• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.2
• /
• pp.89-103
• /
• 2020

As we face an aging society, the demand for personal mobility for disabled and aged people is increasing. In fact, as of 2017, the number of electric wheelchair in the country continues to increase to 90,000. However, people with disabilities and seniors are more likely to have accidents while driving, because their judgment and coordination are inferior to normal people. One of the causes of the accident is the interference of personal vehicle steering control due to unbalanced road surface conditions. In this paper, we introduce a encoder type semantic segmentation algorithm that can recognize road conditions at high speed to prevent such accidents. To this end, more than 1,500 training data and 150 test data including road surface damage were newly secured. With the data, we proposed a deep neural network composed of encoder stages, unlike the Auto-encoding type consisting of encoder and decoder stages. Compared to the conventional method, this deep neural network has a 4.45% increase in mean accuracy, a 59.2% decrease in parameters, and an 11.9% increase in computation speed. It is expected that safe personal transportation will be come soon by utilizing such high speed algorithm.

• Journal of Korean Society of Transportation
• /
• v.24 no.7 s.93
• /
• pp.7-14
• /
• 2006

Most researches about rumble strips have Presented only the before-and-after analysis of the accidents. So, Researchers have not dealt with the estimation of rumble strip's effectiveness on the driver's alertness. In this study. the effectiveness of the rumble strips on the driver's alertness was estimated by measuring the bio-signal transmitted from the driver. The bio-signal acquired for this experiments were theta wave in central lobe. The experimental results revealed that the theta waves as measured form the drivers's head while in the rumble strip section differed from those while in non-rumbled section; 74 percent decrease in theta wave value, respectively. This fact finding could mean that the driver's alertness increased from 74 percent while in the rumble strip section of the road. In all five trials of driving experiments on the rumble strip section, all the drivers showed the best alertness as measured by the theta waves in the first driving trial.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.43-52
• /
• 2023

Traffic accidents among children have been decreasing after the installation of yellow carpets. However, the explanatory power of the causal relationship between yellow carpet installation and traffic accidents is still insufficient. The yellow carpet effect was analyzed in greater depth using virtual reality (VR) simulation experiments in various situation that could not be evaluated in existing actual vehicle research studies due to difficulties or risks in implementation. A target site where an actual yellow carpet was installed was selected and, implemented into a virtual environment. Subjects were made to, were gaze measurement equipment and ride the simulator. The visual/driving behavior before and after yellow carpet installation was compared, and a t-test analysis was performed for statistical verification. All the results were found to be statistically significant.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.213-224
• /
• 2009

This paper presents a new algorithm for estimating a driver's physical condition using real-time vision system and performs experimentation for real facial image data. The system relies on a face recognition to robustly track the center points and sizes of person's two pupils, and two side edge points of the mouth. The face recognition constitutes the color statistics by YUV color space together with geometrical model of a typical face. The system can classify the rotation in all viewing directions, to detect eye/mouth occlusion, eye blinking and eye closure, and to recover the three dimensional gaze of the eyes. These are utilized to determine the carelessness and drowsiness of the driver. Finally, experimental results have demonstrated the validity and the applicability of the proposed method for the estimation of a driver's physical condition.

• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.590-592
• /
• 2018

Taxis that are illegally parked on the road to catch customer can cause traffic congestion and sometimes cause traffic accidents. Stop position of taxis is determined by the long term experience of taxi drivers. In this study, We provide information to taxi drivers and customer who visit in first time through finding stop position of taxis by time. To do this, we used the Internet of Vehicle (IoV) data collected from sensors installed in 40 taxis. Previous studies attempted by forming a cluster around a taxi. Since this method is centered on a taxi, the position of the cluster changes depending on the location of the taxi. In this study, we use a road segmentation algorithm to solve these problems. Unlike the previous studies, since the cluster is formed around the road, the position of the cluster is fixed and it is not affected by the number of taxis, so it is possible to grasp the stop position in real time. The road segmentation is made up of 30m units, and map the taxi location data divided into hourly, weekday, and weekend to the nearest point. As a result of the mapping, it was difficult to see a big difference in the time of week because there were few taxis to operate on weekends, but in case of weekdays, the difference of stop position between the commute time zone and the night time zone was confirmed. The results of this study suggest that it will be possible to propose the prevention of taxi illegally driving taxi and the location of the taxi stand.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2014.06a
• /
• pp.152-154
• /
• 2014

