• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.319-320
• /
• 2022

교통량이 증가됨에 따라 높아지는 사고율을 줄이기 위해 효율적이며, 다양한 교통 위반 단속이 요구되고 있다. 기존의 유무인 교통법규 위반 단속 시스템의 도입으로 단속 구역 확대를 시도하고 있으나 높은 비용의 문제로 한정된 지역에서만 실시되고 있다. 해당 문제 해결을 위해 본 논문에서는 딥러닝 실시간 객체인식기술을 적용하여 차량의 교통법규 위반을 인식하며 이에 대한 정보를 제공하는 시스템을 개발하였다. 실시간 객체인식 알고리즘인 YOLOv4와 실시간 객체추적기술인 deepSORT 알고리즘을 데스크톱 PC에 적용하여 구현하였다. 개발한 시스템은 과속, 버스 전용 차로, 주정차, 급속 다차선 변경에 대한 인식 결과를 제공한다. 기존 설치된 CCTV 영상을 대상으로 시스템 적용이 가능하여 저비용으로 넓은 지역에 대한 교통법규 위반 상황 인식을 기대할 수 있다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.1
• /
• pp.203-211
• /
• 2014

Tunnel reduces travel time as and it is essential facilities for the eco-friendly road construction. In recent years, It has been accelerating the tunnel construction to provide a higher level of traffic service but a driver driving in the narrow and dark tunnel takes characteristically psychological anxiety and the restriction of the sight. Moreover, A driver passing through more than 1,000m long tunnel, as to pass inside the monotonous form of the tunnel for a long time can cause drowsiness and increase the driver load. This driver load can degrade road-holding of the inside of the long tunnel highly and pose a high risk of accidents. Accordingly, In this study is to present the proper length of the Tunnel, considering the characteristics of traffic accident. For this, this study is that the long tunnel that affects traffic safety traffic safety variables are selected and classified. Traffic safety variables are classified in detail as a variable of the traffic accident and velocity one, the applicable variables the number of the traffic accident, the ratio of the traffic accident, driving velocity, the individual vehicle velocity etc. Traffic safety variables are categorized as more than a pole length of the tunnel in order to examine its impact on correlation analysis. The results indicate significant results in traffic accidents in accordance with traffic accidents, traffic safety, selects the variable was Variable depending on the length of the tunnel traffic safety point of significantly increasing the possibility of an accident can be seen as a high point. And the point of the Distribution of selected variables in order to create a traffic safety was a significant increase in traffic safety variables was set at critical intervals. Before reaching the critical point and the corresponding length of the long tunnel was set at the proper length. In this study, the optimum length of the proposed long tunnel through the long tunnel that occur in the future to contribute to reducing traffic accidents would be able to be determined.

• Journal of Korean Society of Transportation
• /
• v.26 no.2
• /
• pp.17-24
• /
• 2008

Traffic accident forecasting model has been developed steadily to understand factors affecting traffic accidents and to reduce them. In Korea, the length of highways is over 3,000km, and it is within the top ten in the world. However, the number of accidents-per-one kilometer highway is higher than any other countries. The rapid increase of travel demand and transportation infrastructures since 1980's may influence on the high rates of traffic accident. Accident severity is one of the important indices as well as the rate of accident and factors such as road geometric conditions, driver characteristics and type of vehicles may be related to traffic accident severity. However, since all these factors are interacted complicatedly, the interactions are not easily identified. A structural equations model is adopted to capture the complex relationships among variables. In the model estimation, we use 2,880 accident data on highways in Korea. The SEM with several factors mentioned above as endogenous and exogenous variables shows that they have complex and strong relationships.

• Journal of the Korea Institute of Construction Safety
• /
• v.2 no.1
• /
• pp.9-15
• /
• 2019

Despite the efforts for enhancing the safety record, construction industry has been suffered from higher fatalities than other industries. The poor record of safety in construction industry means that there is a clear need for an effective countermeasure. As mentioned in previous studies, it is important to identify the type of activities or risks that are likely to cause accidents and to develop appropriate safety measures. Considering the large number of accident cases on the temporary installations including work platforms and work passages, the temporary installations should be managed first. To support it, this study aims to analyze falling accident cases on construction working platforms and passages which can lead to develop proper safety measures. Through the analysis of 1663 accident cases in the perspective of cost, progress, activity, and type of workers, this study identifies how the recent accidents occur and what is the cause of the accident occurrence. The identified causes of accident occurrence will help us to improve current construction safety.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.329-332
• /
• 2015

