• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.687-690
• /
• 2000

Lately, many studies have been progressed for the protection human's lives and property as holding in check accidents happened by human's carelessness or mistakes. One part of these is the development of an autonomouse vehicle. General control method of vision-based autonomous vehicle system is to determine the navigation direction by analyzing lane images from a camera, and to navigate using proper control algorithm. In this paper, characteristic points are abstracted from lane images using lane recognition algorithm with sobel operator. And then the vehicle is controlled using two proposed auto-steering algorithms. Two steering control algorithms are introduced in this paper. First method is to use the geometric relation of a camera. After transforming from an image coordinate to a vehicle coordinate, a steering angle is calculated using Ackermann angle. Second one is using a neural network algorithm. It doesn't need to use the geometric relation of a camera and is easy to apply a steering algorithm. In addition, It is a nearest algorithm for the driving style of human driver. Proposed controller is a multilayer neural network using Levenberg-Marquardt backpropagation learning algorithm which was estimated much better than other methods, i.e. Conjugate Gradient or Gradient Decent ones.

• International Journal of Automotive Technology
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2002

A new control method far vision-based autonomous vehicle is proposed to determine navigation direction by analyzing lane information from a camera and to navigate a vehicle. In this paper, characteristic featured data points are extracted from lane images using a lane recognition algorithm. Then the vehicle is controlled using new Levenberg-Marquardt neural network algorithm. To verify the usefulness of the algorithm, another algorithm, which utilizes the geometric relation of a camera and vehicle, is introduced. The second one involves transformation from an image coordinate to a vehicle coordinate, then steering is determined from Ackermann angle. The steering scheme using Ackermann angle is heavily depends on the correct geometric data of a vehicle and a camera. Meanwhile, the proposed neural network algorithm does not need geometric relations and it depends on the driving style of human driver. The proposed method is superior than other referenced neural network algorithms such as conjugate gradient method or gradient decent one in autonomous lateral control .

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.2
• /
• pp.44-52
• /
• 2019

In this study a safety evaluation method is presented for a ADAS vehicle to be tested in collision situation when multiple vehicles are present on a single lane. Test scenarios are developed based on Euro-NCAP assessment scenarios, accident database and related simulation results in previous works. An automated evaluation system that is called as the K-target mover is used for active safety evaluation experiments. The experiments are conducted with two types of tests. First, the rear-end collision tests with 25% and 50% overlap for the test vehicle and target vehicle are conducted with the two kinds of test vehicles. On the other hand, the rear-end collision tests which include multiple vehicles in a single lane with 25% and 50% overlaps, are also conducted. Experimental results show that the test vehicles with ADAS cannot recognize the collision situation sometimes in the developed test scenarios, even in the case that the test vehicle showed stable performance in the simple overlap scenarios.

• Journal of Environmental Science International
• /
• v.14 no.12
• /
• pp.1081-1085
• /
• 2005

This study is carried out for obtaining the basic materials for presentation of creation and desirable management of urban roadside trees through analyse the existence effect of trees on people who operate th commercial areas along the streets. Roadside tree and green areas are recognized comfort space in addition to simple planting area. Therefore various trees and flowering plants should be introduced in addition to roadside facilities for convenience. Planted roadside trees should be maintained. We will propose an method that residents plant and manage the trees and flowering plants on the two lane of one way road. However main lines more than four lane of one way have more public property beside the residents space. Therefore these should be maintained mainly by related government agencies.

• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1171-1181
• /
• 2018

Most simulated shooting systems are TDM based method and dot type laser has been used. The proposed laser pattern based simulated shooting system is a new approach. It can distinguish shooters by calculating the angle of bar shaped laser pattern by each shooter. Unlike the existing TDM method, it is possible to distinguish shooters and lanes by patterns so that there is no time division restriction like TDM method. It is also possible to recognize overlapped impact points of laser patterns launched by multiple shooters. After the laser pattern based simulated shooting system was implemented, general shot and overlapped shot were tested for each lane. Through experiments, we confirmed the possibility of continuous shooting. In addition, it is possible to separate the pattern by each lane, and 100% recognition result was obtained even if impact points overlapped.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.303-304
• /
• 2006

This paper proposes detection method of vehicles using camera for auto-vehicle-system. Detection method is based on shadow detection and symmetric feature of vehicle. This method consists of three part. First is lane detection. By lane detection, we can reduce the area for vehicle detection. Second part is shadow detection. Shadow has information of vehicle width and position. Third part is symmetry. This feature is helpful for confirming the vehicle.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.332-333
• /
• 2018

본 논문에서는 딥러닝 기반의 주행 차로 인식 기법을 활용한 차선 변경 검출 기술을 제안한다. 제안한 방법은 주행 차로, 좌우 차로, 차량 등 3 종의 이미지 데이터를 학습, 검증, 실험 데이터로 나눠 활용하였다. 주행 차로 및 차선 변경 인식을 위하여 변형된 AlexNet 모델을 개발하였다. 실험 결과 주행 차로 69.45%, 좌우 차로 66.9%, 차량 76.4%의 인식률 결과를 보여 기존 패턴인식 방법과 비교하여 우수한 결과를 보였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.1
• /
• pp.186-195
• /
• 2017

Recently, autonomous vehicles have been studied actively. There are various technologies such as ITS, Connected Car, V2X and ADAS in order to realize such autonomous driving. Among these technologies, it is particularly important to recognize where the vehicle is on the road in order to change the lane and drive to the destination. Generally, it is done through GPS and camera image processing. However, there are limitations on the reliability of the positioning due to shaded areas such as tunnels in the case of GPS, and there are limitations in recognition and positioning according to the state of the road lane and the surrounding environment when performing the camera image processing. In this paper, we propose that LED lights should be installed for autonomous vehicles in tunnels which are shaded area of the GPS. In this paper, we show that it is possible to measure the position of the current lane of the autonomous vehicle by analyzing the color temperature after constructing the tunnel LED lighting simulation environment which illuminates light of different color temperature by lane. Based on the above, this paper proposes a lane positioning technique using tunnel LED lights.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1107-1109
• /
• 1996

In this paper, we discuss the automatic recognition system of vehicle types and licence plate numbers using artificial neural networks, which will be used as vehicle identifier. We confine to expose the vehicle licence number for violating bus lane and stolen cars. Therefore, the vehicle height, width and distribution profile are used as the feature parameters of vehicle type. This system is composed of two parts: one is an image preprocessor of vehicle images and the other one is a pattern classifier by neural networks. The experimental results show that our method has good results for the recognition of vehicle types and numbers.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.34.6-34
• /
• 2002

1. Introduction 2. System Configuration 2.1 Control System 2.1.1 Longitudinal control 2.1.2 Lateral control 2.2 Sensor System 2.2.1 Photo interrupt 2.2.2 Ultrasonic sensor 2.3 Vision system 2.4 Communication system 2.4.1 Data communication 2.4.2 Image Communication 3. Test and Result 3.1 Vision test 3.2 Ultrasonic sensor test 4. Conculsion. Acknowledgment References.