• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.3
• /
• pp.1-9
• /
• 2012

In this paper, we propose a vision-based robust vehicle detection and inter-vehicle distance estimation algorithm for driving assistance system. We use the haar-like features of car rear-shadows, as well as the edge features for detecting of vehicles. The use of additional vehicle edge features greatly reduces the false-positive errors in the vehicle detection. And, after analyzing the conventional two inter-vehicle distance estimation methods: the location-based and the vehicle width-based, an improved inter-vehicle distance estimation algorithm which has the advantage of both method is proposed. Several experimental results show the effectiveness of the proposed method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.5
• /
• pp.26-37
• /
• 2009

This paper suggests a sensor's placement method for detecting the dilemma zone problem when real-time driver's safety service is provided at signalized intersections by multiple pointed traffic sensors using USN environments. For detecting the dangerous situations from vehicles accelerating through yellow intervals, red-light running and stopping abruptly like as dilemma zone problem, VISSIM(microscopic, behavior-based multi-purpose traffic simulation program) is used to perform a real-time multiple detection situation by changing the input data like as various inflow-volume, design speed change, driver perception and response time. As a result, the optimal interval of traffic sensors is 20~27m, and the initialized sensor location from stop-line is different according to road design speed. Moreover, the pattern of detection about dilemma zone is also different according to inflow-volumes. This paper shows that the method is useful to evaluate the sensor's placement problem based on micro-simulation and the results can be used as the basic research for USN services.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.109-123
• /
• 2024

Research into vision-based end-to-end autonomous driving systems utilizing deep learning and reinforcement learning has been steadily increasing. These systems typically encode continuous and high-dimensional vehicle states, such as location, velocity, orientation, and sensor data, into latent features, which are then decoded into a vehicular control policy. The complexity of urban driving environments necessitates the use of state representation learning through networks like Variational Autoencoders (VAEs) or Convolutional Neural Networks (CNNs). This paper analyzes the impact of different image state encoding methods on reinforcement learning performance in autonomous driving. Experiments were conducted in the CARLA simulator using RGB images and semantically segmented images captured by the vehicle's front camera. These images were encoded using VAE and Vision Transformer (ViT) networks. The study examines how these networks influence the agents' learning outcomes and experimentally demonstrates the role of each state representation technique in enhancing the learning efficiency and decision- making capabilities of autonomous driving systems.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.43-49
• /
• 2022

FMCW(Frequency Modulated Continuous Wave) Radar is very useful for vehicle collision warning system and autonomous driving sensor. In this paper, the design and implementation of FMCW radar based on two chip MMIC developed as an autonomous driving sensor was described. Especially, generation of frame-based and chirp-based waveform generation and signal processing are mixed to have the strength of maximum detection speed and compensation of speed. This implemented system was analyzed for performance and commercialization potential through lab. test and driving test in K-city.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.276-281
• /
• 2014

Necessities of a traffic means work a car in the modern society human to an usability of a life is enjoying. On the other hand, the damage by traffic accident increment the human quotient worked as we were in proportion to the vehicle which increased. Passing an examination moves necessarily on an obstacle to suddenly appear at the fronts if a car travels and the vehicles which stopped suddenly. Dynamic passing an examination about an obstacle turn on Vehicle Emergency Lamp to by hand when is unhurried, and can turn off, but to appear urgently dynamic passing an examination in time human is instinctive, but cannot inform an emergency to a back vehicle, and a rear-end collision occurs. A car we synthesize a speed of a vehicle, and this unit analyzes as we use GPS, and to drive runs Vehicle Emergency Lamp to automatic in the situations that shall turn on emergencies etc. If a speed of a vehicle continuously slows down in too high-speed driving or low-speed driving, or we are stopped, Vehicle Emergency Lamp is always turned on. It was built if we rise again as clearing itself from risk, and a speed of a vehicle judges, and we turn off Vehicle Emergency Lamp to automatic. It runs till rear-end collision sensor operates, and by hand reset does Vehicle Emergency Lamp a driving vehicle collides from behind to a back vehicle or when a driving vehicle was overthrown. It is shortened very much to the chain rear-end collision traffic accident that is a traffic accident of large size if we use this unit. And we did authentication through the experiment which a driver was helpful to unnecessary operation and a relaxed safe driving during drivings.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.259-260
• /
• 2008

