• 제어로봇시스템학회논문지
• /
• 제7권3호
• /
• pp.238-245
• /
• 2001

This paper describes a method for detecting a close leading vehicle using the contour of the vehi-cles rear wheels. The contour of a leading vehicles rear wheels in 속 front road image from a B/W CCD camera mounted on the central front bumper of the vehicle, has vertical components and can be discerned clearly in contrast to the road surface. After extracting positive edges and negative edges using the Sobel op-erator in the raw image, every point that can be recognized as a feature of the contour of the leading vehicle wheel is determined. This process can detect the presence of a close leading vehicle, and it is also possible to calculate the distance to the leading vehicle and the lateral deviation angle. This method might be useful for developing and LSA (Low Speed Automation) system that can relieve drivers stress in the stop-and-go traffic conditions encoun-tered on urban roads.

• 전기학회논문지
• /
• 제60권1호
• /
• pp.93-99
• /
• 2011

A PRT vehicle's control method is presented in this paper. In the asynchronous vehicle control system, vehicles follow their leading vehicles. Leading vehicles are defined differently among the different types of track. The main topic of this paper is to present a method to define the leading vehicle among different types of track and the calculation algorithm of the safety length the following vehicle must maintain. Simulation program is developed using the algorithm and the results of the test run are presented. An asynchronous PRT vehicle control algorithm was presented by Szillat in the paper "A low level PRT Microsimulation, Dissertation, University of Bristol, 2001". But it is different from the algorithm in this paper. In the algorithm proposed by Markus, vehicles in the merging track are controlled synchronously, and its safety distance between the leading and the following car is evaluated after the establishment of the complicated future time-location table instead of simple equations proposed in this paper.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1999년도 제14차 학술회의논문집
• /
• pp.181-184
• /
• 1999

Leading vehicle states are useful and essential elements in adaptive cruise control (ACC) system, collision warning (CW) and collision avoidance (CA) system, and automated highway system (AHS). There are many approaches in ACC using Kalman filter. Mostly only distance to leading vehicle and velocity difference are estimated and used for the above systems. Applications in road vehicle in curved road need to obtain more informations such as yaw angle, steering angle which can be estimated using vision system. Since vision system is not robust to environment change, we used Kalman filter to estimate distance, velocity, yaw angle, and steering angle. Application to active tracking of target vehicle is shown.

• 대한임베디드공학회논문지
• /
• 제7권4호
• /
• pp.163-172
• /
• 2012

A driver assistance system is critical to improve a convenience and stability of vehicle driving. Several systems have been already commercialized such as adaptive cruise control system and forward collision warning system. Efficient vehicle detection is very important to improve such driver assistance systems. Most existing vehicle detection systems are based on a radar system, which measures distance between a host and leading (or oncoming) vehicles under various weather conditions. However, it requires high deployment cost and complexity overload when there are many vehicles. A camera based vehicle detection technique is also good alternative method because of low cost and simple implementation. In general, night time vehicle detection is more complicated than day time vehicle detection, because it is much more difficult to distinguish the vehicle's features such as outline and color under the dim environment. This paper proposes a method to detect vehicles at night time using analysis of a captured color space with reduction of reflection and other light sources in images. Four colors spaces, namely RGB, YCbCr, normalized RGB and Ruta-RGB, are compared each other and evaluated. A suboptimal threshold value is determined by Otsu algorithm and applied to extract candidates of taillights of leading vehicles. Statistical features such as mean, variance, skewness, kurtosis, and entropy are extracted from the candidate regions and used as feature vector for SVM(Support Vector Machine) classifier. According to our simulation results, the proposed statistical feature based SVM provides relatively high performances of leading vehicle detection with various distances in variable nighttime environments.

• 한국정보처리학회논문지
• /
• 제7권9호
• /
• pp.3037-3047
• /
• 2000

본 논문에서는 커러영상처리로 차량 후면에 위치하고 붉은색을 띄는 미등과 브레이크등을 이용하여 저속주행환경에서 근거리 전방차량을 추적하는 방법에 대해 설명한다. HSV 컬러모델로 변환된 컬러영상에서 미등과 브레이크등의 컬러특징을 이용하여 후보영역을 분할한 후, 미등과 브레이크등 패턴의 기하학적 특징과 위치적 특징을 이용하여 한 쌍의 미등 혹은 브레이크등을 탐지한다. 탐지된 등의 위치를 이용하여 전방차량의 위치를 측정하고 연속적으로 추적한다. 또한, 등 영역내의 HSV 컬러요소 변화를 측정하여 전방차량의 브레이크 사용여부를 판단한다. 도심지의 도로영상을 이용한 실험에서 성공적으로 근거리 전방차량을 추적할 수 있었으며, 주간보다 야간에서 효과적으로 적용될 수 있었다. 또한 본 알고리즘이 구현된 컬러비전시스템을 무인자동차 KAV-III(Korea Autonomous Vehicle-III)에 탑재하여 야간에 자동으로 전방차량을 15km/h의 속도로 따라갈 수 있는 결과를 얻었다. 이 방법은 도심지에서 가다서다를 반복하는 저속주행환경에서 차량 스스로 운전하여 운전자의 부담을 줄일 수 있는 LSA(Low Speed Automation)시스템 개발에 적용될 수 있을 것이다.

