• International Journal of Advanced Culture Technology
• /
• v.10 no.2
• /
• pp.300-306
• /
• 2022

Currently, Korea is building traffic infrastructure using Intelligent Transport Systems (ITS), but the pedestrian traffic accident rate is very high. The purpose of this paper is to prevent the risk of traffic accidents by jaywalking pedestrians. The development of this study aims to detect pedestrians who trespass using the public data set provided by the Artificial Intelligence Hub (AIHub). The data set uses training data: 673,150 pieces and validation data: 131,385 pieces, and the types include snow, rain, fog, etc., and there is a total of 7 types including passenger cars, small buses, large buses, trucks, large trailers, motorcycles, and pedestrians. has a class format of Learning is carried out using YOLOv5 as an implementation model, and as an object detection and edge detection method of an input image, a canny edge model is applied to classify and visualize human objects within the detected road boundary range. In this study, it was designed and implemented to detect pedestrians using the deep learning-based YOLOv5 model. As the final result, the mAP 0.5 showed a real-time detection rate of 61% and 114.9 fps at 338 epochs using the YOLOv5 model.

• Journal of the Korean Society of Safety
• /
• v.26 no.4
• /
• pp.120-126
• /
• 2011

Under the current law or system, the range of traffic accident on the crosswalk does not reflect the characteristics of traffic accident and the pedestrian's walking pattern. Thus, this study conducted a video recording survey on the 250 spots which are high to traffic accident rate of pedestrian-vehicle to reset the range of traffic accident on or near the crosswalk considering the characteristics of traffic accident and the pedestrian's walking pattern. Based on the collected data through a video recording survey, this study analyzed the pattern of pedestrians and extracted the variables influenced in the pedestrian's walking pattern. After conducting the regression analysis, this study made the model of measuring the range of traffic accident on the crosswalk. Through all processes these, this study reset the range of traffic accident on the crosswalk which could minimize the disadvantages of pedestrian when they have an accident on the crosswalk and ensure the right of way of pedestrian.

• Journal of Korean Society of Transportation
• /
• v.28 no.5
• /
• pp.155-162
• /
• 2010

Elderly pedestrians account for more than 30% of all deaths in traffic accident and the number of elderly-related traffic accidents are increasing every year. Considering Korea's quickly aging society, drastic measures must henceforth be taken. Taking notice of the elderly living in and moving around the provinces, this research focused on analyzing the characteristics of elderly pedistrians' traffic accidents on provincial roads and developing an Equivalent Property Damage Only (EPDO) model. The authors collected 720 traffic accident data points from the police agency and developed the EPDO model, weighted differently by light injury, severe injury, and death using Multiple Regression Analysis. As a result, the speed of vehicles is the most influential variable in EPDO, and the shape of the road is significant as well. Therefore, various policies should be established like improving the environmental factors of provincial roads, like expanding speed-reduction treatments and signage, and setting up detours around areas of high elderly concentration.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.3
• /
• pp.413-418
• /
• 2015

As the elderly are increasing, traffic accidents which are related to the elderly are one of major issues in aged society. In this paper, we analyze traffic accident statistics for the elderly. Based on the analyzed data, safety message transmission system for the elderly pedestrians is introduced. The proposed system is based on the P2V(Pedestrian-to-Vehicle) communication which combines ICT(Information and Communication Technology) with vehicles and pedestrians. We introduce the concept and principle of the proposed system and discuss implementation issues for realizing the proposed system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.564-566
• /
• 2015

Red traffic light indicates a different meaning, the green one. Motorists and pedestrians in the crosswalk must stop or move in accordance with a signal light. However, the probability of an accident is high if you do not see or ignore these signals. In addition to the curved pedestrian crossing installed the announcement system using an infrared sensor is difficult. In this paper, we design and implement methods of detecting pedestrians using the camera. A camera installed on the pontoon walking up the pedestrian and the pedestrian detection range is set through the image. With the proposed system it is effective in detecting pedestrians in the crosswalk curved.

