• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.556-559
• /
• 2021

해당 연구는 Insta evo 360° 카메라로 촬영한 Equirectangular 형태의 영상을 활용하여 보행자에게 위험한 차량을 구분한 후 실시간적으로 차량 접근 알림을 주는 시스템에 관한 연구이다. 360° 영상 속 위험 차량 탐지와 추적을 위해 파노라마와 일반도로 이미지 데이터 세트로 전이학습 된 You Look Only Once v5 (YOLOv5), 객체 추적 알고리즘 Simple Online and Realtime Tracking with a Deep Association Metric (DeepSORT), 그리고 실험을 통해 개발한 비 위험 차량 필터링 알고리즘을 활용한다. Insta evo 360° 카메라를 머리 위에 얹어 촬영한 영상을 개발한 최종 시스템에 적용한 결과, 약 90% 정확도로 영상에서 비 위험 차량과 위험 차량을 구분할 수 있고, 위험 차량의 경우 차량의 방향을 시각적으로 알려줄 수 있다. 본 연구를 바탕으로 보행자 시야각 외부의 위험 차량에 대한 경고 알림을 주어 보행자 교통사고 발생 가능성을 줄이고, 전방위를 볼 수 있는 360° 카메라의 활용 분야가 보행 안전 시스템뿐만 아니라 더 다양해질 것으로 기대한다.

• Journal of Korean Society of Transportation
• /
• v.32 no.2
• /
• pp.106-118
• /
• 2014

The objective of this study is to develop a methodology for evaluating the effectiveness of in-vehicle pedestrian warning systems. Driving Simulator-based experiments were conducted to collect data to represent driver's responsive behavior. The braking frequency, lane change duration, and collision speed were used as measure of effectiveness (MOE) to evaluate the effectiveness. Collision speed data obtained from the simulation experiments were further used to predict pedestrian injury severity. Results demonstrated the effectiveness of warning information systems by reducing the pedestrian injury severity. It is expected that the proposed evaluation methodology and outcomes will be useful in developing various vehicular technologies and relevant policies to enhance pedestrian safety.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.2
• /
• pp.255-260
• /
• 2017

In Korea, traffic accidents between pedestrians and vehicles in 2015 account for 38.8% of all accidents. This study proposes a system design that can measure the risk of conflict between a vehicle and a pedestrian. Firstly the systemdetect and estimate the position, speed, and directional data of the vehicle and the pedestrian. And then it estimate the conflict point between a vehicle and a pedestrian. The risk of conflict is quantified by estimating the pedestrian safety margin (PSM), which is the time difference between the arrival of the pedestrian at the crossing point to the point of conflict and the vehicle approaching the point. In this system each data is acquired through an external monitoring based evaluation module and an individual wearing module. In the future, such a system can be used for decision making such as the design of road hazard improvement facilities and the designation of the elderly protection area.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.2
• /
• pp.54-63
• /
• 2023

Pedestrian traffic needs to be accurately quantified to predict effectively pedestrian traffic accidents, however, pedestrian traffic is more difficult to measure than vehicle traffic. In this study, we suggest the time-and cost-effective application of mobile closed-circuit television (CCTV) using a smartphone as an alternative that can collect and analyze real-time data with little. In the present investigation, the pedestrian-vehicle conflict that can develop into an accident was defined as the pedestrian accident exposure. After installing mobile CCTV in 40 sections of Dongseong-ro, Daegu, the pedestrian accident exposure was estimated through negative binomial regression analysis using the collected data. The results of the analysis showed statistically significant changes in the pedestrian accident exposure variables. Based on the present results, a pedestrian accident exposure estimation model was developed which can be used in sections where pedestrian accidents may occur.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.19 no.5
• /
• pp.82-91
• /
• 2011

In this paper, a planar model for mechanics of a vehicle/pedestrian collision incorporating road gradient is derived to evaluate the pre-collision speed of vehicle. It takes into account a few physical variables and parameters of popular wrap and forward projection collisions, which include horizontal distance traveled between primary and secondary impacts with the vehicle, launch angle, center-of-gravity height at launch, distance from launch to rest, pedestrian-ground drag factor, the pre-collision vehicle speed and road gradient. The model including road gradient is derived analytically for reconstruction of pedestrian collision accidents, and evaluates the vehicle speed from the pedestrian throw distance. The model coefficients have physical interpretations and are determined through direct calculation. This work shows that the road gradient has a significant effect on the evaluation of the vehicle speed and must be considered in accident cases with inclined road. In additions, foreign/domestic empirical cases and multibody dynamic simulation results are used to construct a least-squares fitted model that has the same structure of the analytical one that provides an estimate of the vehicle speed based on the pedestrian throw distance and the band within which the vehicle speed would be expected to be in 95% of cases.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.440-448
• /
• 2015

