• 한국컴퓨터정보학회논문지
• /
• 제28권5호
• /
• pp.9-15
• /
• 2023

본 연구는 신경망을 이용하여 링크 속도로부터 각 차로의 속도를 예측하는 방법을 제시하였다. 예측 정확도를 높이기 위해 학습 데이터 구성에 있어 3가지 사항을 고려하였다. 첫 번째는 링크의 시작점과 끝점이 연결된 14개의 링크를 포함하여 데이터 소스의 공간적 범위를 확장하였다. 또한 시간 간격을 07:00에서 22:00로 늘리고 특성 데이터에 데이터 생성 시각을 포함했다. 마지막으로 요일과 공휴일을 표시했다. 실험 결과 직진 차로는 속도 오차가 6.4km/h에서 5.0km/h로 21.9%, 우회전은 8.5km/h에서 7.4km/h로 12.9%, 좌회전은 8.7km/h에서 8.2km/h로 5.7% 감소한 것으로 나타났다. 두번째 결과로 교통 정체시 도심부 도로의 차선별 예측 정확도가 높은 것을 확인하였다. 제안한 방법의 특징은 도로 소통 상황을 차로 단위로 예측하여 도로 소통 상황을 보다 정확하게 예측한 것이다.

• 한국도로학회논문집
• /
• 제14권6호
• /
• pp.131-138
• /
• 2012

PURPOSES : Two-lane highways have one lane in each direction, and lane changing and passing maneuvers take place in the opposing lane depending on the availability of passing sight distance. 2001 Korea Highway Capacity Manual (KHCM) is classified into two classes of two-lane highways (Type I, II), and average travel speed and time-delayed rate are used as measures of effectiveness (MOEs). However, since existing two-lane highways have both uninterrupted and interrupted traffic flow-system elements, a variety of free-flow speeds exhibits in two-lane highways. In addition, it is necessary to check if the linear-relationship between volumes and time-delayed rate is appropriate. Then, this study is to reestablish the relationship between average travel speed, time-delayed rate, and flow. METHODS : TWOPAS model was selected to conduct this study, and the free-flow speeds of passenger cars and the percentage of following vehicles observed in two-lane highways were applied to the model as the input. The revised relationships were developed from the computer simulation. RESULTS : In the revised average travel speed vs. flow relationship, the free-flow speed of 90km/h and 70km/h were added. It shows that the relationship between time delayed-rate and flow appeared to be appropriate with the log-function form and that there was no difference in time-delayed rate between the free flow speeds. In addition to revise the relationships, the speed prediction model and the time-delayed rate prediction model were also developed. CONCLUSIONS : The revised relationships between average travel speed, time-delayed rate, and flow would be useful in estimating the Level of Service(LOS) of a two-lane highway.

• 한국정보통신학회논문지
• /
• 제21권8호
• /
• pp.1553-1559
• /
• 2017

본 논문은 자동차 전방에 장착된 단일 카메라를 이용한 차선 이탈 검출 알고리즘을 제안한다. 제안된 알고리즘은 카메라에 의해 취득된 영상으로부터 top-view 공간에 지정된 작은 관심 영역을 위한 부분 top-view 영상을 생성하고, 작은 부분 top-view 영상에서 차선을 검출하고, 미리 지정된 가상 자동차와 검출된 차선들의 겹침을 조사해 차선 이탈을 결정한다. 또한 제안된 알고리즘은 차선 사이에서 차선 이탈 검출을 방해하는 도로 표기 (잡음)에 의한 직선들의 제거와 이전 프레임의 차선 정보를 이용한 손실된 차선의 예측을 포함한다. 실제 주행 동영상을 이용한 차선 이탈 검출 실험에서 제안된 알고리즘은 차선 유지 상태에서 99.0%, 차선 이탈 상태에서 94.7%를 정상적으로 검출한다.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 1부
• /
• pp.205-209
• /
• 2008

최근 하드웨어의 발달로 영상처리를 사용한 운전자 보조 기능의 차선인식 시스템이 상용화 되고 있다. 하지만 고속도로 주행과 같은 차선이 확실하고 곡률이 완만한 비교적 이상적인 상황에서의 차선인식을 전제로 만들어진 시스템이 많아 시내도로와 같이 상대적으로 곡률이 크고 일부 차선이 확실치 않은 장소에서는 차선인식이 힘들어 무인 자동차 제어에는 적용하기 힘들다. 본 논문은 무인차량의 자동주행을 위해 labeling과 차선예측을 통해 급격한 곡선 차로나 차선이 한쪽만 그려져 있는 경우에도 강인하게 차선인식이 가능한 시스템을 제안한다. 제안된 방법을 이용하여 이상적인 경우가 아닌 급격한 곡선차로가 있거나, 차선이 한쪽만 있는 실제 환경의 경우에서도 차선인식이 가능함을 보였다.

