• International Journal of Highway Engineering
• /
• v.10 no.2
• /
• pp.101-113
• /
• 2008

VMS are installed in many Korean highways in oder to give drivers informations such as travel time to destination, congestion and Incident situation. However, some guidelines for install VMS are restricted in only geometric factors although human factors considering driver behavior are very important to affect the VMS installation. Therefore, this paper are focusing on developing and verifying the discriminant model for VMS installation considering human factors. As a result, following outputs are obtained ; (1) developing the discriminant model using human factors of driving simulation experiments in oder to predict driver reading VMS messages safely detour highway. (2) proving that driving experiences in highway, personal driving history, vehicle speed orderly affects VMS installation (3) verifying predictability of developed model by comparing the real values with predicted values. (4) suggesting that VMS should be installed off 3.2Km from the I.C. of rural highway.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.3
• /
• pp.112-123
• /
• 2012

Different from general roads, intersections are the points where roads having different geometric structure and traffic operation system are met, and thereby they have complicated road structure and environmental factors. Various changes in driving patterns such as collision between vehicles approaching from roads adjacent to intersections, sudden stop of vehicles upon stop sign, quick start upon green lights kept increasing traffic accidents. It is known that traffic accidents are mainly derived from human factors. This study, in order to find out factors affecting drivers' behaviors within intersections, measured physiological responses such as brain wave, sight, driving speed, and so on by using state-of-the-art measuring device. As to concentration brain wave at individual intersections, it was found out that brain wave of testes was higher at main Arterial and accident-prone intersections compared with that of subsidiary Arterial. In addition, it was detected that drivers' visual activity was widely distributed at accident-prone intersections, meaning that it enhanced cautious driving from nearby vehicles. As to major factors causing drivers' workloads, factors from nearby vehicles such as deceleration, acceleration, lane change of nearby vehicles appeared as direct factors causing drivers' workloads, clarifying that these factors were closely related to causes of traffic accidents at intersections. Results of this study are expected to be used as basic data for evaluation of safety at intersections in consideration of physiological response of drivers.

• Journal of Korean Society of Transportation
• /
• v.27 no.1
• /
• pp.17-25
• /
• 2009

This research analyzed the changes of drivers' visual workload with beta wave of bionic signals from brain's occipital lobe from entrance to exit section of the Yuksimnyeong tunnel which is 3.1km long in Daejeon-Tongyeong section of Jungbu expressway. There are 10 subjects who Participate our experiments and the results are as follows. First. the drivers' visual workload is higher about 41% in entrance section of the tunnel than 200m in advance of the section of the tunnel. Second, it is higher than 200m in advance of the section of the tunnel by 34.5% that the value of the drivers' visual workload who is driving in the tunnel. Third, as a result of analyzing the tunnel into 200m unit section, it is statistically different from other sections' at the 1.0km and 2.4km section from the entrance of the tunnel. If drivers sustain average visual workload for safe driving in very long tunnel, it's not desirable environment that drivers' visual workload goes under the average workload. Therefore, it would be the section where drivers who is driving in tunnel could cause a traffic accident.

• Journal of Digital Convergence
• /
• v.19 no.12
• /
• pp.457-462
• /
• 2021

As South Korea is a mountainous topography, installation of tunnel is essential for construction of expressway in straight lines. According to "2019 Road Bridge and Tunnel Status Report", there are 2,682 tunnels in Korea with total length of 2,077km. Tunnels take up 1.9% of total road length and the number of tunnel increased by 94% with 1,300 newly constructed tunnels over the 10 years. According to domestic and foreign researches, a long tunnel over 1km in expressway has dark lightings and monotonous wall design which decrease driver's concentration and make the driver feel bored. This leads to feeling fatigue and drowsiness more easily. In response, Korea Expressway Corporation installed design lighting that increases attentiveness on 10 tunnels with total length over 3km by 2020. To reduce the risks of accident that may happen inside the tunnel, this study conducted a comparative analysis on characteristics of each type of LED landscape lighting installed inside the expressway tunnel. The study aimed on providing the basic material for effective installation of LED landscape lighting for securing driving stability, reducing fatigue, and lowering the risk of drowsiness.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.271-276
• /
• 2018

