• 자동차안전학회지
• /
• 제12권3호
• /
• pp.34-42
• /
• 2020

ADAS (Advanced Driver Assistance Systems) uses sensors such as camera, radar, lidar and GPS (Global Positioning System). Among these sensors, the camera has many advantages compared with other sensors. The reason is that it is cheap, easy to use and can identify objects. In this paper, therefore, a theoretical formula was proposed to obtain the distance from the vehicle's front wheel to the lane using a monocular camera. And the validity of the theoretical formula was verified through the actual vehicle test. The results of the actual vehicle test in scenario 4 resulted in a maximum error of 0.21 m. The reason is that it is difficult to detect the lane in the curved road, and it is judged that errors occurred due to the occurrence of significant yaw rates. The maximum error occurred in curve road condition, but the error decreased after lane return. Therefore, the proposed theoretical formula makes it possible to assess the safety of the LKA system.

• 대한교통학회지
• /
• 제6권1호
• /
• pp.43-53
• /
• 1988

This study is to find the proper method of estimating urban road traffic capacity. To estimate road traffic capacity, the following methods are chosen ; 1) crossing point of Q-V and S-V, 2) critical velocity and density of Q-V-K model, 3) V-K model with density parameter. The density estimated through S-V relation is 174 veh./km. The methods used in this paper yields more stable values with 2286 veh./h/ in average. The estimated average capacity by three methods are 2272 veh./h. in multilane road. 2411 veh./h in three lane road and 2185 veh./h. in two lane road.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 1996년도 The Korean Institute of Navigation 1996년도 한·중 국제학술 심포지움 및 추계학술발표회 논문집
• /
• pp.31-36
• /
• 1996

It is important to measure the vehicle flow in controlling the traffic system. This report deals with a traffic flow measurement system using the differential spatial filters. This system can measure the velocity the length and height profile of the vehicle. The detector is located above the traffic lane. This provides the system with the following advantages : one is that each lane can be monitored without an influence of the other lanes the other is that the system construction is simple and can be set easily.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• 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.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 추계학술대회 논문집
• /
• 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.

• 한국가스학회지
• /
• 제26권5호
• /
• pp.58-65
• /
• 2022

Gas explosion accidents could cause a catastrophe. we need specialized and systematic accident investigation techniques to shed light on the cause and prevent similar accidents. In this study, we had performed LPG explosion simulation using AUTODYN which is the commercial explosion program and predicted the damage characteristics of the structures by LNG explosive power. In the first step, we could get LPG's physical and chemical explosion properties by calculation using TNT equivalency method. And then, by applying TNT equivalency value about the explosion limit concentration of LPG on the 2D-AUTODYN simulation, we could get the explosion pressure wave profiles (explosion pressure, explosion velocity, etc.). In the last step, we performed LPG explosion simulation by applying to the explosion pressure wave profiles as the input data on the 3D-AUTODYN simulation. As a result, we had performed analyzing of the explosion characteristics of LPG in accordance with concentration through the 3D-AUTODYN simulation in terms of the explosion pressure behavior and structure destruction and damage behavior. The analyses showed that the generated stresses of the structures were lower than the compressive strengths in cases 1(two lane) and 2(four lane), while the generated stress in case 3(six lane) was 8.68e3 kPa, which exceeded the compressive strength of 5.89e3 kPa.

• 한국항행학회논문지
• /
• 제16권6호
• /
• pp.1101-1108
• /
• 2012

본 논문에서는 형태학적 처리와 에지 가반 영역 분할을 이용해 환경변화에 강인한 실시간 차선 검출 알고리즘을 제안한다. 매 프레임마다 가장 적절한 임계값을 적용시키기 위해 적응적 임계값을 사용하고 투사변환을 통해 영상의 왜곡을 보정한다. 이 후, 관심영역을 지정하고 에지를 검출해 실시간적으로 차선을 검출한다. 형태학적 처리의 유무에 따른 차선 검출 정확도와 연산 속도를 비교한다. 실험 결과 제안한 알고리즘을 통해 98.8%의 차선 검출율과 프레임 당 36.72ms의 실시간 처리가 가능함을 확인하였다.

