• 한국ITS학회 논문지
• /
• 제12권6호
• /
• pp.78-86
• /
• 2013

본 논문에서는 효율적인 차량 영상 안정화를 위한 고성능 차량 영상 정보 시스템을 제안한다. 제안된 시스템은 움직임 추정 및 움직임 보상으로 분할하여 설계하였다. 움직임 추정은 지역 모션 벡터 추정 및 불규칙 지역 모션 검출, 전역 모션 벡터 추정으로 구성하였다. 움직임 보상은 추정된 전역 모션 벡터를 사용하여 차량의 영상 흔들림을 보상하기 위해 네 방향에 대하여 보정을 하였다. 설계된 알고리즘은 차량 영상 안정화를 위해 IP에 적용하여 움직임 보정 기술 칩을 설계하였다. 본 논문의 결과, 움직이는 물체에 대한 차량 영상 안정화는 메모리를 사용하지 않고 실시간 처리를 했기 때문에 다른 방법과 비교하여 효율성을 입증하였다. 또한, 블록 정합을 통한 연산으로 계산 시간 감소 효과를 얻었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1130-1133
• /
• 2003

The goal of this research is developing advanced lane detecting algorithm for unmanned vehicle. Previous lane detecting method to bring on error become of the lane loss and noise. Therefore, new algorithm developed to get exact information of lane. This algorithm can be used to AGV(Autonomous Guide Vehicle) and LSWS(Lane Departure Warning System), ACC(Adapted Cruise Control). We used 1/10 scale RC car to embody developed algorithm. A CCD camera is installed on top of vehicle. Images are transmitted to a main computer though wireless video transmitter. A main computer finds information of lane in road image. And it calculates control value of vehicle and transmit these to vehicle. This algorithm can detect in input image marked by 256 gray levels to get exact information of lane. To find the driving direction of vehicle, it search line equation by curve fitting of detected pixel. Finally, author used median filtering method to removal of noise and used characteristic part of road image for advanced of processing time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2483-2503
• /
• 2016

Traffic congestion is a severe problem in many modern cities around the world. Real-time and accurate traffic congestion identification can provide the advanced traffic management systems with a reliable basis to take measurements. The most used data sources for traffic congestion are loop detector, GPS data, and video surveillance. Video based traffic monitoring systems have gained much attention due to their enormous advantages, such as low cost, flexibility to redesign the system and providing a rich information source for human understanding. In general, most existing video based systems for monitoring road traffic rely on stationary cameras and multiple vehicle tracking method. However, most commonly used multiple vehicle tracking methods are lack of effective track initiation schemes. Based on the motion of the vehicle usually obeys constant velocity model, a novel vehicle recognition method is proposed. The state of recognized vehicle is sent to the GM-PHD filter as birth target. In this way, we relieve the insensitive of GM-PHD filter for new entering vehicle. Combining with the advanced vehicle detection and data association techniques, this multiple vehicle tracking method is used to identify traffic congestion. It can be implemented in real-time with high accuracy and robustness. The advantages of our proposed method are validated on four real traffic data.

• 한국통신학회논문지
• /
• 제37권7C호
• /
• pp.584-591
• /
• 2012

Distributing a Certificate Revocation List (CRL) quickly to all vehicles in the system requires a very large number of road side units (RSUs) to be deployed. In reality, initial deployment stage of vehicle networks would be characterized by limited infrastructure as a result in very limited vehicle to infrastructure communication. However, every vehicle wants the most recent CRLs to protect itself from malicious users and malfunctioning equipments, as well as to increase the overall security of the vehicle networks. To address this challenge, we design and implement a nomadic device based CRL acquisition method using nomadic device's communication capability with cellular networks. When a vehicle could not directly communicate with nearby RSUs, the nomadic device acts as a security mediator to perform vehicle's security functions continuously through cellular networks. Therefore, even if RSUs are not deployed or sparsely deployed, vehicle's security threats could be minimized by receiving the most recent CRLs in a reasonable time.