• 자동차안전학회지
• /
• 제9권4호
• /
• pp.26-31
• /
• 2017

The current autonomous vehicle competitions are dominated by a few leading research institutions and universities. Since the leading research groups have been able to accumulate their knowledge and to develop their own algorithms for autonomous vehicle for many years, the technology gap seems too big for other followers to catch up with. On the other hand, recent researches predict that there would be a sharp rise in demand for engineers with background in autonomous vehicle technology. Therefore, it would be warranted to further expand the base of the academia and autonomous vehicle industry. In an effort to achieve this goal, it would be beneficial to hold a new format of autonomous vehicle competition event where undergraduate students can play a leading role. So, this study is to analyze the current autonomous vehicle competitions and thus to establish a strategic plan to develop a unique and improved competition event. This study investigates the pros and cons of the domestic and international autonomous vehicle competitions. Based on the analysis for the current autonomous vehicle competitions, the authors suggest a strategic plan to initiate an autonomous vehicle competition. To implement the aforementioned strategic plan, it is necessary to develop a systematic environment where the education and communication are actively available. Through the strategic plan the authors propose, the newly launching autonomous vehicle competition will able to encourage the undergraduate students and professors to dive in the cutting-edge technology thereby increasing technology competitiveness.

• 한국자동차공학회논문집
• /
• 제16권6호
• /
• pp.134-140
• /
• 2008

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.

• 한국자동차공학회논문집
• /
• 제25권1호
• /
• pp.51-59
• /
• 2017

In 2014, there were approximately 4,762 fatalities on Korean roads. The fatality rate has decreased by 6.5 %, as compared to that of the previous year. The pedestrian-vehicle fatalities (1,795) have also decreased by 6 % over the previous year. However, the percentage of the pedestrian fatalities has increased from 37.9 % to 38.7 % during the same period. This is why further research is required, even though the KNCAP pedestrian safety assessment and KMVSS for pedestrian protection currently exist. This paper studied the Upper Legform to Bonnet Leading Edge Test at the front of the vehicles, which has not been introduced yet in Korea. The test method and procedure of the new BLE test in the Euro NCAP test protocol have been reviewed, and the physical tests on SUV and sedan with different bonnet leading edge heights have also been conducted and reviewed. In addition, the test results and characteristics have been analyzed via comparison with the former BLE test and each vehicle type.

• Advances in aircraft and spacecraft science
• /
• 제7권1호
• /
• pp.1-17
• /
• 2020

In this paper, a new model-based Fault Detection and Diagnosis (FDD) method for an agile supersonic flight vehicle is presented. A nonlinear model, controlled by a classical closed loop controller and proportional navigation guidance in interception scenario, describes the behavior of the vehicle. The proposed FDD method employs the Inertial Navigation System (INS) data and nonlinear dynamic model of the vehicle to inform fins damage to the controller before leading to an undesired performance or mission failure. Broken, burnt, unactuated or not opened control surfaces cause a drastic change in aerodynamic coefficients and consequently in the dynamic model. Therefore, in addition to the changes in the control forces and moments, system dynamics will change too, leading to the failure detection process being encountered with difficulty. To this purpose, an equivalent aerodynamic model is proposed to express the dynamics of the vehicle, and the health of each fin is monitored by the value of a parameter which is estimated using an adaptive robust filter. The proposed method detects and isolates fins damages in a few seconds with good accuracy.

• Journal of Biosystems Engineering
• /
• 제27권5호
• /
• pp.409-416
• /
• 2002

This study was conducted to develop a vehicle, leading or following a worker at a certain distance to assist laborious transporting works in greenhouses. A prototype vehicle, which consisted of the rear driving, the front steering and the console units, was designed and tested in the ideal indoor conditions. Results of this study were summarized as following: 1. The driving unit was designed to travel at the speed ranges of 0.3∼0.8 m/sec depending on the operating modes with a maximum payload of 100 kg. 2. The console unit consisted of a main-board including a 80C196KC microprocessor and peripheral devices, a power-board and safety interlock. Worker-leading, and following modes were available in automatic and manual modes. 3. Steering was achieved by turning the steering motor against the sensed direction. Proper steering angles for correcting travel direction were determined as 5 and 9 degrees when sensing cultivation beds and plants, respectively.