• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.58-70
• /
• 2019

In the case of a pedestrian traffic accident, it has a large-scale danger directly connected by a fatal accident at the time of the accident. The domestic ITS is not used for intelligent risk classification because it is used only for collecting traffic information despite of the construction of good quality traffic infrastructure. The CNN based pedestrian detection classification model, which is a major component of the proposed system, is implemented on an embedded system assuming that it is installed and operated in a restricted environment. A new model was created by improving YOLO's artificial neural network, and the real-time detection speed result of average accuracy 86.29% and 21.1 fps was shown with 20,000 iterative learning. And we constructed a protocol interworking scenario and implementation of a system that can connect with the ITS. If a pedestrian accident prevention system connected with ITS will be implemented through this study, it will help to reduce the cost of constructing a new infrastructure and reduce the incidence of traffic accidents for pedestrians, and we can also reduce the cost for system monitoring.

• Journal of Korean Society of Transportation
• /
• v.24 no.4 s.90
• /
• pp.55-65
• /
• 2006

The ratio of Pedestrians in traffic accident fatality takes up 43% in Korea, which is 2.5 times as much as OECD's average. The traffic accidents features by road type shows that the fatality of the national highway posts the highest due to the accidents of pedestrians. Accordingly, the establishment of safety facilities for pedestrians is expected to increase on the rural roads for the prevention of pedestrian accidents. However, studies on pedestrians have been mainly focused on urban intersections. In Particular, studies on estimating the effectiveness of safety features for pedestrians are very poor. Thus, in this study. the Pedestrian accident probability model on four lane national highway was developed by using logit model. Also, this study analyzed and proposed the effect of facilities as a relative risk by using an odds ratio. As a result of the analysis, the Improvement of sight distance, installing sidewalks and lightings were proven effective alternatives for reducing the pedestrian accidents.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.162-164
• /
• 2022

Efforts are being made to prevent traffic accidents within the child protection zone. Efforts are being made to prevent accidents by enacting safety facilities and laws to prevent traffic accidents in the school zone. However, traffic accidents in school zones continue to occur. If the driver can know the situation in the child protection zone in advance, accidents can be reduced. In this paper, we design a camera that eliminates blind spots in school zones and a number recognition camera system that can collect pre-traffic information. Design a LIDAR system that recognizes vehicle speed and pedestrians. Design an LED guidance system that delivers information to drivers without smart devices. We study time series analysis and artificial intelligence algorithms that collect and process pedestrian and vehicle information recognized by cameras and LIDAR. In the artificial intelligence traffic accident prevention system learned by deep learning, before entering the school zone, the school zone information is sent to the driver through the Force Push Service and the school zone information is delivered to the driver on the LED sign. try to reduce accidents.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.3
• /
• pp.68-83
• /
• 2019

The number of pedestrian traffic accident fatalities is three times the number of car accidents in South Korea. Serious accidents are caused especially at intersections when the vehicle turns to their right. Various pedestrian collision warning services have been developed, but they are insufficient to prevent dangerous pedestrians. In this study, P2CWS is developed to warn approaching vehicles based on the pedestrians' characteristics. In order to evaluate the performance of the service, actual pedestrian data were collected at the intersection of Daejeon, and comparative analysis was carried out according to pedestrian characteristics. As a result, the performance analysis showed a higher accordance when the characteristics of the pedestrian is considered. Accordingly, we can conclude that identifying pedestrian characteristics in predicting the pedestrian crossing is important.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.5
• /
• pp.69-79
• /
• 2014

This paper proposes the Collision Prevention System based on Fuzzy which reasons a risk with the location information of vehicles and pedestrians and prevents collision between vehicles, and between a vehicle and a pedestrian with the reasoned risk. The proposed system provides three functions. First, it identifies a pedestrian's location with his smart phone and a vehicle's location with the GPS equipped in the vehicle. and transfers the identified information to their neighbors. Second, it makes a vehicle and a pedestrian reason a risk by considering a moving direction, a moving speed and road information. Third, it provides a vehicle and a pedestrian with the reasoned information such as route detour, speed reduction, etc. Therefore, the proposed collision prevention system based on Fuzzy not only prevents collision accidents beforehand by reasoning a risk, but also reduces a variety of losses by protecting traffic accident and congestion.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1248-1254
• /
• 2022

Efforts are being made to prevent traffic accidents in the school zone in advance. However, traffic accidents in school zones continue to occur. If the driver can know the situation information in the child protection area in advance, accidents can be reduced. In this paper, we design a camera that eliminates blind spots in school zones and a number recognition camera system that can collect pre-traffic information. It is designed by improving the LIDAR system that recognizes vehicle speed and pedestrians. It collects and processes pedestrian and vehicle image information recognized by cameras and LIDAR, and applies artificial intelligence time series analysis and artificial intelligence algorithms. The artificial intelligence traffic accident prevention system learned by deep learning proposed in this paper provides a forced push service that delivers school zone information to the driver to the mobile device in the vehicle before entering the school zone. In addition, school zone traffic information is provided as an alarm on the LED signboard.

