• Title/Summary/Keyword: Lanes

검색결과 574건 처리시간 0.023초

도로안전시설용 시선유도봉의 신뢰성 평가 (Reliability Assessment of Tubular Markers Used for Road Safety Facilities)

  • 구현진;윤예석
    • 한국신뢰성학회지:신뢰성응용연구
    • /
    • 제12권2호
    • /
    • pp.91-103
    • /
    • 2012
  • Tubular markers for road safety facilities are used to lead the driver's sight line and separate the lanes on the road. Such tubular markers are usually installed on the road and frequently hit by vehicles, they are accordingly requested to assure the product durability. The traditional evaluation method of tubular markers include only quality tests of the material properties. However, most of consuming agencies in charge of road management at fields have proposed problems on long-term performance of the products hit by vehicles under various weather conditions. Therefore, the objectives of this study are to develop the reliability test methods and equipments to simulate the product failures of tubular markers due to vehicle collision and wheel compression and the delamination and discoloration of reflection sheets attached on the surface of the products under high and low temperatures.

Behavior analysis of aerial tunnel maintenance truss platform with high tensile steel UL-700

  • Lee, Dongkyu
    • Steel and Composite Structures
    • /
    • 제24권3호
    • /
    • pp.383-391
    • /
    • 2017
  • The goal of this study is to investigate structural analysis and behaviors of an innovative aerial work platform truss frame whose ductility is improved by using high strength-steel UL-700. The present space truss frame can move or stop through tunnels for maintenance constructions by automatic facilities and workmanship within standardized limited building lines of tunnel. Most of all, this method overcomes problematic, which is to block cars during construction periods, seriously, of typical methods like as using truck and scaffolds for tunnel maintenance. According to evaluated appropriate design results of space truss frames of numerical examples by using a commercial MIDAS GEN program, it is verified that design parameters such as layered size, cross-sectional size, and steel material of the present space truss frame are determined to depend on characteristics such as lanes or shape of road tunnels.

Speed Sign Recognition Using Sequential Cascade AdaBoost Classifier with Color Features

  • Kwon, Oh-Seol
    • Journal of Multimedia Information System
    • /
    • 제6권4호
    • /
    • pp.185-190
    • /
    • 2019
  • For future autonomous cars, it is necessary to recognize various surrounding environments such as lanes, traffic lights, and vehicles. This paper presents a method of speed sign recognition from a single image in automatic driving assistance systems. The detection step with the proposed method emphasizes the color attributes in modified YUV color space because speed sign area is affected by color. The proposed method is further improved by extracting the digits from the highlighted circle region. A sequential cascade AdaBoost classifier is then used in the recognition step for real-time processing. Experimental results show the performance of the proposed algorithm is superior to that of conventional algorithms for various speed signs and real-world conditions.

퍼지신경망을 이용한 도로 씬의 차선정보의 잡음도 판별 (Fuzzy Neural Network-Based Noisiness Decision of Road Scene for Lane Detection)

  • 이운근;백광렬;권석근;이준웅
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2000년도 추계학술대회 논문집 학회본부 D
    • /
    • pp.761-764
    • /
    • 2000
  • This paper presents a Fuzzy Neural Network (FNN) system to decide whether or not the right information of lanes can be extracted from gray-level images of road scene. The decision of noisy level of input images has been required because much noises usually deteriorates the performance of feature detection based on image processing and lead to erroneous results. As input parameters to FNN, eight noisiness indexes are constructed from a cumulative distribution function (CDF) and proved the indexes being classifiers of images as the good and the bad corrupted by sources of noise by correlation analysis between input images and the indexes. Considering real-time processing and discrimination efficiency, the proposed FNN is structured by eight input parameters, three fuzzy variables and single output. We conduct much experiments and show that our system has comparable performance in terms of false-positive rates.

  • PDF

교통용량 개정에 따른 고속도로 공사구간의 서비스 수준에 대한 연구 (A Study on Level-of-Service Changes of Expressway in Accordance with the Revision of Traffic Capacity at Work-Zone)

  • 류성우;박권제;한승환;조윤호
    • 한국도로학회논문집
    • /
    • 제16권3호
    • /
    • pp.109-117
    • /
    • 2014
  • PURPOSES : This study analyzes the available working time at work-zone on the Expressway in accordance to the new capacity manual. METHODS : Sensitivity analysis on variables were conducted to calculate the adjusted capacity at work-zone based on previous researches. RESULTS : The main factors which affect available working time at the work-zone were its capacity, number of lanes, terrain and lane width. Other factors have minimal effect on the available working time. Based on the analysis, a calendar of lane closures was suggested. CONCLUSIONS : A series of studies concluded that the capacity at work-zone in the new capacity manual reduced to 76-82% of the existing manual. As such, the available working time decreased. Furthermore, the factors affecting the available working time needs to be considered when making a plan to rehabilitate the distressed pavement.