When the driver riding in a bicycle goes on board, the load of driver is shown differently according to the position loaded on the frame of bicycle. The load is applied most at the joint of bike frame and the load at the mid-part of frame is applied least than the other parts. So, the weight of frame is decreased as the part not applied with a lot of load is manufactured into the thin thickness. As the part applied with high load is manufactured into the thick thickness, it can be endured through this load. The configurations of general frame, double butted and triple butted were modelled by using CATIA program. The durabilities of each model due to the load of passenger were investigated by carrying the structural and fatigue analyses. As this study result investigated with the analysis program of ANSYS, the deformation of general frame happened most and that of triple butted became least. These simulation analysis data are intended to be used to design the actual bicycle frame in the most efficient way at design and manufacture.

• Journal of Korean Society of Steel Construction
• /
• v.18 no.1
• /
• pp.11-22
• /
• 2006

Message Signs (VMS) structures offer an increase in traffic safety through their ability to relay massages to motorists for warnings of hazards ahead, traffic congestion, accidents, and lane closings. The geometry of these signs sometimes results in the significant cyclic loading of the supports structure due to wind gusts, which can result from passing trucks or from natural wind. This study presents the results of analytical and experimental investigations of VMS structures. The commercially available softwareGTSTRUDL (2003) was used to perform space-frame structural analyses of these welded tubular structures. Fatigue evaluations were performed using stress ranges from field measurements and from structural analyses. Based on the results of the structural analyses that were conducted, where fatigue design loadings that had been derived from AASHTO Specifications for Structural Supports for Highway Signs, Luminaries, and Traffic Signals (2001) were used, the structures that had been studied were found not to have infinite fatigue life. According to the limited measurements that were made in this study, the fatigue design loadings derived from AASHTO Specifications (2001) appear to be conservative, but they are not overly conservative. The results of this study should be used to make a reasonable design of VMS structures, and to maintain their standards.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.3
• /
• pp.53-60
• /
• 2009

The vision-based driver fatigue detection is one of the most prospective commercial applications of facial expression recognition technology. The facial feature tracking is the primary technique issue in it. Current facial tracking technology faces three challenges: (1) detection failure of some or all of features due to a variety of lighting conditions and head motions; (2) multiple and non-rigid object tracking; and (3) features occlusion when the head is in oblique angles. In this paper, we propose a new active approach. First, the active IR sensor is used to robustly detect pupils under variable lighting conditions. The detected pupils are then used to predict the head motion. Furthermore, face movement is assumed to be locally smooth so that a facial feature can be tracked with a Kalman filter. The simultaneous use of the pupil constraint and the Kalman filtering greatly increases the prediction accuracy for each feature position. Feature detection is accomplished in the Gabor space with respect to the vicinity of predicted location. Local graphs consisting of identified features are extracted and used to capture the spatial relationship among detected features. Finally, a graph-based reliability propagation is proposed to tackle the occlusion problem and verify the tracking results. The experimental results show validity of our active approach to real-life facial tracking under variable lighting conditions, head orientations, and facial expressions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.603-607
• /
• 2004

The vision-based driver fatigue detection is one of the most prospective commercial applications of facial expression recognition technology. The facial feature tracking is the primary technique issue in it. Current facial tracking technology faces three challenges: (1) detection failure of some or all of features due to a variety of lighting conditions and head motions; (2) multiple and non-rigid object tracking and (3) features occlusion when the head is in oblique angles. In this paper, we propose a new active approach. First, the active IR sensor is used to robustly detect pupils under variable lighting conditions. The detected pupils are then used to predict the head motion. Furthermore, face movement is assumed to be locally smooth so that a facial feature can be tracked with a Kalman filter. The simultaneous use of the pupil constraint and the Kalman filtering greatly increases the prediction accuracy for each feature position. Feature detection is accomplished in the Gabor space with respect to the vicinity of predicted location. Local graphs consisting of identified features are extracted and used to capture the spatial relationship among detected features. Finally, a graph-based reliability propagation is proposed to tackle the occlusion problem and verify the tracking results. The experimental results show validity of our active approach to real-life facial tracking under variable lighting conditions, head orientations, and facial expressions.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2002.02a
• /
• pp.529-538
• /
• 2002

