• 반도체디스플레이기술학회지
• /
• 제22권3호
• /
• pp.161-165
• /
• 2023

One of the difficult works in an autonomous driving system is detecting road lanes or objects in the road boundaries. Detecting and tracking a vehicle is able to play an important role on providing important information in the framework of advanced driver assistance systems such as identifying road traffic conditions and crime situations. This paper proposes a vehicle detection scheme based on deep learning to classify and tracking vehicles in a complex and diverse environment. We use the modified YOLO as the object detector and polynomial regression as object tracker in the driving video. With the experimental results, using YOLO model as deep learning model, it is possible to quickly and accurately perform robust vehicle tracking in various environments, compared to the traditional method.

• 디지털산업정보학회논문지
• /
• 제9권4호
• /
• pp.69-79
• /
• 2013

A system of tracking a vehicle collects the vehicle location and then transmits the data into a GIS server in order to provide several service areas. An ODU built in the vehicle savesa GPS information data and communicates with the RSU installed in the road over the wave technology. The collected data in RSU is transmitted into the GIS serverand is stored. The system based on the collected GPS data in each vehicle is providing useful and various services between RSU and OBU. In this paper indicates that the system is designed in 2 phasesbased on the collected GPS data. The result comparing to process of GPS data created in 1 phase and 2 phase over the Web GIS service indicates that the capability of process of the GPS data in 2 phase is enhanced in "50.88% ~ 51.81%". Therefore, when the accident is happened the system of tracking the vehicle over GPS tech not only receives the information properly but also provides the emergence rescue services.

• 한국마린엔지니어링학회:학술대회논문집
• /
• 한국마린엔지니어링학회 2000년도 춘계학술대회 논문집(Proceeding of the KOSME 2000 Spring Annual Meeting)
• /
• pp.11-15
• /
• 2000

This paper provides a basic study on automatic of a trailer type vehicle which consists of two parts such as a tractor and a trailer Backward moving and parking control is very important to automate this type of vehicle. However it is very difficult to control such their motion since a trailer type vehicle is a non-holonomic system. Therefore in this paper we propose the backward path tracking control algorithm for a trailer type vehicle. And also this paper presents the results of simulation to verify the effectiveness of the proposed control algorithm.

• 한국자동차공학회논문집
• /
• 제17권2호
• /
• pp.1-9
• /
• 2009

A parking-assist system is defined that a driver adjusts vehicle velocity through brake pedal operation and parking-assist system controls the motion of the vehicle to follow a collision-free path. In this study, a motion control algorithm using Fuzzy inference is proposed to track a maneuvering clothoid parallel path. Simulations are performed under SIMULINK environments using MATLAB and CarSim for a vehicle model. As the vehicle model in MATLAB a bicycle model is used including lateral dynamics. The simulation results show that the path tracking performance is satisfactory under various driving and initial conditions.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제7권5호
• /
• pp.817-832
• /
• 2015

This paper presents a state feedback based backstepping control algorithm to address the trajectory tracking problem of an underactuated Unmanned Surface Vessel (USV) in the horizontal plane. A nonlinear three Degree of Freedom (DOF) underactuated dynamic model for USV is considered, and trajectory tracking controller that can track both curve trajectory and straight line trajectory with high accuracy is designed as the well known Persistent Exciting (PE) conditions of yaw velocity is completely relaxed in our study. The proposed controller has further been enriched by incorporating an integral action additionally for enhancing the steady state performance and control precision of the USV trajectory tracking control system. Global stability of the overall system is proved by Lyapunov theory and Barbalat's Lemma, and then simulation experiments are carried out to demonstrate the effectiveness of the controller designed.

• 한국ITS학회 논문지
• /
• 제16권6호
• /
• pp.219-230
• /
• 2017

본 논문에서는 확장형 칼만필터를 적용하여 영상센서 기반 차대도로간 트래킹 알고리즘을 제안한다. 일반적으로 횡방향 오프셋, 차선대비 상대경로각, 전방도로 곡률은 차선유지지원시스템의 경로추종 횡방향 제어기 구성 또는 차선이탈경보시스템의 경보 로직을 위한 중요 입력값으로 활용되는데 이를 위해 본 연구에서는 영상센서 차선인식 결과값인 이미지 상의 차선 추출점의 좌표값과 더불어 요레이트, 조향각, 차속 센서 측정값, 그리고 차량의 횡방향 운동방정식을 고려한 확장형 칼만필터를 적용하여 차대도로간 트래킹 정보를 추출한다. 제안된 차대도로간 트래킹 알고리즘의 유효성을 증명하기 위해 주행 테스트 도로 상에서 DGPS-RTK 장비를 이용하여 비교 검증하여 그 유효성을 보였다.