• 한국도로학회논문집
• /
• 제18권3호
• /
• pp.11-19
• /
• 2016

PURPOSES : This study supports the evidence that it is possible to rehabilitate a damaged pavement with a lane closure specifically based on the Gimcheon~Sunsan project. METHODS : The prediction results from the simulation programs were compared with field monitoring, which focused on traffic management planning, congestion (length, time, and passing speed), bypass, and user cost, among others. RESULTS : The research results showed that lane closure application and pavement repair of the aged pavement in Korea were possible, even though the prediction results were minimally different from the field monitoring. The road agency contributes to service life extension of the rehabilitated pavement using this method. CONCLUSIONS : A marginal effect caused by the lane closure was observed on travelling users or vehicles, and the user cost of pavement repair decreased. Therefore, introducing the repair method or rehabilitation in Korea is possible. Information dissemination through various media was properly done to execute the project well. Moreover, the construction area traffic utilized nearby alternative roads. Therefore, improving the repaired pavemen's service life while ensuring that the pavement management agency can provide a road with comfortable user riding quality was possible.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.715-716
• /
• 2008

A dead zone prediction system for vehicles are implemented in this paper. To improve performance reliability and stability, we import two method to get a information between car and car, and car and road. One is traffic lane detection method, another is vecle recognition. In this paper, we explain the methods and whole structure about this system except for details.

• 한국항해항만학회지
• /
• 제40권2호
• /
• pp.51-56
• /
• 2016

Expressways mean the primary arterial highways with a high level of efficiency and safety. However, Gyeongbu and Namhae expressways connected with Busan ports are showing travel time delay by increased traffic including the medium/large-sized vehicles of about 20% compared to those of about 13% regardless of the peak periods. This study, thus, intends to analyze lane traffic characteristics in the basic 8-lane segments of the above-mentioned expressways, compute the planning and buffer times based on travel time reliability, find the lane speed showing a higher correlation with planning time between the lane speeds in the basic 8-lane segments, and finally suggest a correlation model for predicting the planning time in expressways.

• 한국항해항만학회지
• /
• 제36권7호
• /
• pp.591-597
• /
• 2012

Generally an urban freeway means a primary arterial which provides road users with a free-flow speed, except for ramp junctions during rush hours. However, most road users suffer from traffic congestion in the basic segments as well as in the ramp junctions of urban freeway during rush hours, because most road users prefer urban freeways to local roads in the urban areas. This study then intends to analyze lane traffic characteristics of urban freeway basic segments having more freight vehicles during rush hours, find the lane showing a high correlation with the segment speed between lane speeds, and finally suggest a segment-speed predictive model by the lane speed of urban freeway basic segments during rush hours.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.97-100
• /
• 1996

In this paper, we describe an algorithm which estimate road following direction using the vanishing point property and obstacle detection. This method of detecting the lane markers in a set of continuous lane highway images using linear approximation is presented. This algorithm is designed for accurate and robust extraction of this data as well as high processing speed. Also, this algorithm reckon distance and chase about an obstacle. It include four algorithms which are lane prediction, lane extraction, road following parameter estimation and obstacle detection algorithm. High accuracy was proven by quantitative evaluation using simulated images. Both robustness and the practicality of real time video rate processing were then confirmed through experiment using VTR real road images.

• 전자공학회논문지S
• /
• 제34S권11호
• /
• pp.126-137
• /
• 1997

This paper describes the algorithm which can estimate road following direction and deetect obstacle using a monocular vision system. This algorithm can estimate the course of vehicle using the vanishing point properties and detect obstacle by statistical method. The proposed algorithm is composed of four steps, which are lane prediction, lane extraction, road following parameter estimation and obstacle detection. It is designed for high processing speed and high accuracy. The former is achieved by a small area named sub-windown in lane existence area, the later is realized by using connected edge points of lane. We would like to present that the new mehod can detect obstacle using the simple statistical method. The paracticalities of the processing speed, the accuracy of the algorithm and proposing obstacle detection method, have been justified through the experiment applied VTR image of the real road to the algorithm.