http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
MeanShift 기법을 이용한 차량 종횡방향 통합 궤적 생성 시스템 개발
황준연(Junyeon Hwang),이동휘(Donghwi Lee),허건수(Kunsoo Huh),나혁민(Hyuckmin Na),강형진(Hyungjin Kang) 한국자동차공학회 2009 한국자동차공학회 학술대회 및 전시회 Vol.2009 No.11
The longitudinal-lateral vehicle control techniques have been widely used in several active driver assistance systems. The lane keeping assistant control, vehicle platooning and adaptive cruise control are typical examples of their. In this study, a path planning method is proposed considering the driving environment such as road shape, ego vehicle and surrounding vehicles’ movement. The relative velocity and distance between the ego vehicle and surrounding vehicles are recognized with respect to the predicted lane shape in front of the ego vehicle. Based on the recognized information, the road shape and surrounding vehicles are mapped into the 8-bit gray scale image and the desired vector for the ego vehicle’s movement is determined by the maximum intensity density tracing. The desired vehicle path is followed by the acceleration/ deceleration control and the steering assist control, respectively. In order to evaluate the performance of the proposed system, simulations are conducted with typical LKAS and ACC systems.
황준연(Junyeon Hwang),허건수(Kunsoo Huh),조동일(Dong-il Cho),박장현(Jahng-hyun Park) 한국자동차공학회 2006 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-
Obstacle detection is a crucial issue for driver assistance system as well as for autonomous vehicle guidance function and it has to be performed with high reliability to avoid any potential collision. The vision-based obstacle detection systems are regarded promising for this purpose because they require little infrastructure on a highway. However, the feasibility of these systems in passenger car requires accurate and robust sensing performance. In this paper, an obstacle detection system using stereo vision sensors is developed. This system utilizes ROI setup, feature extraction, feature clustering and feature matching regarded epipoplar constraint in order to robustly detect the initial corresponding pairs. After the initial detection, the system executes the tracking algorithm for the obstacles. Then, the position parameters of the obstacles or leading vehicles can be obtained. The proposed obstacle detection system is implemented on a passenger car and its performances are verified experimentally.
비젼센서와 DRPG알고리즘을 이용한 차선 유지 보조 시스템 개발
황준연(Junyeon Hwang),허건수(Kunsoo Huh),나혁민(Hyukmin Na),정호기(Hogi Jung),강형진(Hyungjin Kang),윤팔주(Paljoo Yoon) 한국자동차공학회 2009 한국 자동차공학회논문집 Vol.17 No.1
Lane Keeping Assistant Systems (LKAS) require the cooperative operation between drivers and active steering angle/torque controllers. An LKAS is proposed in this study such that the desired reference path generation (DRPG) system generates the desired path to minimize the trajectory overshoot. Based on the reference path from the DRPG system, an optimal controller is designed to minimize the cost function. A HIL (Hardware In the Loop) simulator is constructed to evaluate the proposed LKAS system. The single camera is mounted on the simulator and acquires the monitor images to detect lane markers. The performance of the proposed system is evaluated by HIL system using the Carsim and the Matlab Simulink.
모델기반 예측 제어기를 이용한 차선유지 보조 시스템 개발
황준연(Junyeon Hwang),허건수(Kunsoo Huh),나혁민(Hyukmin Na),정호기(Hogi Jung),강형진(Hyungjin Kang),윤팔주(Paljoo Yoon) 한국자동차공학회 2009 한국 자동차공학회논문집 Vol.17 No.3
Lane keeping assistant system (LKAS) could save thousands of lives each year by maintaining lane position and is regarded as a promising active safety system. The LKAS is expected to reduce the driver workload and to assist the driver during driving. This paper proposes a model based predictive controller for the LKAS which requires cooperative driving between the driver and the assistance system. A Hardware-In-the-Loop-Simulator (HILS) is constructed for its evaluation and includes Carsim, Matlab Simulink and a lane detection algorithm. The single camera is mounted with the HILS to acquire the monitor images and to detect the lane markers. The simulation is conducted to validate the LKAS control performance in various road scenario.