• 정보처리학회논문지A
• /
• 제16A권5호
• /
• pp.381-388
• /
• 2009

무선인터넷 기술의 발달과 응용의 확산으로 위치정보를 이용한 위치기반 서비스 형태는 더욱더 다양해 지고 있다. 특히, 언제 어디서나 사람과 사물 같은 객체의 위치를 인식하고 이를 기반으로 유용한 서비스를 제공하는 유비쿼터스 위치기반 서비스(Ubiquitous Location Based Services : u-LBS)가 중요한 서비스로 대두되고 있다. 이와 관련하여 본 논문에서는 차량 충돌 위치와 관련한 서비스 시스템을 제안한다. 제안 된 시스템에서 사용된 GPS Packet에는 위치에 대한 정보와 차량 충돌에 대한 충돌 세기와 시간, 차량에 대한 NodeID 등으로 구성되어 있다. 이러한 데이터들을 이용하여 하나의 패킷이 만들어 지게 되고 차량 간 충돌이 발생할 경우 차량에서 Gateway로 전송된다. Gateway에서 Server로 전송된 패킷은 충돌 여부를 판단하여 위급상황으로 판단되면, 구급센터로 위치정보와 충돌측정여부에 대하여 알려주게 된다. 또한, 이러한 위급상황에 대해서는 외부에 있는 가족 등의 관련된 사람들에게 무선으로 무선단말기(PDA, 휴대폰)를 통해 알려주게 된다. Server에 들어오게 되는 충돌 정보들은 Database에 저장이 되도록 구성하였다. 아울러, 제안한 u-LBS시스템의 유효성을 검증하기 위한 실험을 수행하였다.

• 한국지능시스템학회논문지
• /
• 제20권3호
• /
• pp.400-405
• /
• 2010

본 논문은 차량 안전시스템을 위한 지능형 HUD 시스템의 특성을 고찰하였다. HUD 시스템은 차량에서 향상된 운전자 정보전달과 새로운 지능형 교통시스템을 제공한다. 자동차의 속도, 거리표시, 엔진 RPM, 내비게이션, 엔진 온도, 연료 게이지, 방향지시등, 경고 표시등에 대한 기본적인 정보를 운전자에게 전달한다. 본 논문에서 설계한 지능형 HUD 시스템은 TFT LCD, LCD 백라이트 LED, 평면 미러, 특수 제작된 렌즈 및 구동회로로 구성되었다. 본 논문은 운전자 안전성을 고려한 차량용 지능형 HUD 시스템을 제작, 분석하였다.

• 한국공간정보시스템학회 논문지
• /
• 제11권2호
• /
• pp.39-44
• /
• 2009

In order to make the effect of the navigation system more direct, the paper proposes a thought of vehicle navigation system based on Video-GIS. A semantic framework has been defined whose core is focused on the integration and interaction of video and spatial information, which supports full content retrieval based on multimodal metadata extraction and fusion, and supports kinds of wireless access mode. Furthermore, requirements of prototype system are discussed. Then the design and implementation of framework are discussed. Next, describe the key ideas and technologies involved. Finally, we point out its future research trend.

• 한국자동차공학회논문집
• /
• 제15권1호
• /
• pp.71-77
• /
• 2007

Dangerous driving is a major cause of traffic accidents in Korea. It becomes more serious for commercial vehicles due to higher fatality rates. The Safe Driving Management System (SDMS), developed in this research, is a comprehensive solution that monitors and stores driving conditions of vehicles, detects dangerous driving situations, and analyzes the results in real time. The Safe Driving Management System consists of a vehicle movement information controller, a dangerous driving detection algorithm and a vehicle movement data report and analysis program. The dangerous driving detection algorithm detects and classifies dangerous driving conditions into representative cases such as sudden acceleration, sudden braking, sudden lane change, and sudden turning. Both computer simulation and vehicle test have been conducted to develop and verify the algorithm. The Safe Driving Management System has been implemented on commercial buses to verify its reliability and objectivity. It is expected that the system can contribute to prevention of traffic accidents, systemization of safe driving management and reduction of commercial vehicle operation costs.

• 제어로봇시스템학회논문지
• /
• 제14권8호
• /
• pp.809-817
• /
• 2008

This paper describes an obstacle detecting system of an unmanned ground vehicle (UGV). The unmanned ground vehicle is consists of several systems such as vehicle control system, navigation system, obstacle detecting system and integration system. Among these systems, the obstacle detecting system is a driving assistance system of UGV. Through the UGV is driving, the system detects obstacles such as cars, human, tree, curb and hills and then send information of obstacles position to integration system for safety driving. In this research, the obstacle detecting system is composed of 5 laser scanners and develop algorithms of detecting obstacles, curb, uphill and downhill road.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2006년도 춘계공동학술대회 논문집
• /
• pp.1170-1177
• /
• 2006

We apply VRP(Vehicle Routing Problem) to sludge collection system in this study. Sewage stores of villages are located in each village around a multipurpose dam. Sludge which is produced in sewage store of village is transported from the sewage store of village to the sewage treatment plants by the special purpose vehicle such as the tank lorry. In this paper, we propose sludge collection strategies which allocate each sewage store of village to sewage treatment plants and decide the schedule of sludge collection in order to collect sludge efficiently. The strategies aim to decrease transportation cost with deciding proposed vehicle routing and scheduling the sludge collection. When we decide route of vehicles, we consider the collection time in sewage store of village, distance between sewage store of villages and vehicle information as average velocity of vehicle, operation time of vehicle driver. We also develop the SCMS(Sludge Collection Management System) based on windows system with real data which is used in certain circumstance. And we experiment to figure out vehicle route and transportation cost throughout changing input data.