신호등 교차로에서의 지체예측에 관한 연구 (A Model for the Estimation of Delay Signalized Intersections)

  • 이철기;이승환
    • 대한교통학회지
    • /
    • 제10권1호
    • /
    • pp.41-54
    • /
    • 1992
  • The purpose of this thesis is to construct a model to estimate the delay that vehicles arriving randomly will be experienced at an isolated singalized intersection. To do this the following objectives are set in this study: (i) An what distance a random arrival pattern occurs after a platoon of vehicles are dis-charged from the stop line; (ii) A model which estimates the average delay per through-vehicle with respect to the de-gree of saturation; and (iii) The relation between the stepped delay and average approach delay per vehicle. The following are the findings of this study: (i) A random arrival pattern on the first second and third lanes occur 300,400 and 300m downstream from stop line rdspectively. A random arrival pattern on lane group occurs 500m downstream from the stop line ; (ii) A model for the estimation of approach delay has been developed in such a way that up to x=0.7 the delay increases linearly and beyond 0.7 the delay increases rapidly in a form of second order polynomial due to high degree of saturation : and (iii) Approach delay equals approximately 1.21 times of stopped delay.

  • PDF

Diagonally-reinforced Lane Detection Scheme for High-performance Advanced Driver Assistance Systems

  • Park, Mingu;Yoo, Kyoungho;Park, Yunho;Lee, Youngjoo
    • JSTS:Journal of Semiconductor Technology and Science
    • /
    • 제17권1호
    • /
    • pp.79-85
    • /
    • 2017
  • In this paper, several optimizations are proposed to enhance the quality of lane detection algorithms in automotive applications. Considering the diagonal directions of lanes, the proposed limited Hough transform newly introduces image-splitting and angle-limiting schemes that relax the number of possible angles at the line voting process. In addition, unnecessary edges along the horizontal and vertical directions are pre-defined and removed during the edge detection procedures, increasing the detecting accuracy remarkably. Simulation results shows that the proposed lane recognition algorithm achieves an accuracy of more than 90% and a computing speed of 92 frame/sec, which are superior to the results from the previous algorithms.

단일 시선 기하구조 기반 주행차선 및 장애물 인식 알고리듬 (A Recognition Algorithm for Vehicle Road Lanes and Obstacles Based on Single View Geometric Constitution)

  • 김정현;송성희;정용배;서경호;김태효
    • 한국지능시스템학회:학술대회논문집
    • /
    • 한국퍼지및지능시스템학회 2004년도 추계학술대회 학술발표 논문집 제14권 제2호
    • /
    • pp.81-84
    • /
    • 2004
  • 본 논문에서는 1대의 CCD카메라로 주행 중 차선과 선행차량을 인식하고 선행차량까지의 거리를 실시간으로 계측하는 알고리즘을 제시하였다. 도로와 카메라간의 기하구조를 분석하여 사영행렬을 추출하였고, 주행 중 차간 거리를 실시간으로 계측하는데 이용하였다. 또한 차선 인식을 위해서 Hough Transform을 적용하여 처리시간을 단축하였다. 도로상의 장애물은 인식된 주행차선 내로 한정하였고 도로 영상에서 수평에지성분을 구한 후 히스토그램 투영을 적용하여 장애물을 검출하였다. 거리가 점차 멀어질수록 계측오차가 증가함을 볼 수 있었으나 기존의 방법에 비하여 주행 중에 운전자가 장애물을 판단하여 제동을 취할 수 있는 정도의 유효한 오차특성을 보였다.

  • PDF

도심 주거지의 실태와 개발 장애요인 분석 (The Analysis of the Situation of Residential Area and Difficulties in Developing)

  • 임준홍;김한수
    • 한국주거학회논문집
    • /
    • 제14권1호
    • /
    • pp.51-59
    • /
    • 2003
  • This study is to analyze the situation of residential area in Down Town and to research any factor of difficulty in developing residential area. First, we can summarize briefly in consequence of analyzing the residential environment classified with apartment and independent house in Down Town. 1) The apartment houses located in Down Town were constructed long ago on a small scale. The field investigation shows that parking lots are not enough and there are many spaces used inappropriately. 2) Each detached house was too old and built in narrow spaces. The irregular narrow lanes between houses also cause problems in walking and parking. And empty houses are found in that area. Second, the brief results of analyzing difficulties in developing the residential area in Down Town are as follows. 1) The land and buildings have difficulty in reconstruction because of the deterioration. 2) The economical efficiency is low though it is developed as a residential area. 3) There are some factors that they don't like to live in Down Town. 4) The law system is not enough to support the development of the residential area in Down Town

무어-네이버 에지추적 알고리즘을 이용한 차선검출기법 (Lane Detection Using Moore-Neighbor Edge Trace Algorithm)

  • 김병현;한영준;한헌수
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2008년도 하계종합학술대회
    • /
    • pp.857-858
    • /
    • 2008
  • This paper proposes a new fast algorithm that detects the lanes on the road using Moore-Neighbor edge trace algorithm, which traces the edge elements by searching the connectivity in eight direction window. The detected line components are connected if they have the same orientation on the same line. The proposed algorithm is faster than other conventional algorithms since it tests only the connectivities of the line segments. The performance of the proposed algorithm has tested by the experiments to test how fast and accurate.

  • PDF