단일 카메라를 이용한 차량 감지 및 추적 시스템의 개발
황준연(Junyeon Hwang),허건수(Kunsoo Huh),나혁민(Hyukmin Na),정호기,강형진(Hyungjin Kang),윤팔주(Paljoo Yoon) 한국자동차공학회 2009 한국자동차공학회 부문종합 학술대회 Vol.2009 No.4
The vision-based vehicle detection systems are regarded promising for this purpose because they require little infrastructure on a highway. However, the feasibility of these systems in passenger car requires accurate and robust sensing performance. In this paper, a vehicle detection system using single camera is developed. This system utilizes polar histogram, morphological techniques, labeling and normalized cross correlation. After the detection process, the system executes the inverse perspective mapping and Kalman filter algorithm. The proposed vehicle detection system is implemented on a passenger car and its performances are verified experimentally.
스테레오 비전센서를 이용한 선행차량 감지 시스템의 개발
황준연(Junyeon Hwang),홍대건(Daegun Hong),허건수(Kunsoo Huh) 한국자동차공학회 2008 한국 자동차공학회논문집 Vol.19 No.6
Preceding vehicle detection is a crucial issue for driver assistance system as well as for autonomous vehicle guidance function and it has to be performed with high reliability to avoid any potential collision. The vision-based preceded vehicle detection systems are regarded promising for this purpose because they require little infrastructure on a highway. However, the feasibility of these systems in passenger car requires accurate and robust sensing performance. In this paper, an preceded vehicle detection system is developed using stereo vision sensors. This system utilizes feature matching, epipoplar constraint and feature aggregation in order to robustly detect the initial corresponding pairs. After the initial detection, the system executes the tracking algorithm for the preceded vehicles including a leading vehicle. Then, the position parameters of the preceded vehicles or leading vehicles can be obtained. The proposed preceded vehicle detection system is implemented on a passenger car and its performances is verified experimentally.
레이더와 카메라 정보 융합을 이용한 목표차량 선정 기법의 개발
황준연(Junyeon Hwang),박승범(Seungbum Park) 한국자동차공학회 2010 한국자동차공학회 학술대회 및 전시회 Vol.2010 No.11
In the Advanced Driver Assistance System research field, the importance of the sensor fusion systems is rapidly focusing in recent years. With the increasing of the supplement of radar and camera sensors, the systems of ADAS such as LKAS, SCC and CDM are integrated and newly developed by adding brand new functions. Therefore, the sensor fusion system is almost a necessity for car industry. In this paper, the path from radar and lane information from camera is developed. The path-lane data fusion system is organized with three trajectories, the path only range, path-lane range and lane only range. Each range is designed to consider the driver physical time delay and lateral variation from extrapolated lane model. And the proposed system is verified by real vehicle experiments.
자율주행 차량의 카메라 Fail Operational 제어에 관한 연구
황준연(Junyeon Hwang),손영섭(Youngseop Son) 한국자동차공학회 2011 한국자동차공학회 부문종합 학술대회 Vol.2011 No.5
The longitudinal-lateral vehicle control techniques for ADAS have been widely used in several active driver assistance systems and aims the crash free autonomous system. The camera and radar sensor are necessary elements and the lane keeping assistant control, vehicle platooning and adaptive cruise control are typical examples of their. These systems are not only rapidly adapted in passenger vehicle but related fail safe logics are also widely proceeded. In this study, a sensor fail operational control strategy for autonomous driving system is proposed considering the camera fail. The proposed method estimates the driving environment such as ego vehicle and surrounding vehicles’ movement and road shape by using radar and GPS. And then, the system predicts the optimal path to avoid the crash and drives the vehicle until the driver take over the control priority. The predicted optimal path is based on the recognized information, the road shape and surrounding vehicles are mapped into the 8-bit gray scale image and the desired vector for the ego vehicle’s movement is determined by the maximum intensity density tracing method. The desired vehicle path is followed by the acceleration/ deceleration and the steering control, respectively..