• Journal of the Society of Disaster Information
• /
• v.20 no.2
• /
• pp.351-368
• /
• 2024

Purpose: In general, traffic accidents occur sporadically, so there are various limitations in terms of time and cost when conducting field investigations to prepare prevention and prevention measures. In particular, with the transition to a non-face-to-face society after the COVID-19, there is a greater need to prepare a replacement for field surveys. Therefore, in this study, Roadview provided by various websites was used as an alternative to field surveys in Sasang-gu, Busan City. The possibility was evaluated. Method: The research method was to extract vulnerable points for traffic accidents that occurred between 2016 and 22 and analyze road views based on the field survey evaluation items provided in the Traffic Safety Diagnosis Guidelines. Result: The main result was that Sasang-gu was most vulnerable to accidents involving elderly pedestrians at Sasang-ro, Daedong-ro, and Hakjang-ro. As a result of a detailed analysis of vulnerable points through Road View, Sasang-ro needed control of commercial vehicles and protection of the transportation vulnerable in the market commercial area. Daedong-ro was vulnerable to illegal on-street parking and slope merging sections, and Hakjang-ro was vulnerable to roads that were prone to speeding. When evaluating the possibility of replacing Roadview's field survey based on the results of this analysis, Roadview was able to effectively evaluate most items, such as separation of sidewalks and the location and spacing of safety facilities. However, there were limitations in items such as actual measurement performance. Conclusion: In other words, the road view can replace most field surveys, and the actual measurement evaluation items can be judged to be useful as auxiliary data, resulting in time and cost savings and high efficiency.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.1112-1117
• /
• 2010

The intelligent safety system for level crossing which employs information and communication technology has been developed in USA and Japan, etc. But, in Korea, the relevant research has not been performed. In this paper, we analyze the cause of railway level crossing accidents and the inherent problem of the existing safety equipments. Based on analyzed results, we design the intelligent safety system which prevent collision between a train and a vehicle. This system displays train approaching information in real-time at roadside warning devices, informs approaching train of the detected obstacle in crossing areas, and is interconnected with traffic signal to empty the crossing area before train comes. Especially, we present the video based obstacle detection algorithm and verify its performance with prototype H/W since the abrupt obstacles in crossing areas are the main cause of level crossing accidents. We identify that the presented scheme detects both pedestrian and vehicle with good performance. Currently, we demonstrate developed railway crossing intelligence system at one crossing of Young-dong-seon line of Korail with Sea Train cockpit.

• Journal of Trauma and Injury
• /
• v.32 no.3
• /
• pp.143-149
• /
• 2019

Purpose: No previous study has assessed elderly pedestrian traffic accidents based on a nationwide database. This study aimed to help primary physicians who examine patients in emergency departments to determine and make prompt and accurate treatment decisions. Methods: This study used data from the Emergency Department-based Injury Indepth Surveillance from 2013 to 2017, managed by the Korea Centers for Disease Control and Prevention. Pedestrians aged ${\geq}65years$ were included, and using multivariate logistic regression multiple factors were analyzed to determine their relationship with injury severity. Results: Of 227,695 subjects, 6,498 were included, of whom 2,065 (31.8%) were severely injured. There were more female than male patients in all severity groups. Most accidents occurred in the afternoon and on general roads. In the multivariate analysis, the odds ratio (OR) of injury severity for male pedestrians was 1.165 (95% confidence interval: 1.034-1.313, p=0.012). Older age of patients and the use of ambulances were associated with greater injury severity. The accident time affected the degree of injury severity; i.e., compared to dawn, injury severity increased in the morning (OR: 1.246, p=0.047) and decreased at night (OR: 0.678, p<0.001). A significant difference was noted in the correlation between the type of vehicle causing the accident and the accident severity; i.e., motorcycle accidents had lower severity than bicycle accidents (OR: 0.582, p=0.047). Conclusions: Injury severity was correlated with sex, age, transportation to the ED, TA onset time, and type of vehicle. The study results suggest that injury severity may be positively reflected in initial assessments and overall integrated treatments by physicians and in the related policies.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.3
• /
• pp.99-105
• /
• 2014

Since traffic accidents account for the highest proportion of the artificial disasters which occur in urban areas along with fire, more scientific an analysis on the causes of traffic accidents and various prevention measures against traffic accidents are needed. In this study, the research selected Jinju-si, which belongs to local small and medium-sized cities as a research target to analyze the characteristics of temporal and spacial distribution of traffic accidents by associating the data of traffic accidents, occurred in 2013 with the causes of traffic accidents and location information that includes occurrence time and seasonal features. It subsequently examines the spatial correlation between traffic accidents and the characteristics of urban space development according to the plans of land using. As a result, the characteristics of accident distribution according to the types of accidents reveal that side right-angle collisions (car versus car) and pedestrian-crossing accident (car versus man) showed the highest clustering in the density analysis and average nearest neighbor analysis. In particular, traffic accidents occurred the most on roads which connect urban central commercial areas, high-density residential areas, and industrial areas. In addition, human damage in damage conditions, clear day in weather condition, dry condition in the road condition, and three-way intersection in the road way showed the highest clustering.