• 한국우주과학회:학술대회논문집(한국우주과학회보)
• /
• 한국우주과학회 2004년도 한국우주과학회보 제13권2호
• /
• pp.247-250
• /
• 2004

Tracking systems for launch vehicle consist mainly of radar transponder (beacon), RF switch or power divider, antennas as onboard system, and single or multiple radars as ground one. In this paper, tracking systems, which are applicable to KSLV (Korea Space Launch Vehicle)-l, are introduced and the electrical performances for developed prototypes are presented. We have also performed RF link analysis for both uplink and downlink, and estimated that the maximum distance to be able to track KSLV-l stably is dependent on uplink characteristic in our system.

• 전력전자학회논문지
• /
• 제18권4호
• /
• pp.376-386
• /
• 2013

This paper proposes an improved Maximum Power Point Tracking method and design methods of unmanned solar vehicle system by parts of hardware, unmanned driving control and power conversion. The hardware design is offered on the weight reduction and structural reliability by using structural analysis software. The technique of curve fitting is applied to unmanned control system due to minimizing the vehicle's behavior. Furthermore, lateral controller applying actuator dynamics is robust enough to prevent performance degradation by measurement noise regarding position and heading angle. The power conversion system contains battery charger system and tapped-inductor boost converter. In the battery charger system, variable step-size MPPT is conducted for quick response of maximum power point tracking. The validity of the proposed algorithm are verified by simulations and experiments.

• 대한조선학회논문집
• /
• 제42권4호
• /
• pp.299-306
• /
• 2005

To determine a guidance law which is suitable for Target Tracking System(TTS) of an underwater vehicle, the performance (hitting probability) of TTS were calculated with four different guidance schemes, considering underwater vehicle's manoeuvrability and characteristics of seeking equipment such as sonar To evaluate the performance of TTS with each guidance law, numerous target-tracking simulations of underwater vehicle were performed under the condition of target's various motion scenario. Furthermore, the effect of sonar characteristics to the performance of guidance law in TTS was studied by changing parameters of sonar such as frequency of ping and detecting error of target. The pursuit-tail guidance law showed the best performance among four different guidance laws. Complex motion of target from straight line to turning circle and zigzag movement, low frequency of sonar ping and large detecting error of target decreased the hitting probability.

• 한국지능시스템학회논문지
• /
• 제14권1호
• /
• pp.63-68
• /
• 2004

본 논문은 영상검지기를 이용하여 도로상에서 주행하는 차량의 움직임 추적 시스템에 필요한 탐지방법과 이동궤적을 추적하는 방법을 제안하여 차량의 움직임을 추적하는 시스템을 구현하였다. 도로상에서 주행하는 차량의 움직임을 측정하는 이유는 지능형 교통 시스템의 첨단교통관제에 필요한 정보를 제공한 수 있으며, 기존에 설치되어진 매설식 루프 검지기가 가지는 유지보수의 문제를 해결할 수 있다. 본 논문에서는 양방향 도로에서 주행하는 차량의 물체 탐지를 위하여 차영상 분석법을 기반으로 하였다. 이는 도로의 주변 환경이 빠르게 변화하기 때문에 배경영상을 사용하는 방법은 적합하지 않기 때문이다. 본 논문에서는 칼만필터와 이노베이션을 사용한 가변 탐색영역으로 차량의 이동 궤적을 추적하였다. 가변 탐색영역을 사용한 이유는 기존에 제한된 검색영역을 이용한 방법에서 나타나 질 수 있는 차량의 이동 속도 및 궤적의 변화에 따른 문제를 해결 할 수 있기 때문이다. 실험 결과 제한된 검색영역을 사용하는 방식보다 제안하는 방법이 우수한 성능을 보임을 알 수 있었다.