• Journal of Korean Society of Transportation
• /
• v.21 no.4
• /
• pp.47-56
• /
• 2003

There are no specific criteria deciding what type of crosswalk installs although 4 typed crosswalks at signalized intersections classify according to number of stop line, spacing from the border of intersections and existence of traffic islands or not. Accidents involving pedestrians at signalized intersections are classified by type of crosswalks by traffic volume, pedestrian volume at crosswalk, intersection geometry and phase in view of pedestrians' safety at 50 intersections in Gwangju. The Multiple regression models are applied to express the pedestrian accident rate. In addition, process deciding what type of crosswalk installs which includes accident rate involved pedestrian is changed into number of accident is represented to reduce number of accidents. This paper presents what type of crosswalk installs in order to reduce pedestrian involved accidents at new or existing crosswalk.

• Journal of Auto-vehicle Safety Association
• /
• v.10 no.4
• /
• pp.25-32
• /
• 2018

Due to the rapid increase in the number of vehicles, the physical and human losses caused by traffic accidents have become serious social problems. In the global trend, there have been active studies conducted on improving safety level of automobile in order to reduce the number of automobile accident. As a result of such research, traffic accidents continue to decline. In the case of South Korea, however, rate of death by automobile accident is 8.5 per 10,000 people and it is a seven rank among the countries in OECD (Organization for Economic Cooperation and Development). This average rate is almost double compared to average automobile accident rate per 10,000 vehicles, of other OECD countries in 2015. Consequently, many studies and policies currently have been conducted and made for increasing safety of pedestrians; however, they are only emphasizing characteristics of pedestrians and drivers. For this reason, this study suggests scenarios for establishment of test standard corresponding with domestic environment and international standard of AEB (Autonomous Emergency Braking) and conducts a real car test by scenarios by setting up a goal with a function for remaining distance after braking and then examine equation by comparing real car tests results and outcome after calculation. This is a theoretical method to predict a relative remaining distance after AEB prior to conducting a real car test for evaluation of safeness of automobile with AEB and it is expected that it solves problem of complication of real car test.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.138-150
• /
• 2020

Pedestrians are the most vulnerable road users. According to one analysis of traffic accidents over a five year period, pedestrians accounted for about 40% of all road traffic deaths in South Korea. Although some policy and engineering approaches have been taken to reduce and prevent traffic accidents, the annual accident change rate is -0.7%, which is insufficient. This study verifies the effectiveness of presenting visual messages to pedestrians and the effect from adding auditory messages to the visual messages. The experiment was conducted on crosswalks adjacent to an intersection, and safety behaviors were recorded for a total of 898 pedestrians and considered sufficient. As a result of the study, overall pedestrian safety behavior improved when both visual and auditory messages were presented, rather than just visual messages. Therefore, the results indicate it is more effective to provide a mixed visual/auditory form of messages, rather than providing single stimulus messages.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.7
• /
• pp.1556-1567
• /
• 2009

The death rate of pedestrian in car accidents in Korea is 2.5 times higher than the average of OECD countries'. If a system that can detect pedestrians and send alarm to drivers is built and reduces the rate, it is worth developing such a pedestrian detection system (PDS). Since the accident rate in which pedestrians are involved is higher at nighttime than in daytime, the adoption of nighttime PDS is being standardized by big auto companies. However, they are usually using night visions or multiple sensors, which are usually expensive. In this paper we suggest a method for nighttime PDS using single wide dynamic range (WDR) monochrome camera in visible spectrum band. In our experiments, pedestrians were accurately detected if only most edges of pedestrians could be obtained.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.9
• /
• pp.2280-2289
• /
• 2009

The death rate of pedestrians in car accidents in Korea is about 2.5 times higher than the average of OECD countries'. If a system that can detect pedestrians and send alarm to driver is built and reduces the rate, it is worth developing such a pedestrian detection system (PDS). Since the accident rate in which pedestrians are involved is higher at nighttime than in daytime, the adoption of nighttime PDS is being standardized by big auto companies. However, they are usually using expensive night visions or multiple sensors for their PDS. In this paper we propose a method for nighttime PDS using a monochrome visible spectrum camera. We could verify its superiority in both performance and real?time operation to existing algorithm through tests against video data taken in several different environments.