A pedestrian collision warning system which makes a judgement of pedestrian's intention to help avoiding hitting accidents is proposed. This system uses the image sequences obtained from a car black box as well as vehicle's speed obtained from a GPS. It detects pedestrians, if any, based on the Histogram of Gradient method and extracts several information such as the pedestrian's relative positions, the direction of motion vectors, and distance between vehicle and pedestrian . A fuzzy logic based on these extracted information is applied to analyze the pedestrian's safety levels. When the safety level is determined to be danger, an alarm is triggered to the driver. The performance of the proposed algorithm is tested under various driving scenarios, which shows it works successfully in real-time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.767-768
• /
• 2017

국토교통부에 따르면 2014년, 대한민국의 자동차 1대당 인구수가 2.56명으로 기록되었다고 한다. 또한, 교통안전공단에 의하면, 2015년 총 교통사고는 23만 2035건이 발생하였고 이로 인한 사망자는 4621명이라고 한다. 그 중 약 53%인 12만 3760건이 폭이 9m 미만인 이면도로에서 발생하였고 이로 인한 사망자는 전체 사망자의 약 56%인 2586명이라고 한다. 이는 상당히 수의 사고들이 이면도로에서 일어나고 있음을 알려준다. 국민 안전의 측면에서 많은 사고의 위험이 있는 이면도로에 사고를 예방할 수 있는 대책이 시급하다. 이에 본 논문에서 IoT(사물인터넷)을 기반으로 한 이면도로에서의 사고 예방 장치를 제시하여 '차량과 차량'뿐만 아니라 '차량과 보행자', '차량과 자전거' 충돌사고 문제해결에 접목하였다.

• Journal of Korean Society of Transportation
• /
• v.24 no.3 s.89
• /
• pp.95-102
• /
• 2006

This study develops a methodology on how to assess the traffic safety benefit of advanced vehicular technology for Protecting pedestrian in pedestrian-vehicle collision. Safety benefit is defined here as the reduction of Pedestrian fatality by employing advanced vehicular technology. As an application of the proposed methodology the safety benefit of active hood lift system (AHLS) is assessed. Both actual accident data analysis and simulation experiment are conducted to establish statistical models that are used for estimating the reduction of pedestrian fatality It is believed that the developed methodology and outcomes would be greatly useful in developing various advanced vehicular technologies and establishing more effective traffic safety policies.

• Journal of Korean Society of Transportation
• /
• v.23 no.3 s.81
• /
• pp.49-57
• /
• 2005

This study developed a methodology for estimating the fatality reduction by introducing technical regulation on pedestrian protection in pedestrian-vehicle collisions. Modeling a probabilistic pedestrian fatality model with logistic regression approach was one of keen interests, which employed in estimating the fatality reduction. Collision speed obtained from the accident reconstruction was used in the model development. The effects of fatality reduction, in case various Head Injury Criterion (HIC) and collision speeds are applied for the regulation. were presented as the major outcome of this study. It is expected that the outcome of this study would be an invaluable tool to assist in developing various technologies and policies for pedestrian protection.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.3
• /
• pp.38-49
• /
• 2015

Seoul has 424 traffic fatalities in 2010 and 227 of them related to pedestrian crashes. In addition, it revealed that 40% of pedestrian fatalities occurred during jaywalking. Through the effective methods preventing jaywalking can save lots of people, and it can reduce social costs pertinent to pedestrian crashes. Therefore, this study is to suggest the methods preventing jaywalking through conducting literature reviews, human factors with pedestrian and vehicle characteristics, as well as geometric features of accident site or spot. Firstly, in order for examining the contributing factors of accident, this research conducts statistical analysis on pedestrian accidents specifically in jaywalking. Secondly, the analysis on human factors about pedestrian and drivers revealed that drivers with high speed play pivotal roles in pedestrian fatalities. Thirdly, Road and environment factors showed both expected and contradictory results through analyzing total numbers of lane or dry/icy pavement conditions. Consequently, this study can be used to prevent and alleviate pedestrian accidents as well as expected to be applied to future researches about pedestrian safety facilities.