• 대한교통학회지
• /
• 제22권1호
• /
• pp.7-18
• /
• 2004

국내에서는 복잡하고 심각해진 도시교통난을 해소하기 위한 대안으로 1981년부터 교통체계관리 기법 중 가변차로제를 도입하여 현재 서울을 비롯한 주요 도시에서 운용하고 있다. 그러나 가변차로제 시행에 따른 운영 효과에 대한 연구는 미진한 편이고, 적용함에 있어서 일반적인 경험치를 따른 설치기준을 이용하여 가변차로제를 시행하고 있다. 따라서, 본 연구에서는 현재 서울시에서 운영되고 있는 가변차로 구간에 대한 사례조사를 통해 컴퓨터 시뮬레이션을 이용하여 가변차로 수행에 따른 효과를 분석하고, 그 시행의 효율성을 높기 위한 방안으로서, 국내의 교통여건에 부합하는 가변차로제의 설치기준을 재설정 하였다. 가변차로제 시행 효과 분석을 위한 효과측정기준으로 평균지체와 연료소모량을 선정하였다. TRANSYT-7F 컴퓨터 시뮬레이션을 이용하여, 가변차로로 유입 유출되는 v/c별 교통량과 방향별 교통량비율, 그리고 기하구조측면으로 가변차로수와 가변차로 구간 내에서의 좌회전의 허용여부 이 네 가지 영향요소의 변화에 따른 각각의 상황별 가변차로제 시행효과를 분석하였다. 시뮬레이션 결과 왕복 6차로 구간의 경우 현재 가변차로제의 설치기준으로 제시된 방향별 교통량비율보다 더 작은 차이에서도 가변차로제 실시 효과의 의미를 부여 할 수 있는 것으로 나타났다.

• 자동차안전학회지
• /
• 제13권2호
• /
• pp.35-41
• /
• 2021

In this study, improved path tracking control algorithm based on pure pursuit algorithm is newly proposed by using improved lane detection algorithm through real time post-processing with interpolation methodology. Since the original pure pursuit works well only at speeds below 20 km/h, the look-ahead distance is implemented as a sigmoid function to work well at an average speed of 45 km/h to improve tracking performance. In addition, a smoothing filter was added to reduce the steering angle vibration of the original algorithm, and the stability of the steering angle was improved. The post-processing algorithm presented has implemented more robust lane recognition system using real-time pre/post processing method with deep learning and estimated interpolation. Real time processing is more cost-effective than the method using lots of computing resources and building abundant datasets for improving the performance of deep learning networks. Therefore, this paper also presents improved lane detection performance by using the final results with naive computer vision codes and pre/post processing. Firstly, the pre-processing was newly designed for real-time processing and robust recognition performance of augmentation. Secondly, the post-processing was designed to detect lanes by receiving the segmentation results based on the estimated interpolation in consideration of the properties of the continuous lanes. Consequently, experimental results by utilizing driving guidance line information from processing parts show that the improved lane detection algorithm is effective to minimize the lateral offset error in the diverse maneuvering roads.

• 한국컴퓨터정보학회논문지
• /
• 제15권8호
• /
• pp.31-39
• /
• 2010

본 논문은 도로 영상에서 안개의 존재 여부를 판단하여 미디언 필터를 기반으로 하는 Retinex 알고리즘을 적용하고 영상을 개선한 후 최종적으로 차선을 검출하는 알고리즘을 제안한다. 영상 내에서 특정 관심 영역을 지정하고 해당 영역에서의 히스토그램을 분석하여 안개의 존재 여부를 판단한다. 안개 낀 영상으로 판단되는 경우 영상의 화질개선을 위해 미디언 필터를 기반으로 하는 Retinex 알고리즘을 이용해 대비도를 향상시킨다. 기존의 Retinex 알고리즘은 가우시안 필터를 적용하기 때문에 연산에 많은 시간이 걸리며, 특히 도로의 안개 영상에서는 차선의 특징이 두드러지지 않았다. 본 논문에서는 가우시안 필터를 미디언 필터를 바꿈으로써 도로의 안개 영상에 대해서 강인한 대비도 향상 효과를 얻을 수 있었다. 개선된 영상에서 차선에 대한 정보를 획득하기 위해서 이중 임계치를 이용한 이진화를 수행하고 라벨링을 통해서 검출된 차선의 크기, 방향 등의 정보를 계산하여 최종적인 차선을 검출한다. 제안한 알고리즘의 성능은 다양한 환경의 도로를 주행하면서 획득한 연속적인 영상들에 적용함으로써 제안하는 알고리즘의 효율성 및 우수성을 평가하였다.