이 논문은 노인 및 장애인의 활동을 보조하기 위한 보행보조 로봇의 기술인 사용자의 진행하고자 하는 방향과 속도를 검출하는 보행 보조 로봇의 조향 장치를 구현 하고자 한다. 최근에 노인인구의 증가로 인해 노인 및 장애인을 위한 보행 보조기에 대한 관심이 증가되고 있다. 그러나 대부분의 경우 동력이 없는 시스템으로 경사 등의 공간에서 취약성을 가지 고 있다. 이에 동력형 보행보조기에 대한 관심이 증가되고 있다. 대부분의 경우 보행보조기의 제어가 조정한다는 의미가 적합하였다. 그러나 이 논문에서는 사용자의 움직임이 손에 전달되는 힘에 의해 사용자의 의지력을 파악 하는 두가지형태의 조향장치를 구현하였다. 첫째로 가변저항을 이용하여 보행의지를 파악하고, 두 번째로 힘센서를 이용하여 보행의지를 파악하였다. 위 두가지 센서를 기초로 사용자가 이동하고자 하는 이동 방향과 이동 속도 데이터를 기초로 보행보조기의 차량 속도와 방향에 대해 구동 바퀴의 차동 구동을 통해 사용자의 의지에 맞춰 구동할 수 있도록 하였다.

• 한국항공운항학회:학술대회논문집
• /
• 2004.11a
• /
• pp.302-307
• /
• 2004

무인 항공기는 지상 조종 또는 자동 비행으로 원격제어, 각종 정찰, 수송, 및 공격 등의 다양한 임무를 수행할 수 있는 비행체 및 이를 포함한 시스템을 의미한다. 무인기의 자율 운항을 위해서는 위치, 속도 및 자세 등의 항법 정보를 제공하는 항법 시스템이 반드시 필요하며 크기가 작은 무인기를 위해서는 탑재체의 중량이 적은 항법 시스템이 반드시 필요하다. 최근에는 반도체 MEMS 기술을 이용한 저가형 관성 센서들이 많이 개발 되고 있으며 이를 이용한 소형, 저전력, 고정밀 항법 시스템들이 많이 연구 개발되고 있다. GPS/AHRS 결합 시스템은 자세각, 각속도, 가속도 정보 및 GPS를 이용한 위치, 슥도 정보 제공이 가능한 시스템으로 비행체의 자율비행을 위한 정보 제공이 가능한 시스템이다. 본 논문에서는 MEMS 센서를 기반으로한 GPS/AHRS 결합 항법 시스템 설계하고 차량을 이용하여 성능을 평가한 결과를 보여준다.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.6
• /
• pp.117-122
• /
• 2022

In this paper, we developed a vehicle control terminal using IoT and low-power long-distance communication (NB-IoT) technology. This system collects information on the location and status of a parked vehicle, and transmits the vehicle status to the vehicle owner's terminal in real time with low power to prevent vehicle theft, and in the case of a vehicle in motion, When primary information about the vehicle, such as an impact, is collected and transmitted to the server, the server analyzes the relevant data to generate secondary information on traffic congestion, road damage, and safety accidents. By sending it, you can know the exact arrival time of the vehicle at its destination. This terminal device is an IoT gateway for a vehicle and can be connected to various wired and wireless sensors inside the vehicle. In addition, the data collected from vehicle maintenance, efficient operation, and vehicles can be usefully used in the private or public sector.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.347-350
• /
• 2012

The researches on driver assistance systems that can prevent an accident have been actively performed due to social issues of traffic accidents with development of vehicle industry in recent. It is required for researchers to develope systems which assist driver's perception and judgment when considering that over 70% of traffic accidents occur by drivers' carelessness and 75% of the total accidents occur at the speed of less 29km per hour. In this paper, we implemented a front and rear vehicle monitoring system that monitors distance in real-time from a vehicle to obstacles at the low-speed or back-ward driving. The implemented system consists of a high angle ultrasonic sensor with distance detection of 10m and 10-degree angle, a wide angle ultrasonic sensor with the detection distance of 3m and a 180-degree, and a ATmega128 chip of ATmel company.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.15-27
• /
• 2022

In the past five years, the fatality rate of single-vehicle accidents has been 4.7 times higher than that of all accidents, so it is necessary to establish a system that can detect and respond to single-vehicle accidents immediately. The IoT(Internet of Thing)-based real-time traffic accident recognition system proposed in this study is as following. By attaching an IoT sensor which detects the impact and vehicle ingress to the guardrail, when an impact occurs to the guardrail, the image of the accident site is analyzed through artificial intelligence technology and transmitted to a rescue organization to perform quick rescue operations to damage minimization. An IoT sensor module that recognizes vehicles entering the monitoring area and detects the impact of a guardrail and an AI-based object detection module based on vehicle image data learning were implemented. In addition, a monitoring and operation module that imanages sensor information and image data in integrate was also implemented. For the validation of the system, it was confirmed that the target values were all met by measuring the shock detection transmission speed, the object detection accuracy of vehicles and people, and the sensor failure detection accuracy. In the future, we plan to apply it to actual roads to verify the validity using real data and to commercialize it. This system will contribute to improving road safety.