야간에 자동차를 운행할 때 검정색 차량 같은 어두운 색상의 자동차는 운전자가 인지를 못하는 경우가 많고 안개가 짙게 낀 상황도 운전자의 시야가 좁아져 교통사고율이 급격하게 증가한다. 도로교통공단의 자료에 의하면 최근 5년(2009~2013) 동안 가해자의 안전거리 미확보로 인한 교통사고는 매년 감소하는 것으로 나타나지만, 안전운전 의무 불이행 다음으로 두 번째로 높은 사고 건수를 기록하고 있다. 이는 아직도 운전자의 시인성 저하에 대한 방안이 부족하기 때문이다. 시인성 저하를 위한 대책으로 BMW, AUDI, Benz 회사에서 적외선 카메라를 이용한 나이트 비젼이 있으나 거리감지기능이 없어 디스플레이를 계속 주시하면서 운행하여야 하므로 시야가 좁아져 다른 위험이 발생할 수 있다. 현재 시중에 제공되고 있는 적외선 나이트 비젼 카메라를 이용하였을 때 일반 시야보다 약 4배 정도의 거리를 인식할 수 있었고, 이러한 나이트 비젼의 장점을 활용하여 전면 차량과의 안전거리를 확보하는 시스템을 제안한다. 본 논문에서는 제시하는 시스템은 시인성이 떨어지는 환경을 가정하여 설계하였고 나이트 비젼 카메라를 이용해 디스플레이로 출력하여 육안으로 구분할 수 없는 물체도 인지할 수 있어 헤드라이트를 켜고 운행할 때보다 안전한 운행을 할 수 있을 것으로 보인다. 하지만 디스플레이를 지속적으로 주시하며 운행할 경우 거리 감각이 떨어져 근접해 오는 물체와의 충돌 사고를 막기 힘들 것으로 보인다. 따라서 이러한 단점을 보안하기 위해 영상 데이터를 활용하여 앞 차량의 유무를 파악하고 차량이 있을 때 안전거리를 디스플레이에 표시함으로 앞 차량과의 거리를 유지하여 사고를 예방하여 안전 운행이 가능하도록 설계하였다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.1 s.19
• /
• pp.67-76
• /
• 2002

At a recent, with an increase of traffic demand and a spread of automobile culture, the safety, convenience and speed of highway is required. On this study, using the real time kinematic GPS, observation value at a center line of ready-built road is obtained and then design specification of highway, IP, IA and R are obtained by least square method. Using those IP, IA and R, we analysed the risk factor of highway alignment by the standard for structure and facility of the road. With using RTK GPS, we could analyse dangerous element of highway alignment rapidly and cope with dangerous area of the existing road. It is also proved to apply availably whether we determine alignment improvement is needed or not or analyze source of accident related with alignment in the region having a high traffic accident rate.

• Journal of Korean Society of Transportation
• /
• v.18 no.5
• /
• pp.7-16
• /
• 2000

This paper is focused on verifying time-space repetition of the highway accident and finding the their causes and deterrents. We classify all months into several seasonal groups, develop the model for each seasonal group and analyze the results of these models for Joong-bu highway. The existence of seasonal effect is verified by the analysis or self-organizing map and the accident indices. Agglomerative hierarchical cluster analysis which is used to decide the seasonal groups in accordance with accident patterns, winter group, spring-fall group. and summer group. The accident features of winter group are that the accident rate is high but the severity rate is low. while those of summer group are that the accident rate is low but the severity rate is high. Also, the regression model which is developed to identify the accident Pattern or each seasonal group represents that the season-related factors, such as the amount of rainfall, the amount of snowfall, days of rainfall, days of snowfall etc. are strongly related to the accident pattern of evert seasonal group and among these factors the traffic volume, amount of rainfall. the amount of snowfall and days of freezing importantly affect the local accident Pattern. So, seasonal effect should be considered to the identification of high-risk road section. the development of descriptive and Predictive accident model, the resource allocation model of accident in order to make safety management plan efficient.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.3
• /
• pp.96-106
• /
• 2014

Necessarily traffic policies have been biased in car than pedestrian, so pedestrian's environment is getting worse. Result of this situation our accident rate is high as 36.4%, compared to OECD member countries with average rate of 17.8%(in 2009). Increasing interest for pedestrians environment improvement, and it make an effort to build environment to guarantee walk and safety of pedestrians. Analysis on the binary logistic regression(BLR) was used. The dependent variable is occurring from the road width of less than 9m accident, and independent variable extracted can be obtained from the traffic accident data. Traffic accident on roads having width of less than 9 meters affecting variables is when the driver is straight, when the driver is female, when the pedestrian is walk driveway, and so on. To prevent it, efforts is demanded to protect handicapped, to build safe pedestrians environment using C-ITS and to decrease speed of going straight vehicle on roads having width of less than 9 meters.

• 전자공학회논문지 IE
• /
• v.46 no.1
• /
• pp.31-36
• /
• 2009

This study was to simulate it that the sending receiving vehicles run on the general national roads with the one-way two-lanes at 80[km/h] speed. This study was to select 280[m] radius of curvature based on the statistical data with high rate of traffic accidents, 140[m] length of direct roads considering the stopping stadia, 90[m] length of curve, and 8 points of curved roads at 11.25[m] intervals. As a result above, when the distance between the sending and receiving vehicles became more than 111[m], the propagation path of reflected wave by the adjacent vehicles became longer than the propagation path of reflected wave by the left/right reflectors because the number of repeated reflection increased. In this study, the repeated reflection for the propagation's reach to the receiving vehicles was about $1{\sim}2$[times] as it supposed it less than 111[m]. Accordingly, it found out that the propagation path of reflected wave received through the left/right reflectors was about $1{\sim}1.5[m]$ larger than the reflected wave produced by the adjacent vehicles regardless of lanes on which the sending and receiving vehicles were located.

• Journal of Navigation and Port Research
• /
• v.34 no.6
• /
• pp.471-477
• /
• 2010

In recently, IMO consider including an marine casualty factor when Port State Control Inspection evaluate.. This paper proposes an evaluation to Target Factor Values of Port State Control Inspections(PSCITFV) using absolute measurement. To this solve, therefore, this paper used the absolute measurement which is informed compensate the defect and the more rational and objective methode, checked the effectiveness to compare an result with absolute measurement and PSCITFV of Tokyo MOU using Wilcoxson test. Finally, rate change of PSC was investigated by an experiment which changed the values of evaluation factors. As a result, it was evaluation factors of high rate change that was detention, ship's age, casualty factors. Therefore, this factors have to a priority management to do for prevent of PSC.