• Proceedings of the KAIS Fall Conference
• /
• 2009.05a
• /
• pp.757-758
• /
• 2009

본 논문은 영상 처리 기법을 이용한 차량 조수석 탑승자 인식 방법을 제안하였다. 이 방법은 차량 내에 장착된 카메라로부터 실시간으로 동영상을 획득하여 조수석의 탑승자를 모니터링 하여, 조수석에 탑승자의 존재 유무와 탑승자의 자세 등을 인식한다. 본 논문의 방법은 조수석 영역의 불변 특징을 추출하고 움직임을 검출하여 탑승자의 상태를 인식한다. 실험에서 제안한 방법이 차량의 움직임과 밝기 변화와 같은 환경 변화에 강인한 인식 방법임을 보였다.

• International Journal of Highway Engineering
• /
• v.12 no.4
• /
• pp.47-51
• /
• 2010

A vehicle classification data is essential for traffic road planning and pavement. In this study, the vehicle height, vehicle criteria for classification applied to measure the height of the car driving has devised a way to install equipment. It is capable of measuring the vehicle height was confirmed to field experiments, the measurement system is obtained to the vehicle length and height data. In this experiment, results showed the accuracy of 88.6% compared to classification data using the discriminant function obtained from video replaying. The height of vehicle applying the classification criteria can be utilized to determine the vehicle class.

• Journal of the Korean Society for Railway
• /
• v.12 no.6
• /
• pp.865-872
• /
• 2009

Korean railroad company is continuously improving the service for the disabled. They also install and reform many facilities for them. However, It is not considered the importance of egress when fire occurred in a cabin Now, Fire hazard analysis and risk assessment are introduced into domestic regulations for improving fire safety performance of train car and railroad facilities. Considering the fact that fire safety evaluation process doesn't fully include disabled person, fundamental egress data for them is very important for life safety aspect. In this paper, Egress experiments and analysis were conducted to measure the movement speed of the disabled with Mugunghwa and Saemaul.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1279-1290
• /
• 2021

As vehicle technology has grown, autonomous driving that does not require driver intervention has developed. Accordingly, CAN security, an network of in-vehicles, has also become important. CAN shows vulnerabilities in hacking attacks, and machine learning-based IDS is introduced to detect these attacks. However, despite its high accuracy, machine learning showed vulnerability against adversarial examples. In this paper, we propose a adversarial CAN frame generation method to avoid IDS by adding noise to feature and proceeding with feature selection and re-packet for physical attack of the vehicle. We check how well the adversarial CAN frame avoids IDS through experiments for each case that adversarial CAN frame generated by all feature modulation, modulation after feature selection, preprocessing after re-packet.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.40 no.8
• /
• pp.485-494
• /
• 2016

In this work, we conducted a study of fuel consumption characteristics and regenerative braking recovery rate by conducting an experiment using a TMED type parallel hybrid electric vehicle. As regenerative braking technology is considered essential to improve the energy efficiency of the hybrid vehicle, it is necessary to conduct research on the regenerative braking system. Therefore, the electrical characteristics, current balance, and fuel consumption were investigated using an EC type chassis dynamometer with experimental conditions as per IM240 mode. From the results, it was observed that when the initial SOC condition was lower, the engine operating time of the hybrid vehicle increased, and the energy efficiency decreased. While operating in the driving mode characteristics condition and the driving characteristics condition, the difference in the average fuel consumption was not significant. However, after completion of the experiment, there was a difference in the engine operation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.89-96
• /
• 2017

This Paper proposes a vehicle detection system and a license plate recognition system from CCTV images installed on public roads. Since the environment of this system acquires the image in the general road environment, the stable condition applied to the existing vehicle entry / exit system is not given, and the input image is distorted and the resolution is irregular. At the same time, the viewing angle of the input image is more wide, so that the computation load is high and the recognition accuracy of the plate is likely to be lowered. In this paper, we propose an improved method to detect and recognize a license plate without a separate input control devices. The vehicle and license plate were detected based on the HOG feature descriptor, and the characters inside the license plate were recognized using the k-NN algorithm. Experimental environment was set up for the roads more than 45m away from the CCTV, Experiments were carried out on an entry vehicle capable of visually identifying license plate and Experimental results show good results of the proposed method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.9 no.3
• /
• pp.21-30
• /
• 1989