콤바인 곡물 포대 자동화장치개발은 콤바인 운전자 및 작업자의 피로경감과 안전보호 및 작업성능의 향상을 기하기 위하여 행하여 졌으며, 본 연구의 개발은 기존의 콤바인 작업이 2명이 소요되는 것을 운전자 1명이 수확작업을 할 수 있도록 하며, 노동력의 절감과 작업의 편리성을 도모하고자 하였다. 이러한 본 연구의 결과는 다음과 같다. 1) 곡물 포대의 정 위치화를 위해서 용량형 근접위치센서를 설치하였으며, 포대의 과다이송에 따른 모터의 부하를 최소화 하기위해 선단부와 슈트부에 각각 위치센서를 설치하여 포대의 위치를 제어하였다. 2) 곡물 투입장치부의 작동은 공기압축기와 공압실린더를 이용한 공압시스템을 사용하였으며, 곡물의 투입량제어는 슈트부 게이트의 열림시간을 제어하여, 곡물의 투입량을 제어하였다. 3) 포대 배출장치는 이송장치로부터 이송되어진 충진된 포대를 제 2의 포대가 충진하는 영역 밖으로 밸트 컨베이어를 이용 이송하도록 하였다. 4) 포대는 B3 포대의 경우가 가장 투입량이 많은 것으로 나타났으며, 가진을 한 경우가 하지 않은 경우보다 비교적 투입량이 많은 것으로 나타났다. 본 연구에서 개발된 포대 자동화장치에서는 포대의 가진 장치를 장착하지 않았으며, 실험은 인위적으로 가진을 하여 실행하였으며, 향후 전체적인 장치의 성능 향상을 위해서 포대의 가진 장치가 필요한 것으로 나타났다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.1021-1024
• /
• 2009

현재 사용되고 있는 통행시간 분류방법은 하나의 통행시간을 대푯값으로 가지고 있다. 이에 문제점은 고속도로 특성으로 규정 속도 이상의 속도로 주행하는 차량, 규정 속도 및 휴게소 이용차량, 운전자의 운전 습성, 통행 목적, 피로의 정도, 운전자 성향과 도로상황에 따라 통행시간이 다르게 나타나는 점이다. TCS(Toll Collection System) 자료는 고속도로의 다양한 특성이 포함되어 있으며, 대상 구간의 거리가 멀수록 목적지에 도달하는 통행시간의 분산이 커지는 특성 또한 보인다. 따라서 이를 처리하기 위한 효율적인 통행시간 분류, 구간대표통행시간 추출 알고리즘이 필요하다. 기존의 방법은 전체 통행차량의 통행시간을 감안한 방법으로 통행시간 예측시 정확성이 저하된다. 본 연구에서는 TCS 자료를 Fuzzy c-means 알고리즘을 이용하여 일일 고속도로 통행시간의 시간별 주행특성을 고려한 대푯 값을 추출하는 알고리즘을 제안하였다. 실제 서울-청주 구간을 운행한 TCS 자료를 가지고 실시한 실험으로, 주행특성 및 도로상황을 고려한 Fuzzy c-means를 이용한 통행시간 분류방법과 기존의 통행시간 분류 방법을 통한 통행시간을 PIFAB를 사용 TCS 자료의 실제 통행시간과 경로통행시간을 비교 평가하였다. 평가한 결과 본 연구에서 제안하는 Fuzzy c-means기법은 기존 방법인 MAD기법보다 75%, 신뢰구간(95%) 추출법 대비 81%의 정확성을 제고하였다.