분류된 데이터베이스에 SIFT알고리즘을 사용해본 결과 기존의 SURF를 사용한 연구보다 높은 정확성을 보이는 것을 확인하였다. 따라서 이 방법을 통하여 다양한 이미지를 더욱 정확하게 분류할 수 있을 것으로 기대한다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.1
• /
• pp.121-131
• /
• 2020

Current traffic information is collected through a loop detector or an image detector. This method is influenced by weather and time, so a traffic information generation system is needed to replace it. A system for generating traffic information using a smartphone in a vehicle is proposed and the performance of the proposed method is verified through the collection rate and the travel time error rate obtained through field tests. In addition, we propose an algorithm for generating intersection traffic information for each direction of rotation, suggest ways to increase the amount of valid information, and confirm the results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.447-450
• /
• 2016

선진국에서는 이미 다양한 지능형 교통 시스템(ITS) 기술을 실제 도로에 적용하여 교통문제를 해결하고 있고 국내에서도 이를 도입하여 많은 교통문제를 완화시킬 수 있을 것으로 전망된다. 하지만 국외 교통 환경에 적용된 기존 ITS 솔루션들을 실제 국내 도로에 적용하였을 때 예기치 못한 문제의 발생으로 많은 비용을 낭비할 수 있다. 본 논문에서는 위의 문제를 해결하기 위해 대한민국 고속도로 분석 및 시뮬레이션 시스템인 KHTA를 제안한다. KHTA는 국내 모든 고속도로의 정보를 분석할 수 있을 뿐만 아니라 재현된 국내 교통 환경에서 직접 구현한 ITS 알고리즘을 시뮬레이션 가능하다. 본 논문에서는 KHTA를 구축하고 한국 도로에 ITS 시뮬레이션 적용 가능성을 검증하기 위해 국내 고속도로 전용 Ramp Metering 알고리즘을 구현하고 결과를 분석 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.295-297
• /
• 2007

교통 관련 검지기 시스템에 의해 수집된 교통량, 점유율, 속도와 같은 교통 정보 데이터는 품질평가, 오류판단, 결측보정의 자료처리를 거치게 되며 이러한 전처리 후 다양한 목적에 의해 연구자들에게 활용된다. 신속하고 정확한 자료처리와 보다 편리하고 효과적인 웹 UI 의 제공은 매우 중요하다. 본 논문에서는 품질평가, 오류판단, 결측보정에 해당하는 세 단계의 자료처리 알고리즘을 개발하고 사용자에게 자료처리의 과정을 제공하는 웹 UI 시스템을 구현한다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.1
• /
• pp.9-16
• /
• 2016

As the need of eco-friendly transportation systems for sustainable development increases, public transport accessibility has been considered as an important element of transportation system design. When analyzing the accessibility, shortest path algorithms can be utilized to reflect the actual movement and we can obtain high resolution accessibility for all other stations on the network with shortest distance and time. This study used the algorithm improved by reflecting the penalty of number of transfers and waiting time of overlapped routes to get the accessibility. KTX Seoul Station is a target place and this algorithm is applied to multi-layer subway bus network of Seoul to calculate the accessibility, therefore this study presented the accessibility of KTX Seoul station by stations.