우리나라 항만 입출항 통항 선박의 대형화, 고속화에 따른 해양안전사고가 증가하고 있어 항만 연안 해역에서의 해상교통안전 확보가 절실히 요구되고 있는 실정으로, 최근 국제항로표지협회(IALA)에서 항로표지 설계와 배치계획에 대한 의사결정을 지원할 수 있는 항로표지 전문 기능 시뮬레이터의 개발과 주요 항로의 항로표지 설계 및 계획 등을 검증할 수 있는 시스템 필요성을 제기하였다. 우리나라 주요 항로의 항로표지 설계와 적정 배치 여부 등을 검증하고 보완할 수 있는 시뮬레이션 시스템에 대한 개발이 진행되고 있다. 항로표지 3D 모델에 대한 항로표지 종류별, 속성별 세부사항을 검토하여 다양한 조합이 가능하도록 DB를 구성하였다. 항로표지 3D 모델링 작업데이터에 대하여 각 항로표지 시설물별 조합 경우의 수를 고려하여 다양한 조합이 가능하도록 DB 분류작업을 수행하였으며 항로표지별 폴리건수에 따른 샘플형상을 비교하여 시인성이 양호한 최소한의 폴리건 수(안) 제시하는 등 항로표지 시뮬레이션을 위한 항로표지 3D 구현 방식을 검토하였다.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1897-1898
• /
• 2008

본 논문에서는 비젼을 이용한 영상처리 기술을 기반으로 운전자의 피로도를 측정하여 졸음운전을 감지하여 경고하는 실시간 시스템을 제안한다. 제안된 시스템은 얼굴 영상 분석과 퍼지 이론을 이용하여 운전자의 졸음 또는 부주의함을 감지하여 경고함으로서 교통사고를 미연에 방지하는 시스템이다. 본 논문에서는 실시간 얼굴 탐색 알고리즘 개발을 위해 퍼지 색상 필터와 가상 얼굴 모형을 이용하여 얼굴위치 및 눈 영역을 보다 빠르게 검출하고, 눈 깜박임의 빈도수(Eye blinking frequency)와 눈의 닫힘 지속 기간(Eye closure duration)을 측정하는 방법은 제안한다. 그 다음, 측정된 데이터를 기반으로 퍼지논리를 사용하여 운전자의 피로도를 결정하고 졸음운전 여부를 감지 및 판단하는 방법을 제안한다. 마지막으로, 제안된 방법은 여러 실험을 통해 운전자의 졸음운전 감지 능력의 우수성을 증명한다.

• Journal of Advanced Navigation Technology
• /
• v.12 no.6
• /
• pp.627-633
• /
• 2008

In the case of traffic accidents, the broadcasting methods used in the mobile ad hoc network (MANET) cannot applied to transmit reliable message since moving high-speed in vehicular ad hoc networks (VANET) environments. In this paper, in order to guarantee transmitting reliable messages, we propose a collision avoidance method based-on directional antenna in VANET. In order to reduce interference from omni-broadcasting and to avoid hidden node problem from moving high-speed, we employed a forward-handed and backward directional antenna. The authors simulated the proposed method based on directional antenna and showed that the proposed method has been improved in respect to network utilization compared to existing VANET protocols.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.223-229
• /
• 2008

In this paper. we propose the real-time vision system which judges drowsiness driving based on levels of drivers' fatigue. The proposed system is to prevent traffic accidents by warning the drowsiness and carelessness using face-image analysis and fuzzy logic algorithm. We find the face position and eye areas by using fuzzy skin filter and virtual face model in order to develop the real-time face detection algorithm, and we measure the eye blinking frequency and eye closure duration by using their informations. And then we propose the method for estimating the levels of drivel's fatigue based on measured data by using the fuzzy logic and for deciding whether drowsiness driving is or not. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.