In this study, the dynamic behavior of a continuous bridge under moving load is studied considering roughness of the road surface. Vehicle model includes the spring effects of axes, and due to these effects, equations of motions for the vehicle and bridge are derived in coupled form. And then iteration method is used to solve the equations. In experimental study a bridge model is constructed considering the similarity rule in order that the model exhibits dynamic behavior similar to that of prototype. Three types of roughness such as uneven random roughness, uplift on the approach and piece-wise constant roughness are used to describe road roughness. Through the numerical analysis and experiments, the effects of surface roughness, sprung mass, and velocity on the dynamic behavior of the bridge are examined.

• Journal of the Korean Society for Railway
• /
• v.14 no.2
• /
• pp.137-142
• /
• 2011

A bimodal tram is a new design vehicle introduced to improve a current transportation system, and it has advantages of a bus and a subway. A pipe truss bridge, an exclusive road of the bimodal tram, is constructed for introduction of the bimodal tram. An analysis of dynamic response characteristics is required because this new bridge has never constructed before. A speed increasing test on the pipe truss bridge was conducted with attaching a sensor to bottom of the bridge. Also, Dynamic response characteristics were analyzed by measuring displacements, the maximum vertical and horizontal acceleration about the new bridge through the experiment.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.331-334
• /
• 2013

본 논문에서는 차량에 부착된 4대의 어안렌즈 카메라 영상을 이용하여 차량 주위 전방향의 주변 정보를 포함하는 정합 영상을 생성하고, 생성된 정합 영상에서 차선을 검출하는 알고리즘을 제안한다. 기존의 전방 카메라만을 이용하여 차선을 검출하는 방법들은 안개와 같이 기상 환경이 안 좋은 경우 가시거리가 짧아져 정상적인 차선 검출이 어려운 문제가 있다. 이에 반해 4대의 어안렌즈 카메라로 차량의 주변을 촬영한 영상은 기상 환경에 영향을 적게 받아 안정적인 차선 검출에 용이하다. 어안렌즈 카메라로 촬영한 영상은 왜곡이 심하기 때문에 왜곡 보정을 수행한 후 차량 위에서 아래로 내려다본 시점으로 투영 변환하여 하나의 영상으로 정합한다. 정합영상에서 관심영역을 설정한 후 차선 후보 영역을 검출하고, 검출된 후보 영역들로 차선을 직선으로 모델링한다. 점선 차선 구간이나 차량 흔들림에 대응하기 위해 직선으로 모델링된 차선 정보의 차선 각도와 차량으로부터 거리 정보를 칼만 필터 기반 추적 및 보정하여 안정적으로 차선 검출을 수행한다. 실험 결과 제안하는 방법은 실선구간에서 99.57%, 점선구간에서는 90.48%의 검출 정확도를 가진다.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.2 no.1
• /
• pp.81-88
• /
• 1998

과적차량의 통행에 의한 교량구조물의 손상도를 평가하는 방법의 개발이 매우 활발하다. 본 연구에서는 과거 15년동안 통행한 교통데이타를 분석하고, 이 데이타를 근거로 교량의 손상도를 분석한다. 차량의 분류는 4종으로 대표하여 차량하중을 분석하였으며 해석시에는 이를 대표하는 2종을 사용하였다. 3차원해석을 통하여 구한 영향면을 이용하여 부재력을 계산하고 이를 이용하여 등가응력범위를 구한다. 이 결과는 모형실험을 통하여 구한 피로결과와 비교하였다. 분석결과 설계하중을 초과하는 과적차량이 교량에 미치는 손상정도는 적은 통행빈도에도 불구하고 매우 큼을 알 수 있고, 이러한 실제교통량의 분석을 통한 교량의 손상평가방법은 과적차량에 의한 교량손상정도를 유용하게 평가할 수 있다.